{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FAY3QOSZRPVVKB2KHQ5MUSU4ZX","short_pith_number":"pith:FAY3QOSZ","schema_version":"1.0","canonical_sha256":"2831b83a598beb55074a3c3aca4a9ccdcf8e2aee36bfa410191a35c5ca900c2b","source":{"kind":"arxiv","id":"2503.14935","version":1},"attestation_state":"computed","paper":{"title":"FAVOR-Bench: A Comprehensive Benchmark for Fine-Grained Video Motion Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chongjun Tu, Gang Yu, Lin Zhang, Pengtao Chen, Peng Ye, Tao Chen, Wei Cheng, Xianfang Zeng","submitted_at":"2025-03-19T06:42:32Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have shown remarkable capabilities in video content understanding but still struggle with fine-grained motion comprehension. To comprehensively assess the motion understanding ability of existing MLLMs, we introduce FAVOR-Bench, comprising 1,776 videos with structured manual annotations of various motions. Our benchmark includes both close-ended and open-ended tasks. For close-ended evaluation, we carefully design 8,184 multiple-choice question-answer pairs spanning six distinct sub-tasks. For open-ended evaluation, we develop both a novel cost-efficien"},"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":"2503.14935","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-19T06:42:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"19c572f82611c99c029707991fd7da74d402c27e6ae547b2d14f72b95b72f081","abstract_canon_sha256":"26e3a1fed2dba3d7e3e00db7d302fd3c5314d2891e41aa68964b5f6e668eb256"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:34:27.881079Z","signature_b64":"PCte6KMSfpdeHgElVOyf/TSC9VhOms+yJI7PIZOH5Y6ND0C3QSY/xtmsXQFZXxGZSXHBP9Ot31WvoLlMb9SeBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2831b83a598beb55074a3c3aca4a9ccdcf8e2aee36bfa410191a35c5ca900c2b","last_reissued_at":"2026-07-05T10:34:27.880446Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:34:27.880446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FAVOR-Bench: A Comprehensive Benchmark for Fine-Grained Video Motion Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chongjun Tu, Gang Yu, Lin Zhang, Pengtao Chen, Peng Ye, Tao Chen, Wei Cheng, Xianfang Zeng","submitted_at":"2025-03-19T06:42:32Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have shown remarkable capabilities in video content understanding but still struggle with fine-grained motion comprehension. To comprehensively assess the motion understanding ability of existing MLLMs, we introduce FAVOR-Bench, comprising 1,776 videos with structured manual annotations of various motions. Our benchmark includes both close-ended and open-ended tasks. For close-ended evaluation, we carefully design 8,184 multiple-choice question-answer pairs spanning six distinct sub-tasks. For open-ended evaluation, we develop both a novel cost-efficien"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.14935","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/2503.14935/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":"2503.14935","created_at":"2026-07-05T10:34:27.880513+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.14935v1","created_at":"2026-07-05T10:34:27.880513+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.14935","created_at":"2026-07-05T10:34:27.880513+00:00"},{"alias_kind":"pith_short_12","alias_value":"FAY3QOSZRPVV","created_at":"2026-07-05T10:34:27.880513+00:00"},{"alias_kind":"pith_short_16","alias_value":"FAY3QOSZRPVVKB2K","created_at":"2026-07-05T10:34:27.880513+00:00"},{"alias_kind":"pith_short_8","alias_value":"FAY3QOSZ","created_at":"2026-07-05T10:34:27.880513+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06853","citing_title":"MotionEnhancer: Leveraging Video Diffusion for Motion-Enhanced Vision-Language Models","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04773","citing_title":"NextMotionQA: Benchmarking and Judging Human Motion Understanding with Vision-Language Models","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02522","citing_title":"Moment-Video: Diagnosing Temporal Fidelity of Video MLLMs on Momentary Visual Events","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22884","citing_title":"Can Multimodal Large Language Models Truly Understand Small Objects?","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08209","citing_title":"OmniJigsaw: Enhancing Omni-Modal Reasoning via Modality-Orchestrated Reordering","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20760","citing_title":"Exploring High-Order Self-Similarity for Video Understanding","ref_index":82,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FAY3QOSZRPVVKB2KHQ5MUSU4ZX","json":"https://pith.science/pith/FAY3QOSZRPVVKB2KHQ5MUSU4ZX.json","graph_json":"https://pith.science/api/pith-number/FAY3QOSZRPVVKB2KHQ5MUSU4ZX/graph.json","events_json":"https://pith.science/api/pith-number/FAY3QOSZRPVVKB2KHQ5MUSU4ZX/events.json","paper":"https://pith.science/paper/FAY3QOSZ"},"agent_actions":{"view_html":"https://pith.science/pith/FAY3QOSZRPVVKB2KHQ5MUSU4ZX","download_json":"https://pith.science/pith/FAY3QOSZRPVVKB2KHQ5MUSU4ZX.json","view_paper":"https://pith.science/paper/FAY3QOSZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.14935&json=true","fetch_graph":"https://pith.science/api/pith-number/FAY3QOSZRPVVKB2KHQ5MUSU4ZX/graph.json","fetch_events":"https://pith.science/api/pith-number/FAY3QOSZRPVVKB2KHQ5MUSU4ZX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FAY3QOSZRPVVKB2KHQ5MUSU4ZX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FAY3QOSZRPVVKB2KHQ5MUSU4ZX/action/storage_attestation","attest_author":"https://pith.science/pith/FAY3QOSZRPVVKB2KHQ5MUSU4ZX/action/author_attestation","sign_citation":"https://pith.science/pith/FAY3QOSZRPVVKB2KHQ5MUSU4ZX/action/citation_signature","submit_replication":"https://pith.science/pith/FAY3QOSZRPVVKB2KHQ5MUSU4ZX/action/replication_record"}},"created_at":"2026-07-05T10:34:27.880513+00:00","updated_at":"2026-07-05T10:34:27.880513+00:00"}