{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:N6BNH32BFLZF2BF2RJU2H73SPT","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":"46838f981b2c77726b9bb288889bd35392de84fcc860a71d733c917bb229b68d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-30T10:11:26Z","title_canon_sha256":"646c7967b12ce376339442710584650e3742dc8487239502720d4b1aa439c423"},"schema_version":"1.0","source":{"id":"2404.00308","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.00308","created_at":"2026-07-05T08:02:31Z"},{"alias_kind":"arxiv_version","alias_value":"2404.00308v1","created_at":"2026-07-05T08:02:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00308","created_at":"2026-07-05T08:02:31Z"},{"alias_kind":"pith_short_12","alias_value":"N6BNH32BFLZF","created_at":"2026-07-05T08:02:31Z"},{"alias_kind":"pith_short_16","alias_value":"N6BNH32BFLZF2BF2","created_at":"2026-07-05T08:02:31Z"},{"alias_kind":"pith_short_8","alias_value":"N6BNH32B","created_at":"2026-07-05T08:02:31Z"}],"graph_snapshots":[{"event_id":"sha256:cc519c3a2a3d113f293012ecb5a5a350452348d894cdab93fe0b2c3acdad5b9d","target":"graph","created_at":"2026-07-05T08:02:31Z","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/2404.00308/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have showcased impressive capabilities in text comprehension and generation, prompting research efforts towards video LLMs to facilitate human-AI interaction at the video level. However, how to effectively encode and understand videos in video-based dialogue systems remains to be solved. In this paper, we investigate a straightforward yet unexplored question: Can we feed all spatial-temporal tokens into the LLM, thus delegating the task of video sequence modeling to the LLMs? Surprisingly, this simple approach yields significant improvements in video understanding.","authors_text":"Chen Li, Ge Li, Haoran Tang, Ruyang Liu, Ying Shan, Yixiao Ge","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-30T10:11:26Z","title":"ST-LLM: Large Language Models Are Effective Temporal Learners"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00308","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":"sha256:9919c7f599902ebce0a457226450dddc35620cfaab6da6d1297d1a57fade15ac","target":"record","created_at":"2026-07-05T08:02:31Z","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":"46838f981b2c77726b9bb288889bd35392de84fcc860a71d733c917bb229b68d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-30T10:11:26Z","title_canon_sha256":"646c7967b12ce376339442710584650e3742dc8487239502720d4b1aa439c423"},"schema_version":"1.0","source":{"id":"2404.00308","kind":"arxiv","version":1}},"canonical_sha256":"6f82d3ef412af25d04ba8a69a3ff727cd348e508e64bbed0c2b75b372d3461ec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f82d3ef412af25d04ba8a69a3ff727cd348e508e64bbed0c2b75b372d3461ec","first_computed_at":"2026-07-05T08:02:31.290213Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:02:31.290213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CmEfXoy6B8pLm1at51thDXpa6c+ay3xxoe4kD/Uth6vin/7Pfi5rTQS9O9aBjvnyFfgFeHIDGbC9CyBvjiVxAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:02:31.290743Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.00308","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9919c7f599902ebce0a457226450dddc35620cfaab6da6d1297d1a57fade15ac","sha256:cc519c3a2a3d113f293012ecb5a5a350452348d894cdab93fe0b2c3acdad5b9d"],"state_sha256":"3134d089dc97e071396c269c7a2db71d90237a8d0ef51b8416bcc71f22694801"}