Record owner-confirmed successful R4 SEGMENT finals submission

EVALUATION.json

@@ -2098,7 +2098,7 @@
     "unique_question_ids": 533
   },
   "current_candidate_runtime_qualification": "passed_complete_agreed_local_matrix_not_platform",
-  "current_platform_status": "R4 official execution/result not established by this local packet. Prior owner-reported generic failure has no authenticated cause or artifact join here.",
+  "current_platform_status": "Owner confirmed successful R4 finals submission, with no errors reported, on September 14, 2026. Exact submission time, platform UUIDs/resources/logs and final score/ranking were not supplied.",
   "docker_config_sha256": "3f43fce1081dc5db454447dbe4678947e5cefec014635e611d8d1032a0ac71c4",
   "exact_docker20": {
     "answers": 20,
@@ -2199,7 +2199,7 @@
     "zip500_capacity_inferred": false
   },
   "exact_docker_zip_runtime_accepted": true,
-  "final_submission_performed": false,
+  "final_submission_performed": true,
   "fine_capability_5b": {
     "candidate_minus_reference_equal_video_percentage_points": -16.881419234360408,
     "candidate_minus_reference_micro_percentage_points": -17.741935483870968,
@@ -4061,12 +4061,16 @@
     "status": "passed_local_complete_runtime_matrix_archive_load_not_platform"
   },
   "schema": "segment-private-model-evaluation-presentation/1",
-  "scope": "The completed development comparison is between two registered serving implementations under the same fixed Qwen3.5-27B judge and 20-case batching protocol: candidate 2373/4000 (59.325%) versus named reference 1940/4000 (48.500%), +10.825 percentage points. Strict sensitivity is 2334/3940 versus 1906/3940. All ten original-source-video differences are positive; 5b causal consequence reasoning regressed 17.742 micro points on 62 cases from six sources. These are adaptively used development results with inherited training/data-exposure limits, not an independent holdout, an official finals score or an all-candidate ranking. The registered local scorer passed14 convenience controls (6positive,8negative). These check response/parser boundaries; they do not estimate organizer-judge agreement, real-question false-positive rates, official calibration or a finals score. All 4,000 were not run through a Docker archive. Source-derived routing equality on the 4,000 intervals 1–299s does not by itself transfer these scores to new image bytes.",
+  "scope": "The completed development comparison is between two registered serving implementations under the same fixed Qwen3.5-27B judge and 20-case batching protocol: candidate 2373/4000 (59.325%) versus named reference 1940/4000 (48.500%), +10.825 percentage points. Strict sensitivity is 2334/3940 versus 1906/3940. All ten original-source-video differences are positive; 5b causal consequence reasoning regressed 17.742 micro points on 62 cases from six sources. These are adaptively used development results with inherited training/data-exposure limits, not an independent holdout, an official finals score or an all-candidate ranking. The registered local scorer passed14 convenience controls (6positive,8negative). These check response/parser boundaries; they do not estimate organizer-judge agreement, real-question false-positive rates, official calibration or a finals score. All 4,000 were not run through a Docker archive. Source-derived routing equality on the 4,000 intervals 1\u2013299s does not by itself transfer these scores to new image bytes.",
   "strict": {
     "candidate_correct": 2334,
     "cases": 3940,
     "reference_correct": 1906
   },
   "successful_organizer_tryout_received": false,
-  "zip_runtime_status": "Exact retained500 ZIP locally accepted at4GiB and16GiB; platform scratch quota remains unknown."
+  "zip_runtime_status": "Exact retained500 ZIP locally accepted at4GiB and16GiB; platform scratch quota remains unknown.",
+  "final_submission_evidence_type": "direct_owner_confirmation",
+  "owner_confirmation_date": "2026-09-14",
+  "current_submission_record": "SUBMISSION_STATUS.json",
+  "platform_qualification_evidence_scope": "Direct owner confirmation is recorded in SUBMISSION_STATUS.json. platform_qualified remains the historical independently verified qualification flag; no authenticated terminal receipt or score has been added."
 }

EVALUATION.md

@@ -1,6 +1,8 @@
 # SEGMENT evaluation evidence
 
-**R4 local runtime, archive and import checks completed; official platform qualification remains unproven.** The exact archive is `e477d307ff2e09f469d83569ec1ce8703daeef34edbba633a3f240eab955de00` (35,613,293,722 bytes), immutable generation `1789092734891901`. The build manifest is `ba9ddb1e78a45040803ae6f0e68c66de7a538f5e3e86397777e5fc2c488106b0` and configuration `3f43fce1081dc5db454447dbe4678947e5cefec014635e611d8d1032a0ac71c4`. Full compressed/raw archive verification covers all 26 ordered DiffIDs; actual same-generation classic Docker import reports config `3f43fce1081dc5db454447dbe4678947e5cefec014635e611d8d1032a0ac71c4` and no imported manifest digest. The agreed eight cases completed 9 application invocations and 1593 answer executions across 533 unique qIDs. Healthy20 and loose/ZIP500 matched saved content; reverse20 matched the same-image ordinary20, and both ZIP quotas matched the same-image loose500. Canonical repeated calls retained the exact disclosed deferrals. The mixed recovery case blanked only its declared failed questions and preserved later healthy outputs. These are bounded runtime/interface/content checks; no new semantic grade or official final result is claimed.
+**Finals submission: owner confirmed on September 14, 2026 that repaired R4 was successfully submitted for SEGMENT finals, with no errors reported.** The submitted archive SHA256 is `e477d307ff2e09f469d83569ec1ce8703daeef34edbba633a3f240eab955de00`. September 14 is the confirmation date; the actual submission time, platform UUIDs, terminal logs, score and ranking were not supplied. See [SUBMISSION_STATUS.json](SUBMISSION_STATUS.json) for the exact identity and evidence scope. The model weights, source files and immutable loading revisions are unchanged.
+
+**September 11 local qualification record: R4 runtime, archive and import checks completed.** The exact archive is `e477d307ff2e09f469d83569ec1ce8703daeef34edbba633a3f240eab955de00` (35,613,293,722 bytes), immutable generation `1789092734891901`. The build manifest is `ba9ddb1e78a45040803ae6f0e68c66de7a538f5e3e86397777e5fc2c488106b0` and configuration `3f43fce1081dc5db454447dbe4678947e5cefec014635e611d8d1032a0ac71c4`. Full compressed/raw archive verification covers all 26 ordered DiffIDs; actual same-generation classic Docker import reports config `3f43fce1081dc5db454447dbe4678947e5cefec014635e611d8d1032a0ac71c4` and no imported manifest digest. The agreed eight cases completed 9 application invocations and 1593 answer executions across 533 unique qIDs. Healthy20 and loose/ZIP500 matched saved content; reverse20 matched the same-image ordinary20, and both ZIP quotas matched the same-image loose500. Canonical repeated calls retained the exact disclosed deferrals. The mixed recovery case blanked only its declared failed questions and preserved later healthy outputs. These are bounded runtime/interface/content checks; no new semantic grade or official final result is claimed.
 
 The completed development comparison is between two registered serving implementations under the same fixed Qwen3.5-27B judge and 20-case batching protocol: candidate 2373/4000 (59.325%) versus named reference 1940/4000 (48.500%), +10.825 percentage points. Strict sensitivity is 2334/3940 versus 1906/3940. All ten original-source-video differences are positive; 5b causal consequence reasoning regressed 17.742 micro points on 62 cases from six sources. These are adaptively used development results with inherited training/data-exposure limits, not an independent holdout, an official finals score or an all-candidate ranking. The registered local scorer passed14 convenience controls (6positive,8negative). These check response/parser boundaries; they do not estimate organizer-judge agreement, real-question false-positive rates, official calibration or a finals score. All 4,000 were not run through a Docker archive. Source-derived routing equality on the 4,000 intervals 1–299s does not by itself transfer these scores to new image bytes.
 

LINEAGE.json

@@ -86,7 +86,7 @@
   "derived_annotation_current_scope_clarification": "The known derived packet contains all 13,177 listed extensions: 4,621 paraphrases, 5,217 count remints, 2,317 convention remints and 1,022 adoption rows. Exclusion of the 33,581 organizer rows is intentional, not evidence that those rows must be republished. The unresolved items are the separate private annotation URL/access/delivery receipts and complete signature provenance.",
   "forward_change": "Only tested frame_sampler; same selected models/priors/precision/rendering/generation.",
   "forward_gradient_updates": 0,
-  "full_algorithm_and_image_qualification": "R4 local runtime, archive and import checks completed; official platform qualification remains unproven. The exact archive is `e477d307ff2e09f469d83569ec1ce8703daeef34edbba633a3f240eab955de00` (35,613,293,722 bytes), immutable generation `1789092734891901`. The build manifest is `ba9ddb1e78a45040803ae6f0e68c66de7a538f5e3e86397777e5fc2c488106b0` and configuration `3f43fce1081dc5db454447dbe4678947e5cefec014635e611d8d1032a0ac71c4`. Full compressed/raw archive verification covers all 26 ordered DiffIDs; actual same-generation classic Docker import reports config `3f43fce1081dc5db454447dbe4678947e5cefec014635e611d8d1032a0ac71c4` and no imported manifest digest. The agreed eight cases completed 9 application invocations and 1593 answer executions across 533 unique qIDs. Healthy20 and loose/ZIP500 matched saved content; reverse20 matched the same-image ordinary20, and both ZIP quotas matched the same-image loose500. Canonical repeated calls retained the exact disclosed deferrals. The mixed recovery case blanked only its declared failed questions and preserved later healthy outputs. These are bounded runtime/interface/content checks; no new semantic grade or official final result is claimed. The full retained ZIP500 was qualified locally at the stated 4 GiB and 16 GiB tmpfs profiles, alongside loose500, healthy20, reversed20, default and persistent canonical calls, and controlled recovery. These fixtures do not establish the platform scratch quota, all possible input sizes, continuous resource peaks, cold-cache requirements, general order invariance, new semantic scores, independent-holdout performance or official platform success. Canonical deferrals and deliberately failed recovery rows are reduced scientific coverage. The prior R3 4 GiB eager-ZIP failure is a conditional local capacity reproduction, not proof of the organizer failure cause. Earlier images and failed attempts remain historical.",
+  "full_algorithm_and_image_qualification": "Owner-confirmed successful R4 finals submission with no errors reported on September 14, 2026; see SUBMISSION_STATUS.json. The following is the preserved September 11 local-qualification account, not a current submission-pending statement: R4 local runtime, archive and import checks completed; official platform qualification remains unproven. The exact archive is `e477d307ff2e09f469d83569ec1ce8703daeef34edbba633a3f240eab955de00` (35,613,293,722 bytes), immutable generation `1789092734891901`. The build manifest is `ba9ddb1e78a45040803ae6f0e68c66de7a538f5e3e86397777e5fc2c488106b0` and configuration `3f43fce1081dc5db454447dbe4678947e5cefec014635e611d8d1032a0ac71c4`. Full compressed/raw archive verification covers all 26 ordered DiffIDs; actual same-generation classic Docker import reports config `3f43fce1081dc5db454447dbe4678947e5cefec014635e611d8d1032a0ac71c4` and no imported manifest digest. The agreed eight cases completed 9 application invocations and 1593 answer executions across 533 unique qIDs. Healthy20 and loose/ZIP500 matched saved content; reverse20 matched the same-image ordinary20, and both ZIP quotas matched the same-image loose500. Canonical repeated calls retained the exact disclosed deferrals. The mixed recovery case blanked only its declared failed questions and preserved later healthy outputs. These are bounded runtime/interface/content checks; no new semantic grade or official final result is claimed. The full retained ZIP500 was qualified locally at the stated 4 GiB and 16 GiB tmpfs profiles, alongside loose500, healthy20, reversed20, default and persistent canonical calls, and controlled recovery. These fixtures do not establish the platform scratch quota, all possible input sizes, continuous resource peaks, cold-cache requirements, general order invariance, new semantic scores, independent-holdout performance or official platform success. Canonical deferrals and deliberately failed recovery rows are reduced scientific coverage. The prior R3 4 GiB eager-ZIP failure is a conditional local capacity reproduction, not proof of the organizer failure cause. Earlier images and failed attempts remain historical.",
   "image_compatibility_change": "R4 retains the image-owned literal SEGMENT task and the original request clocks. It stages only the selected ZIP member for each startup probe or answer, verifies that member through CRC/EOF and SHA-256, closes decoder handles, and removes the lease before continuing. Loose input remains a direct read. Model initialization is still eager. An attributed ordinary per-question exception produces empty content for that qID with measured latency and failure telemetry; successful answers are preserved and later questions continue. Unsafe or ambiguous archives, source mutation, cleanup integrity, required model initialization, environment and fixed-track failures remain fatal. The inherited precise pre-generation rules deferrals remain separately disclosed as degraded coverage. The four changed image files are the bootstrap, contract, probe entrypoint and new ZIP helper; all 51 unchanged inherited serving source files, including cap_fmt, all 50 model/prior assets, prompts, model arithmetic and generation settings remain unchanged.",
   "image_identity": {
     "added_diff_id": "ee65a0fd5c5057739b208abb4bab056ff0b874e40fd9dfa43c18acf1ddbf5e1e",
@@ -461,5 +461,6 @@
       "unique_rows": 2912
     },
     "trainable_parameters": 15335424
-  }
+  },
+  "current_submission_record": "SUBMISSION_STATUS.json"
 }

LINEAGE.md

@@ -21,7 +21,9 @@ The known derived packet contains all 13,177 listed extensions: 4,621 paraphrase
 
 ## R4 serving compatibility update
 
-R4 local runtime, archive and import checks completed; official platform qualification remains unproven. The exact archive is `e477d307ff2e09f469d83569ec1ce8703daeef34edbba633a3f240eab955de00` (35,613,293,722 bytes), immutable generation `1789092734891901`. The build manifest is `ba9ddb1e78a45040803ae6f0e68c66de7a538f5e3e86397777e5fc2c488106b0` and configuration `3f43fce1081dc5db454447dbe4678947e5cefec014635e611d8d1032a0ac71c4`. Full compressed/raw archive verification covers all 26 ordered DiffIDs; actual same-generation classic Docker import reports config `3f43fce1081dc5db454447dbe4678947e5cefec014635e611d8d1032a0ac71c4` and no imported manifest digest. The agreed eight cases completed 9 application invocations and 1593 answer executions across 533 unique qIDs. Healthy20 and loose/ZIP500 matched saved content; reverse20 matched the same-image ordinary20, and both ZIP quotas matched the same-image loose500. Canonical repeated calls retained the exact disclosed deferrals. The mixed recovery case blanked only its declared failed questions and preserved later healthy outputs. These are bounded runtime/interface/content checks; no new semantic grade or official final result is claimed.
+**Finals submission: owner confirmed on September 14, 2026 that repaired R4 was successfully submitted for SEGMENT finals, with no errors reported.** The submitted archive SHA256 is `e477d307ff2e09f469d83569ec1ce8703daeef34edbba633a3f240eab955de00`. September 14 is the confirmation date; the actual submission time, platform UUIDs, terminal logs, score and ranking were not supplied. See [SUBMISSION_STATUS.json](SUBMISSION_STATUS.json) for the exact identity and evidence scope. The model weights, source files and immutable loading revisions are unchanged.
+
+**September 11 local qualification record: R4 runtime, archive and import checks completed.** The exact archive is `e477d307ff2e09f469d83569ec1ce8703daeef34edbba633a3f240eab955de00` (35,613,293,722 bytes), immutable generation `1789092734891901`. The build manifest is `ba9ddb1e78a45040803ae6f0e68c66de7a538f5e3e86397777e5fc2c488106b0` and configuration `3f43fce1081dc5db454447dbe4678947e5cefec014635e611d8d1032a0ac71c4`. Full compressed/raw archive verification covers all 26 ordered DiffIDs; actual same-generation classic Docker import reports config `3f43fce1081dc5db454447dbe4678947e5cefec014635e611d8d1032a0ac71c4` and no imported manifest digest. The agreed eight cases completed 9 application invocations and 1593 answer executions across 533 unique qIDs. Healthy20 and loose/ZIP500 matched saved content; reverse20 matched the same-image ordinary20, and both ZIP quotas matched the same-image loose500. Canonical repeated calls retained the exact disclosed deferrals. The mixed recovery case blanked only its declared failed questions and preserved later healthy outputs. These are bounded runtime/interface/content checks; no new semantic grade or official final result is claimed.
 
 R4 retains the image-owned literal SEGMENT task and the original request clocks. It stages only the selected ZIP member for each startup probe or answer, verifies that member through CRC/EOF and SHA-256, closes decoder handles, and removes the lease before continuing. Loose input remains a direct read. Model initialization is still eager. An attributed ordinary per-question exception produces empty content for that qID with measured latency and failure telemetry; successful answers are preserved and later questions continue. Unsafe or ambiguous archives, source mutation, cleanup integrity, required model initialization, environment and fixed-track failures remain fatal. The inherited precise pre-generation rules deferrals remain separately disclosed as degraded coverage. The four changed image files are the bootstrap, contract, probe entrypoint and new ZIP helper; all 51 unchanged inherited serving source files, including cap_fmt, all 50 model/prior assets, prompts, model arithmetic and generation settings remain unchanged.
 

PLATFORM_COMPATIBILITY.md

@@ -1,6 +1,8 @@
 # Fixed SEGMENT task and explicit degraded coverage
 
-**R4 local runtime, archive and import checks completed; official platform qualification remains unproven.** The exact archive is `e477d307ff2e09f469d83569ec1ce8703daeef34edbba633a3f240eab955de00` (35,613,293,722 bytes), immutable generation `1789092734891901`. The build manifest is `ba9ddb1e78a45040803ae6f0e68c66de7a538f5e3e86397777e5fc2c488106b0` and configuration `3f43fce1081dc5db454447dbe4678947e5cefec014635e611d8d1032a0ac71c4`. Full compressed/raw archive verification covers all 26 ordered DiffIDs; actual same-generation classic Docker import reports config `3f43fce1081dc5db454447dbe4678947e5cefec014635e611d8d1032a0ac71c4` and no imported manifest digest. The agreed eight cases completed 9 application invocations and 1593 answer executions across 533 unique qIDs. Healthy20 and loose/ZIP500 matched saved content; reverse20 matched the same-image ordinary20, and both ZIP quotas matched the same-image loose500. Canonical repeated calls retained the exact disclosed deferrals. The mixed recovery case blanked only its declared failed questions and preserved later healthy outputs. These are bounded runtime/interface/content checks; no new semantic grade or official final result is claimed.
+**Finals submission: owner confirmed on September 14, 2026 that repaired R4 was successfully submitted for SEGMENT finals, with no errors reported.** The submitted archive SHA256 is `e477d307ff2e09f469d83569ec1ce8703daeef34edbba633a3f240eab955de00`. September 14 is the confirmation date; the actual submission time, platform UUIDs, terminal logs, score and ranking were not supplied. See [SUBMISSION_STATUS.json](SUBMISSION_STATUS.json) for the exact identity and evidence scope. The model weights, source files and immutable loading revisions are unchanged.
+
+**September 11 local qualification record: R4 runtime, archive and import checks completed.** The exact archive is `e477d307ff2e09f469d83569ec1ce8703daeef34edbba633a3f240eab955de00` (35,613,293,722 bytes), immutable generation `1789092734891901`. The build manifest is `ba9ddb1e78a45040803ae6f0e68c66de7a538f5e3e86397777e5fc2c488106b0` and configuration `3f43fce1081dc5db454447dbe4678947e5cefec014635e611d8d1032a0ac71c4`. Full compressed/raw archive verification covers all 26 ordered DiffIDs; actual same-generation classic Docker import reports config `3f43fce1081dc5db454447dbe4678947e5cefec014635e611d8d1032a0ac71c4` and no imported manifest digest. The agreed eight cases completed 9 application invocations and 1593 answer executions across 533 unique qIDs. Healthy20 and loose/ZIP500 matched saved content; reverse20 matched the same-image ordinary20, and both ZIP quotas matched the same-image loose500. Canonical repeated calls retained the exact disclosed deferrals. The mixed recovery case blanked only its declared failed questions and preserved later healthy outputs. These are bounded runtime/interface/content checks; no new semantic grade or official final result is claimed.
 
 R4 retains the image-owned literal SEGMENT task and the original request clocks. It stages only the selected ZIP member for each startup probe or answer, verifies that member through CRC/EOF and SHA-256, closes decoder handles, and removes the lease before continuing. Loose input remains a direct read. Model initialization is still eager. An attributed ordinary per-question exception produces empty content for that qID with measured latency and failure telemetry; successful answers are preserved and later questions continue. Unsafe or ambiguous archives, source mutation, cleanup integrity, required model initialization, environment and fixed-track failures remain fatal. The inherited precise pre-generation rules deferrals remain separately disclosed as degraded coverage. The four changed image files are the bootstrap, contract, probe entrypoint and new ZIP helper; all 51 unchanged inherited serving source files, including cap_fmt, all 50 model/prior assets, prompts, model arithmetic and generation settings remain unchanged.
 

README.md

@@ -16,7 +16,9 @@ tags:
 ---
 # SURGFIELD ORena2026 SEGMENT FINAL
 
-**R4 local runtime, archive and import checks completed; official platform qualification remains unproven.** The exact archive is `e477d307ff2e09f469d83569ec1ce8703daeef34edbba633a3f240eab955de00` (35,613,293,722 bytes), immutable generation `1789092734891901`. The build manifest is `ba9ddb1e78a45040803ae6f0e68c66de7a538f5e3e86397777e5fc2c488106b0` and configuration `3f43fce1081dc5db454447dbe4678947e5cefec014635e611d8d1032a0ac71c4`. Full compressed/raw archive verification covers all 26 ordered DiffIDs; actual same-generation classic Docker import reports config `3f43fce1081dc5db454447dbe4678947e5cefec014635e611d8d1032a0ac71c4` and no imported manifest digest. The agreed eight cases completed 9 application invocations and 1593 answer executions across 533 unique qIDs. Healthy20 and loose/ZIP500 matched saved content; reverse20 matched the same-image ordinary20, and both ZIP quotas matched the same-image loose500. Canonical repeated calls retained the exact disclosed deferrals. The mixed recovery case blanked only its declared failed questions and preserved later healthy outputs. These are bounded runtime/interface/content checks; no new semantic grade or official final result is claimed.
+**Finals submission: owner confirmed on September 14, 2026 that repaired R4 was successfully submitted for SEGMENT finals, with no errors reported.** The submitted archive SHA256 is `e477d307ff2e09f469d83569ec1ce8703daeef34edbba633a3f240eab955de00`. September 14 is the confirmation date; the actual submission time, platform UUIDs, terminal logs, score and ranking were not supplied. See [SUBMISSION_STATUS.json](SUBMISSION_STATUS.json) for the exact identity and evidence scope. The model weights, source files and immutable loading revisions are unchanged.
+
+**September 11 local qualification record: R4 runtime, archive and import checks completed.** The exact archive is `e477d307ff2e09f469d83569ec1ce8703daeef34edbba633a3f240eab955de00` (35,613,293,722 bytes), immutable generation `1789092734891901`. The build manifest is `ba9ddb1e78a45040803ae6f0e68c66de7a538f5e3e86397777e5fc2c488106b0` and configuration `3f43fce1081dc5db454447dbe4678947e5cefec014635e611d8d1032a0ac71c4`. Full compressed/raw archive verification covers all 26 ordered DiffIDs; actual same-generation classic Docker import reports config `3f43fce1081dc5db454447dbe4678947e5cefec014635e611d8d1032a0ac71c4` and no imported manifest digest. The agreed eight cases completed 9 application invocations and 1593 answer executions across 533 unique qIDs. Healthy20 and loose/ZIP500 matched saved content; reverse20 matched the same-image ordinary20, and both ZIP quotas matched the same-image loose500. Canonical repeated calls retained the exact disclosed deferrals. The mixed recovery case blanked only its declared failed questions and preserved later healthy outputs. These are bounded runtime/interface/content checks; no new semantic grade or official final result is claimed.
 
 Private model and resource handoff by **HeyDonto Labs**. Responsible contact: **Reza Nehzati, Ph.D.**, via [rezanehzati](https://huggingface.co/rezanehzati).
 

REQUIRED_LINKS.json

@@ -1,16 +1,18 @@
 {
-  "current_image_publication_status": "R4 payload locally qualified; exact replacement private commit/readback must be bound separately.",
+  "current_image_publication_status": "R4 private model/source metadata at fd4e85f08fcf8c5dd13bdace344b0f5a8d27a9da was read back on September 14: all 89 remote file identities match the verified September 11 publication. The current presentation adds the owner-confirmed successful finals submission in SUBMISSION_STATUS.json.",
   "current_records": {
     "R4_source": "platform_wrapper/ (four exact image source files)",
     "asset_inventory": "MODEL_FILES.json",
     "asset_revision": "35fc28af1d55a5a9ae8096ff2e2cd2c961aa7119",
     "current_loading_instructions": "LOAD.md",
-    "current_runtime_and_platform_status": "PLATFORM_COMPATIBILITY.json",
+    "current_runtime_and_platform_status": "EVALUATION.json",
     "current_serving_image": "IMAGE_IDENTITY.json#/current_image",
     "metadata_tools_revision": "bc9e092422beac9ae51005694824cdc70205e0d5",
     "model_prior_asset_bytes": 36966713444,
     "model_prior_asset_count": 50,
-    "weights_checksums": "WEIGHTS_SHA256SUMS"
+    "weights_checksums": "WEIGHTS_SHA256SUMS",
+    "local_runtime_qualification": "PLATFORM_COMPATIBILITY.json",
+    "owner_reported_finals_submission": "SUBMISSION_STATUS.json"
   },
   "derived_annotation_scope": "The known derived packet contains all 13,177 listed extensions: 4,621 paraphrases, 5,217 count remints, 2,317 convention remints and 1,022 adoption rows. Exclusion of the 33,581 organizer rows is intentional, not evidence that those rows must be republished. The unresolved items are the separate private annotation URL/access/delivery receipts and complete signature provenance.",
   "expected_private_paths": {
@@ -20,7 +22,8 @@
     "loading": "LOAD.md",
     "model_card": "README.md",
     "r4_probe_source": "platform_wrapper/probe_entrypoint.py",
-    "r4_zip_source": "platform_wrapper/segment_zip_input.py"
+    "r4_zip_source": "platform_wrapper/segment_zip_input.py",
+    "submission_status": "SUBMISSION_STATUS.json"
   },
   "historical_availability_verification": {
     "asset_rows_matching_immutable_A_custody": 50,
@@ -49,7 +52,7 @@
   },
   "not_inferred": [
     "public release",
-    "final platform submission",
+    "independently retrieved platform terminal receipt",
     "full 46758-row annotation/pixel custody",
     "new organizer eligibility ruling"
   ],
@@ -74,7 +77,7 @@
     "profile": "https://huggingface.co/rezanehzati"
   },
   "schema": "segment-hf-required-links/1",
-  "scope": "Private A/M component links are unchanged. Current R3 image has separate local interface/parity and archive/load receipts; platform success, owner declarations and organizer access remain separate.",
+  "scope": "Private immutable A/M component links are unchanged. Current R4 image has separate local runtime/archive/load receipts and direct owner confirmation of successful finals submission. Exact platform UUIDs/logs/resources, scores, method-form submission, owner declarations and organizer access remain separate.",
   "upstreams": {
     "cholectrack20": "https://github.com/CAMMA-public/cholectrack20",
     "heico": "https://huggingface.co/datasets/orena-dkfz/heico-focus-vqa",

SUBMISSION_STATUS.json

@@ -0,0 +1,47 @@
+{
+  "schema": "segment-owner-confirmed-finals-submission/1",
+  "track": "SEGMENT",
+  "candidate": "R4",
+  "status": "owner_confirmed_successful_finals_submission_no_errors_reported",
+  "confirmation_date": "2026-09-14",
+  "confirmation_timezone": "Europe/Berlin",
+  "confirmation_date_is_submission_timestamp": false,
+  "evidence_type": "direct_owner_message",
+  "owner_message": "the segment Image e477d307ff2e09f469d83569ec1ce8703daeef34edbba633a3f240eab955de00 was successfully submitted for finals for segment track. this time didn't get any errors.",
+  "owner_message_sha256": "f91a4447d1883da3eedc547599a1131bd2555be3e6c5f264d4145a35349311cb",
+  "original_owner_message_file_sha256": "e5b9b2f0dabb02aecdcb5859559527ec1be23c1bdd7cebd7bf45410d1f633876",
+  "original_owner_message_file_serialization": "UTF-8 owner message plus one trailing LF",
+  "source_record": {
+    "path": "packages/segment/review/submissions/finals-owner-confirmation-20260914-r1/CONFIRMATION.json",
+    "sha256": "2ade02cebe92da6c8b4bc766fe2910bd6f0e7a040e3c4fd19b7adf6ac753cd7b"
+  },
+  "artifact_identity": {
+    "archive_sha256": "e477d307ff2e09f469d83569ec1ce8703daeef34edbba633a3f240eab955de00",
+    "archive_bytes": 35613293722,
+    "archive_generation": "1789092734891901",
+    "archive_uri": "gs://heydonto-surgfield-research/submissions/segment_final_recovery_20260911_r1/output/segment-final.tar.gz#1789092734891901",
+    "docker_config_sha256": "3f43fce1081dc5db454447dbe4678947e5cefec014635e611d8d1032a0ac71c4",
+    "build_store_manifest_sha256": "ba9ddb1e78a45040803ae6f0e68c66de7a538f5e3e86397777e5fc2c488106b0",
+    "layer_count": 26
+  },
+  "platform_details_not_supplied": {
+    "submission_timestamp": null,
+    "submission_uuid": null,
+    "algorithm_image_version_uuid": null,
+    "evaluation_result_uuid": null,
+    "terminal_logs": null,
+    "actual_resource_configuration": null,
+    "score": null,
+    "ranking": null
+  },
+  "independently_fetched_platform_terminal_receipt": false,
+  "prior_platform_failure_cause_confirmed": false,
+  "new_semantic_evaluation": false,
+  "model_and_loader_assets_changed": false,
+  "asset_revision": "35fc28af1d55a5a9ae8096ff2e2cd2c961aa7119",
+  "metadata_tools_revision": "bc9e092422beac9ae51005694824cdc70205e0d5",
+  "prior_private_r4_metadata_revision": "fd4e85f08fcf8c5dd13bdace344b0f5a8d27a9da",
+  "visibility": "private",
+  "organizer_invitation": "deferred_by_owner",
+  "scope": "Direct owner confirmation of submission and absence of reported errors. This is separate from independently retrieved platform logs, per-case model health, score/ranking, method-form submission, public release and organizer access. Historical local qualification flags retain their original measurement scope."
+}