{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Y2JXR346O7RXHNFYN6QL3GAKRX","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":"d3c3ee92076b3ece90b4c86972e6a8f36621ebcc50405416f3915804ed3d49d8","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-15T09:07:25Z","title_canon_sha256":"54beeaa452a1f2788a260c97d9b96841fb7106f884010f994c40745941d90603"},"schema_version":"1.0","source":{"id":"2410.11417","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.11417","created_at":"2026-07-05T09:20:53Z"},{"alias_kind":"arxiv_version","alias_value":"2410.11417v1","created_at":"2026-07-05T09:20:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11417","created_at":"2026-07-05T09:20:53Z"},{"alias_kind":"pith_short_12","alias_value":"Y2JXR346O7RX","created_at":"2026-07-05T09:20:53Z"},{"alias_kind":"pith_short_16","alias_value":"Y2JXR346O7RXHNFY","created_at":"2026-07-05T09:20:53Z"},{"alias_kind":"pith_short_8","alias_value":"Y2JXR346","created_at":"2026-07-05T09:20:53Z"}],"graph_snapshots":[{"event_id":"sha256:02cfef7288a772bc3901a26a91c1295a33749341824dfb5a711e6c5956cb558a","target":"graph","created_at":"2026-07-05T09:20:53Z","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/2410.11417/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video-based multimodal large language models (Video-LLMs) possess significant potential for video understanding tasks. However, most Video-LLMs treat videos as a sequential set of individual frames, which results in insufficient temporal-spatial interaction that hinders fine-grained comprehension and difficulty in processing longer videos due to limited visual token capacity. To address these challenges, we propose VidCompress, a novel Video-LLM featuring memory-enhanced temporal compression. VidCompress employs a dual-compressor approach: a memory-enhanced compressor captures both short-term ","authors_text":"Lin Ma, Xiaohan Lan, Yitian Yuan, Zequn Jie","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-15T09:07:25Z","title":"VidCompress: Memory-Enhanced Temporal Compression for Video Understanding in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11417","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":"sha256:6881205064b63eefba600899df6f0dea6f8aecc73faa271a7d80ef2c681d2de5","target":"record","created_at":"2026-07-05T09:20:53Z","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":"d3c3ee92076b3ece90b4c86972e6a8f36621ebcc50405416f3915804ed3d49d8","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-15T09:07:25Z","title_canon_sha256":"54beeaa452a1f2788a260c97d9b96841fb7106f884010f994c40745941d90603"},"schema_version":"1.0","source":{"id":"2410.11417","kind":"arxiv","version":1}},"canonical_sha256":"c69378ef9e77e373b4b86fa0bd980a8dfa270bc4bd5dc09f662e4483bb5dbdd5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c69378ef9e77e373b4b86fa0bd980a8dfa270bc4bd5dc09f662e4483bb5dbdd5","first_computed_at":"2026-07-05T09:20:53.224289Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:20:53.224289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h+JFVYVL5U6EFh/gCI2QAXoNeWKZs1wF6rga4UGgJrHcsB50mktZFQCsk1wPNtYebE3B6xUY+nwYFiW7GwdKBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:20:53.224777Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.11417","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6881205064b63eefba600899df6f0dea6f8aecc73faa271a7d80ef2c681d2de5","sha256:02cfef7288a772bc3901a26a91c1295a33749341824dfb5a711e6c5956cb558a"],"state_sha256":"5d4632d2038cafe6890dd24ee16b1999374105967e7e0cd1b299abe52007bd4e"}