{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BUAZVBGTAUISSS4MO35QYSBWET","short_pith_number":"pith:BUAZVBGT","schema_version":"1.0","canonical_sha256":"0d019a84d30511294b8c76fb0c483624e5270596d0a6f6415790db8b8421c5bc","source":{"kind":"arxiv","id":"2501.00599","version":3},"attestation_state":"computed","paper":{"title":"VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","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","submitted_at":"2024-12-31T18:56:46Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2501.00599","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-31T18:56:46Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5bf48cd9194a342ccc959dcdaca93dcd05525e73f431a581a534c11d5cb7fb2c","abstract_canon_sha256":"ba33d100d3a8806e23d7229e6ec32db8d0017e063ae374526f02185f54f49702"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:40.803427Z","signature_b64":"di09vu9tvQxmNE81ZhCfXWaWYrBpaqxWxQhrKIRipSNQ8UgrYJkyuYP4jteZHAw98+i5AwMfyuLUaSjxLl5NCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d019a84d30511294b8c76fb0c483624e5270596d0a6f6415790db8b8421c5bc","last_reissued_at":"2026-07-05T10:38:40.802868Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:40.802868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","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","submitted_at":"2024-12-31T18:56:46Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00599","kind":"arxiv","version":3},"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/2501.00599/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.00599","created_at":"2026-07-05T10:38:40.802930+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.00599v3","created_at":"2026-07-05T10:38:40.802930+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00599","created_at":"2026-07-05T10:38:40.802930+00:00"},{"alias_kind":"pith_short_12","alias_value":"BUAZVBGTAUIS","created_at":"2026-07-05T10:38:40.802930+00:00"},{"alias_kind":"pith_short_16","alias_value":"BUAZVBGTAUISSS4M","created_at":"2026-07-05T10:38:40.802930+00:00"},{"alias_kind":"pith_short_8","alias_value":"BUAZVBGT","created_at":"2026-07-05T10:38:40.802930+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31933","citing_title":"No Place to Hide: Benchmarking Video Hallucination with Background-Controlled Pairs","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21625","citing_title":"Flat-Pack Bench: Evaluating Spatio-Temporal Understanding in Large Vision-Language Models through Furniture Assembly","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2501.13106","citing_title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","ref_index":101,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BUAZVBGTAUISSS4MO35QYSBWET","json":"https://pith.science/pith/BUAZVBGTAUISSS4MO35QYSBWET.json","graph_json":"https://pith.science/api/pith-number/BUAZVBGTAUISSS4MO35QYSBWET/graph.json","events_json":"https://pith.science/api/pith-number/BUAZVBGTAUISSS4MO35QYSBWET/events.json","paper":"https://pith.science/paper/BUAZVBGT"},"agent_actions":{"view_html":"https://pith.science/pith/BUAZVBGTAUISSS4MO35QYSBWET","download_json":"https://pith.science/pith/BUAZVBGTAUISSS4MO35QYSBWET.json","view_paper":"https://pith.science/paper/BUAZVBGT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.00599&json=true","fetch_graph":"https://pith.science/api/pith-number/BUAZVBGTAUISSS4MO35QYSBWET/graph.json","fetch_events":"https://pith.science/api/pith-number/BUAZVBGTAUISSS4MO35QYSBWET/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BUAZVBGTAUISSS4MO35QYSBWET/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BUAZVBGTAUISSS4MO35QYSBWET/action/storage_attestation","attest_author":"https://pith.science/pith/BUAZVBGTAUISSS4MO35QYSBWET/action/author_attestation","sign_citation":"https://pith.science/pith/BUAZVBGTAUISSS4MO35QYSBWET/action/citation_signature","submit_replication":"https://pith.science/pith/BUAZVBGTAUISSS4MO35QYSBWET/action/replication_record"}},"created_at":"2026-07-05T10:38:40.802930+00:00","updated_at":"2026-07-05T10:38:40.802930+00:00"}