{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CAENBIY46RWI6DDLF4XL2UKSSJ","short_pith_number":"pith:CAENBIY4","schema_version":"1.0","canonical_sha256":"1008d0a31cf46c8f0c6b2f2ebd5152926a31256dd27aa6f959fef688984f2065","source":{"kind":"arxiv","id":"2501.03230","version":1},"attestation_state":"computed","paper":{"title":"Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Hanwang Zhang, Hao Fei, Meishan Zhang, Mong-Li Lee, Shengqiong Wu, Wei Ji, Wynne Hsu","submitted_at":"2024-05-07T11:55:10Z","abstract_excerpt":"Existing research of video understanding still struggles to achieve in-depth comprehension and reasoning in complex videos, primarily due to the under-exploration of two key bottlenecks: fine-grained spatial-temporal perceptive understanding and cognitive-level video scene comprehension. This paper bridges the gap by presenting a novel solution. We first introduce a novel video Multimodal Large Language Model (MLLM), MotionEpic, which achieves fine-grained pixel-level spatial-temporal video grounding by integrating video spatial-temporal scene graph (STSG) representation. Building upon MotionE"},"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":"2501.03230","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-07T11:55:10Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"04a42f044524e178530c0a1c8ff641ec7eb4df547c4ef98ff60d4ca7a1fb0ee3","abstract_canon_sha256":"e57fd6ba3544dfd7cf72476465df6ca86dbe413feafd7db2684317732be1cf8c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:51.073506Z","signature_b64":"OGjvVMieIxsN6USD5EkWWIQ26BPGhE8JepINeCC/GPN3zRc8LYe5PMO9etjNUUGvweDlmSo1tNw5CrJ3CBp9Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1008d0a31cf46c8f0c6b2f2ebd5152926a31256dd27aa6f959fef688984f2065","last_reissued_at":"2026-07-05T09:57:51.073034Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:51.073034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Hanwang Zhang, Hao Fei, Meishan Zhang, Mong-Li Lee, Shengqiong Wu, Wei Ji, Wynne Hsu","submitted_at":"2024-05-07T11:55:10Z","abstract_excerpt":"Existing research of video understanding still struggles to achieve in-depth comprehension and reasoning in complex videos, primarily due to the under-exploration of two key bottlenecks: fine-grained spatial-temporal perceptive understanding and cognitive-level video scene comprehension. This paper bridges the gap by presenting a novel solution. We first introduce a novel video Multimodal Large Language Model (MLLM), MotionEpic, which achieves fine-grained pixel-level spatial-temporal video grounding by integrating video spatial-temporal scene graph (STSG) representation. Building upon MotionE"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03230","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/2501.03230/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":"2501.03230","created_at":"2026-07-05T09:57:51.073091+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.03230v1","created_at":"2026-07-05T09:57:51.073091+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03230","created_at":"2026-07-05T09:57:51.073091+00:00"},{"alias_kind":"pith_short_12","alias_value":"CAENBIY46RWI","created_at":"2026-07-05T09:57:51.073091+00:00"},{"alias_kind":"pith_short_16","alias_value":"CAENBIY46RWI6DDL","created_at":"2026-07-05T09:57:51.073091+00:00"},{"alias_kind":"pith_short_8","alias_value":"CAENBIY4","created_at":"2026-07-05T09:57:51.073091+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11838","citing_title":"Plan-and-Verify Video Reward Reasoning with Spatio-Temporal Scene Graph Grounding","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09181","citing_title":"Counterfactual Reasoning for Fine-Grained Evidence Disentanglement in VideoQA","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07433","citing_title":"Watch, Remember, Reason: Human-View Video Understanding with MLLMs","ref_index":178,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02724","citing_title":"AVTrack: Audio-Visual Tracking in Human-centric Complex Scenes","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14692","citing_title":"Chain-of-Glimpse: Search-Guided Progressive Object-Grounded Reasoning for Video Understanding","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2603.03944","citing_title":"SCP: Spatial Causal Prediction in Video","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10106","citing_title":"ViSRA: A Video-based Spatial Reasoning Agent for Multi-modal Large Language Models","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11399","citing_title":"Reasoning Resides in Layers: Restoring Temporal Reasoning in Video-Language Models with Layer-Selective Merging","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14692","citing_title":"Chain-of-Glimpse: Search-Guided Progressive Object-Grounded Reasoning for Video Understanding","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17375","citing_title":"When Text Hijacks Vision: Benchmarking and Mitigating Text Overlay-Induced Hallucination in Vision Language Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01657","citing_title":"Act2See: Emergent Active Visual Perception for Video Reasoning","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CAENBIY46RWI6DDLF4XL2UKSSJ","json":"https://pith.science/pith/CAENBIY46RWI6DDLF4XL2UKSSJ.json","graph_json":"https://pith.science/api/pith-number/CAENBIY46RWI6DDLF4XL2UKSSJ/graph.json","events_json":"https://pith.science/api/pith-number/CAENBIY46RWI6DDLF4XL2UKSSJ/events.json","paper":"https://pith.science/paper/CAENBIY4"},"agent_actions":{"view_html":"https://pith.science/pith/CAENBIY46RWI6DDLF4XL2UKSSJ","download_json":"https://pith.science/pith/CAENBIY46RWI6DDLF4XL2UKSSJ.json","view_paper":"https://pith.science/paper/CAENBIY4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.03230&json=true","fetch_graph":"https://pith.science/api/pith-number/CAENBIY46RWI6DDLF4XL2UKSSJ/graph.json","fetch_events":"https://pith.science/api/pith-number/CAENBIY46RWI6DDLF4XL2UKSSJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CAENBIY46RWI6DDLF4XL2UKSSJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CAENBIY46RWI6DDLF4XL2UKSSJ/action/storage_attestation","attest_author":"https://pith.science/pith/CAENBIY46RWI6DDLF4XL2UKSSJ/action/author_attestation","sign_citation":"https://pith.science/pith/CAENBIY46RWI6DDLF4XL2UKSSJ/action/citation_signature","submit_replication":"https://pith.science/pith/CAENBIY46RWI6DDLF4XL2UKSSJ/action/replication_record"}},"created_at":"2026-07-05T09:57:51.073091+00:00","updated_at":"2026-07-05T09:57:51.073091+00:00"}