{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ULWDK4B7AGLYYEW3L5VHPMLRT6","short_pith_number":"pith:ULWDK4B7","canonical_record":{"source":{"id":"2501.13893","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-23T18:08:57Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"65dbcc1292bb42c685c692c25797ccf1fe9295e084bac6527a3dbaa58af56a47","abstract_canon_sha256":"b68089dabee83f2ce3356a06325da3c503b7909564b3a26e74cdb21f88c2c4e1"},"schema_version":"1.0"},"canonical_sha256":"a2ec35703f01978c12db5f6a77b1719fa0ee668acfc64d834fae1c99241b2b71","source":{"kind":"arxiv","id":"2501.13893","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.13893","created_at":"2026-07-05T10:04:35Z"},{"alias_kind":"arxiv_version","alias_value":"2501.13893v1","created_at":"2026-07-05T10:04:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13893","created_at":"2026-07-05T10:04:35Z"},{"alias_kind":"pith_short_12","alias_value":"ULWDK4B7AGLY","created_at":"2026-07-05T10:04:35Z"},{"alias_kind":"pith_short_16","alias_value":"ULWDK4B7AGLYYEW3","created_at":"2026-07-05T10:04:35Z"},{"alias_kind":"pith_short_8","alias_value":"ULWDK4B7","created_at":"2026-07-05T10:04:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ULWDK4B7AGLYYEW3L5VHPMLRT6","target":"record","payload":{"canonical_record":{"source":{"id":"2501.13893","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-23T18:08:57Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"65dbcc1292bb42c685c692c25797ccf1fe9295e084bac6527a3dbaa58af56a47","abstract_canon_sha256":"b68089dabee83f2ce3356a06325da3c503b7909564b3a26e74cdb21f88c2c4e1"},"schema_version":"1.0"},"canonical_sha256":"a2ec35703f01978c12db5f6a77b1719fa0ee668acfc64d834fae1c99241b2b71","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:35.732533Z","signature_b64":"NL4VRNQh9PfSy/3bbcsWg+dgo2itR+ZkBzM+5GFC4BGOyzzRds2uoW8q8ps6zjMHISnpIwBssAgpuyX6RyDQBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2ec35703f01978c12db5f6a77b1719fa0ee668acfc64d834fae1c99241b2b71","last_reissued_at":"2026-07-05T10:04:35.732156Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:35.732156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.13893","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:04:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rs5indX1G3g55UHzRFWq77lPFJInJHY8zP77dnh3tf1QnlSp77F0pGW8J2Vok38jkCGxw0QHwqSD03yQolsEAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:13:13.088495Z"},"content_sha256":"9f60b9187393738fb29223cc7a978edabfb48405656eb201556444277329c8e5","schema_version":"1.0","event_id":"sha256:9f60b9187393738fb29223cc7a978edabfb48405656eb201556444277329c8e5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ULWDK4B7AGLYYEW3L5VHPMLRT6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pix2Cap-COCO: Advancing Visual Comprehension via Pixel-Level Captioning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bo He, Junke Wang, Lingyu Kong, Zuxuan Wu, Zuyao You","submitted_at":"2025-01-23T18:08:57Z","abstract_excerpt":"We present Pix2Cap-COCO, the first panoptic pixel-level caption dataset designed to advance fine-grained visual understanding. To achieve this, we carefully design an automated annotation pipeline that prompts GPT-4V to generate pixel-aligned, instance-specific captions for individual objects within images, enabling models to learn more granular relationships between objects and their contexts. This approach results in 167,254 detailed captions, with an average of 22.94 words per caption. Building on Pix2Cap-COCO, we introduce a novel task, panoptic segmentation-captioning, which challenges mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13893","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2501.13893/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:04:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mPH1umu3+bbrot9Kvu7cCoFtnPtTX3LeicS5Bz8bG7Yo5Q3eG3Y9wq6gZtIxV2srayQ4Yy52l2AF0H6DlW1uAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:13:13.089019Z"},"content_sha256":"a4534e44f039b0208d3f9d2d2ca7b9035c3c91036cd60317a78fdcac3605244c","schema_version":"1.0","event_id":"sha256:a4534e44f039b0208d3f9d2d2ca7b9035c3c91036cd60317a78fdcac3605244c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ULWDK4B7AGLYYEW3L5VHPMLRT6/bundle.json","state_url":"https://pith.science/pith/ULWDK4B7AGLYYEW3L5VHPMLRT6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ULWDK4B7AGLYYEW3L5VHPMLRT6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T17:13:13Z","links":{"resolver":"https://pith.science/pith/ULWDK4B7AGLYYEW3L5VHPMLRT6","bundle":"https://pith.science/pith/ULWDK4B7AGLYYEW3L5VHPMLRT6/bundle.json","state":"https://pith.science/pith/ULWDK4B7AGLYYEW3L5VHPMLRT6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ULWDK4B7AGLYYEW3L5VHPMLRT6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ULWDK4B7AGLYYEW3L5VHPMLRT6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b68089dabee83f2ce3356a06325da3c503b7909564b3a26e74cdb21f88c2c4e1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-23T18:08:57Z","title_canon_sha256":"65dbcc1292bb42c685c692c25797ccf1fe9295e084bac6527a3dbaa58af56a47"},"schema_version":"1.0","source":{"id":"2501.13893","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.13893","created_at":"2026-07-05T10:04:35Z"},{"alias_kind":"arxiv_version","alias_value":"2501.13893v1","created_at":"2026-07-05T10:04:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13893","created_at":"2026-07-05T10:04:35Z"},{"alias_kind":"pith_short_12","alias_value":"ULWDK4B7AGLY","created_at":"2026-07-05T10:04:35Z"},{"alias_kind":"pith_short_16","alias_value":"ULWDK4B7AGLYYEW3","created_at":"2026-07-05T10:04:35Z"},{"alias_kind":"pith_short_8","alias_value":"ULWDK4B7","created_at":"2026-07-05T10:04:35Z"}],"graph_snapshots":[{"event_id":"sha256:a4534e44f039b0208d3f9d2d2ca7b9035c3c91036cd60317a78fdcac3605244c","target":"graph","created_at":"2026-07-05T10:04:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2501.13893/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Pix2Cap-COCO, the first panoptic pixel-level caption dataset designed to advance fine-grained visual understanding. To achieve this, we carefully design an automated annotation pipeline that prompts GPT-4V to generate pixel-aligned, instance-specific captions for individual objects within images, enabling models to learn more granular relationships between objects and their contexts. This approach results in 167,254 detailed captions, with an average of 22.94 words per caption. Building on Pix2Cap-COCO, we introduce a novel task, panoptic segmentation-captioning, which challenges mo","authors_text":"Bo He, Junke Wang, Lingyu Kong, Zuxuan Wu, Zuyao You","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-23T18:08:57Z","title":"Pix2Cap-COCO: Advancing Visual Comprehension via Pixel-Level Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13893","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9f60b9187393738fb29223cc7a978edabfb48405656eb201556444277329c8e5","target":"record","created_at":"2026-07-05T10:04:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b68089dabee83f2ce3356a06325da3c503b7909564b3a26e74cdb21f88c2c4e1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-23T18:08:57Z","title_canon_sha256":"65dbcc1292bb42c685c692c25797ccf1fe9295e084bac6527a3dbaa58af56a47"},"schema_version":"1.0","source":{"id":"2501.13893","kind":"arxiv","version":1}},"canonical_sha256":"a2ec35703f01978c12db5f6a77b1719fa0ee668acfc64d834fae1c99241b2b71","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2ec35703f01978c12db5f6a77b1719fa0ee668acfc64d834fae1c99241b2b71","first_computed_at":"2026-07-05T10:04:35.732156Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:04:35.732156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NL4VRNQh9PfSy/3bbcsWg+dgo2itR+ZkBzM+5GFC4BGOyzzRds2uoW8q8ps6zjMHISnpIwBssAgpuyX6RyDQBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:04:35.732533Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.13893","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9f60b9187393738fb29223cc7a978edabfb48405656eb201556444277329c8e5","sha256:a4534e44f039b0208d3f9d2d2ca7b9035c3c91036cd60317a78fdcac3605244c"],"state_sha256":"545734ad25c8b3215aec98e945e8bc18fdcea7c9a24b8c10357cb288f3fa30f6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7B1dyBCT/4qlPcEoAKq0beN++pzEbDIbhTJSZz47E6P0B3a+sEjP1BIx8S1Ii11vPDiG6ls4b4B6usZqwu+NDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T17:13:13.093994Z","bundle_sha256":"e99bff8342e0acb0a57060c29ce0f809e8ba0bc0db4adf8be9bf274c65eed5e5"}}