{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BUAZVBGTAUISSS4MO35QYSBWET","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":"ba33d100d3a8806e23d7229e6ec32db8d0017e063ae374526f02185f54f49702","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-31T18:56:46Z","title_canon_sha256":"5bf48cd9194a342ccc959dcdaca93dcd05525e73f431a581a534c11d5cb7fb2c"},"schema_version":"1.0","source":{"id":"2501.00599","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.00599","created_at":"2026-07-05T10:38:40Z"},{"alias_kind":"arxiv_version","alias_value":"2501.00599v3","created_at":"2026-07-05T10:38:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00599","created_at":"2026-07-05T10:38:40Z"},{"alias_kind":"pith_short_12","alias_value":"BUAZVBGTAUIS","created_at":"2026-07-05T10:38:40Z"},{"alias_kind":"pith_short_16","alias_value":"BUAZVBGTAUISSS4M","created_at":"2026-07-05T10:38:40Z"},{"alias_kind":"pith_short_8","alias_value":"BUAZVBGT","created_at":"2026-07-05T10:38:40Z"}],"graph_snapshots":[{"event_id":"sha256:040f474885dcdba6bc1fbd9f964a945c94e41b4665d15763392429ce3b37d493","target":"graph","created_at":"2026-07-05T10:38:40Z","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/2501.00599/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video Large Language Models (Video LLMs) have recently exhibited remarkable capabilities in general video understanding. However, they mainly focus on holistic comprehension and struggle with capturing fine-grained spatial and temporal details. Besides, the lack of high-quality object-level video instruction data and a comprehensive benchmark further hinders their advancements. To tackle these challenges, we introduce the VideoRefer Suite to empower Video LLM for finer-level spatial-temporal video understanding, i.e., enabling perception and reasoning on any objects throughout the video. Speci","authors_text":"Boqiang Zhang, Deli Zhao, Hang Zhang, Jianke Zhu, Lidong Bing, Long Li, Wenqiao Zhang, Wentong Li, Xin Li, Yueting Zhuang, Yuqian Yuan, Zesen Cheng","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-31T18:56:46Z","title":"VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00599","kind":"arxiv","version":3},"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:a0b9c6bd218146465c725e1c0d529b249a11d917c4f33bfcdb1164c282e61439","target":"record","created_at":"2026-07-05T10:38:40Z","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":"ba33d100d3a8806e23d7229e6ec32db8d0017e063ae374526f02185f54f49702","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-31T18:56:46Z","title_canon_sha256":"5bf48cd9194a342ccc959dcdaca93dcd05525e73f431a581a534c11d5cb7fb2c"},"schema_version":"1.0","source":{"id":"2501.00599","kind":"arxiv","version":3}},"canonical_sha256":"0d019a84d30511294b8c76fb0c483624e5270596d0a6f6415790db8b8421c5bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d019a84d30511294b8c76fb0c483624e5270596d0a6f6415790db8b8421c5bc","first_computed_at":"2026-07-05T10:38:40.802868Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:38:40.802868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"di09vu9tvQxmNE81ZhCfXWaWYrBpaqxWxQhrKIRipSNQ8UgrYJkyuYP4jteZHAw98+i5AwMfyuLUaSjxLl5NCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:38:40.803427Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.00599","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0b9c6bd218146465c725e1c0d529b249a11d917c4f33bfcdb1164c282e61439","sha256:040f474885dcdba6bc1fbd9f964a945c94e41b4665d15763392429ce3b37d493"],"state_sha256":"e5b977b5ece68a578e273a9f336ec87ea9783ee32c3342a93f224f4de28f3b6d"}