{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CAENBIY46RWI6DDLF4XL2UKSSJ","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":"e57fd6ba3544dfd7cf72476465df6ca86dbe413feafd7db2684317732be1cf8c","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-07T11:55:10Z","title_canon_sha256":"04a42f044524e178530c0a1c8ff641ec7eb4df547c4ef98ff60d4ca7a1fb0ee3"},"schema_version":"1.0","source":{"id":"2501.03230","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.03230","created_at":"2026-07-05T09:57:51Z"},{"alias_kind":"arxiv_version","alias_value":"2501.03230v1","created_at":"2026-07-05T09:57:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03230","created_at":"2026-07-05T09:57:51Z"},{"alias_kind":"pith_short_12","alias_value":"CAENBIY46RWI","created_at":"2026-07-05T09:57:51Z"},{"alias_kind":"pith_short_16","alias_value":"CAENBIY46RWI6DDL","created_at":"2026-07-05T09:57:51Z"},{"alias_kind":"pith_short_8","alias_value":"CAENBIY4","created_at":"2026-07-05T09:57:51Z"}],"graph_snapshots":[{"event_id":"sha256:de30362985146a82105c956b3f5144a4f732f1e9730d24839108043808af87b4","target":"graph","created_at":"2026-07-05T09:57:51Z","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/2501.03230/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hanwang Zhang, Hao Fei, Meishan Zhang, Mong-Li Lee, Shengqiong Wu, Wei Ji, Wynne Hsu","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-07T11:55:10Z","title":"Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03230","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:d9cfc15286d8779b32211cbf580409e9ab4661ff0fd96584668d5d6aa9ee8ab8","target":"record","created_at":"2026-07-05T09:57:51Z","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":"e57fd6ba3544dfd7cf72476465df6ca86dbe413feafd7db2684317732be1cf8c","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-07T11:55:10Z","title_canon_sha256":"04a42f044524e178530c0a1c8ff641ec7eb4df547c4ef98ff60d4ca7a1fb0ee3"},"schema_version":"1.0","source":{"id":"2501.03230","kind":"arxiv","version":1}},"canonical_sha256":"1008d0a31cf46c8f0c6b2f2ebd5152926a31256dd27aa6f959fef688984f2065","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1008d0a31cf46c8f0c6b2f2ebd5152926a31256dd27aa6f959fef688984f2065","first_computed_at":"2026-07-05T09:57:51.073034Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:57:51.073034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OGjvVMieIxsN6USD5EkWWIQ26BPGhE8JepINeCC/GPN3zRc8LYe5PMO9etjNUUGvweDlmSo1tNw5CrJ3CBp9Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:57:51.073506Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.03230","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9cfc15286d8779b32211cbf580409e9ab4661ff0fd96584668d5d6aa9ee8ab8","sha256:de30362985146a82105c956b3f5144a4f732f1e9730d24839108043808af87b4"],"state_sha256":"8f6f7fd850ca8127812bc6ddfa61edca2e4a859712c1f65dc7f6093b6f7a6863"}