{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5EXARGARDHLVKVERIAPZSF3TA2","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":"544dfc13f02973f38f74376a9dc6cf7400ba7e0fb67335ed393fc8df269826c4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-18T03:04:38Z","title_canon_sha256":"c9a744224f498a1ea48872ce58a35987163689a12706826fb37070104073404a"},"schema_version":"1.0","source":{"id":"2402.11435","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.11435","created_at":"2026-07-05T08:26:19Z"},{"alias_kind":"arxiv_version","alias_value":"2402.11435v2","created_at":"2026-07-05T08:26:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11435","created_at":"2026-07-05T08:26:19Z"},{"alias_kind":"pith_short_12","alias_value":"5EXARGARDHLV","created_at":"2026-07-05T08:26:19Z"},{"alias_kind":"pith_short_16","alias_value":"5EXARGARDHLVKVER","created_at":"2026-07-05T08:26:19Z"},{"alias_kind":"pith_short_8","alias_value":"5EXARGAR","created_at":"2026-07-05T08:26:19Z"}],"graph_snapshots":[{"event_id":"sha256:d0679157f1882ff8fa086acfa53a81bedb520e5110b8568e23d2a5cb1122be0e","target":"graph","created_at":"2026-07-05T08:26:19Z","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/2402.11435/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) demonstrate remarkable proficiency in comprehending and handling text-based tasks. Many efforts are being made to transfer these attributes to video modality, which are termed Video-LLMs. However, existing Video-LLMs can only capture the coarse-grained semantics and are unable to effectively handle tasks related to comprehension or localization of specific video segments. In light of these challenges, we propose Momentor, a Video-LLM capable of accomplishing fine-grained temporal understanding tasks. To support the training of Momentor, we design an automatic data ","authors_text":"Hao Fei, Juncheng Li, Long Qian, Siliang Tang, Tat-Seng Chua, Yaobo Ye, Yueting Zhuang, Yu Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-18T03:04:38Z","title":"Momentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11435","kind":"arxiv","version":2},"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":"sha256:5171213cd7cfa3b00690dfa19b3f1f70f758fb378f4cac01f75efaff4fbc3de7","target":"record","created_at":"2026-07-05T08:26:19Z","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":"544dfc13f02973f38f74376a9dc6cf7400ba7e0fb67335ed393fc8df269826c4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-18T03:04:38Z","title_canon_sha256":"c9a744224f498a1ea48872ce58a35987163689a12706826fb37070104073404a"},"schema_version":"1.0","source":{"id":"2402.11435","kind":"arxiv","version":2}},"canonical_sha256":"e92e08981119d7555491401f991773068eaf36a9f60c89eed73ca6e0dd14bc18","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e92e08981119d7555491401f991773068eaf36a9f60c89eed73ca6e0dd14bc18","first_computed_at":"2026-07-05T08:26:19.914517Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:26:19.914517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6vfw7gJD3WiGit7qgZ9YooQJ3fdEu8emjPzq3bzTNtwLNY4I+LJBsiw2cy9idpOlqoa2oJrGLlBaWe8gJQz6Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:26:19.914982Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.11435","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5171213cd7cfa3b00690dfa19b3f1f70f758fb378f4cac01f75efaff4fbc3de7","sha256:d0679157f1882ff8fa086acfa53a81bedb520e5110b8568e23d2a5cb1122be0e"],"state_sha256":"694211260129b1e8df156dc753318f31992dacbb673994139920dc3f3ddb4152"}