{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:V5F2GF3F42QPINKHN4JSZIJSB7","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":"4f83489b3483b5a0a5a7cda2a299da278743ec4233bdf65c3c0b0a82171a7e1e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-04T00:13:54Z","title_canon_sha256":"fee90ff37463c684d88619a94167f1b09c4c29918471cd94ac5543222b5ee8b6"},"schema_version":"1.0","source":{"id":"2410.03051","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.03051","created_at":"2026-07-05T10:46:20Z"},{"alias_kind":"arxiv_version","alias_value":"2410.03051v4","created_at":"2026-07-05T10:46:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03051","created_at":"2026-07-05T10:46:20Z"},{"alias_kind":"pith_short_12","alias_value":"V5F2GF3F42QP","created_at":"2026-07-05T10:46:20Z"},{"alias_kind":"pith_short_16","alias_value":"V5F2GF3F42QPINKH","created_at":"2026-07-05T10:46:20Z"},{"alias_kind":"pith_short_8","alias_value":"V5F2GF3F","created_at":"2026-07-05T10:46:20Z"}],"graph_snapshots":[{"event_id":"sha256:99e7f59a5324e0aa1d43f65db2b12c59aecbc1c4b9b70c157ba5cee8ffc31d08","target":"graph","created_at":"2026-07-05T10:46:20Z","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/2410.03051/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video detailed captioning is a key task which aims to generate comprehensive and coherent textual descriptions of video content, benefiting both video understanding and generation. In this paper, we propose AuroraCap, a video captioner based on a large multimodal model. We follow the simplest architecture design without additional parameters for temporal modeling. To address the overhead caused by lengthy video sequences, we implement the token merging strategy, reducing the number of input visual tokens. Surprisingly, we found that this strategy results in little performance loss. AuroraCap s","authors_text":"Chenlin Meng, Christopher D. Manning, Enxin Song, Jenq-Neng Hwang, Omer Bar-Tal, Saining Xie, Vashisht Madhavan, Wenhao Chai, Yilun Du","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-04T00:13:54Z","title":"AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03051","kind":"arxiv","version":4},"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":"sha256:5c9df4fc5e014fdd400bc988c0ee43f8242560dc23bbc80c0fc773fd7d17699b","target":"record","created_at":"2026-07-05T10:46:20Z","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":"4f83489b3483b5a0a5a7cda2a299da278743ec4233bdf65c3c0b0a82171a7e1e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-04T00:13:54Z","title_canon_sha256":"fee90ff37463c684d88619a94167f1b09c4c29918471cd94ac5543222b5ee8b6"},"schema_version":"1.0","source":{"id":"2410.03051","kind":"arxiv","version":4}},"canonical_sha256":"af4ba31765e6a0f435476f132ca1320fdc90806ffa08972f3ea1f6e83c84022a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af4ba31765e6a0f435476f132ca1320fdc90806ffa08972f3ea1f6e83c84022a","first_computed_at":"2026-07-05T10:46:20.756498Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:46:20.756498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FyDan8IMay0Agqdo8i8iOTZAFtxN2cX6Qkhd1lGjcgZsgr16AWxbs3ZV6qvx57eHe8NhHXziFVtP1RDTJ6U9AA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:46:20.756968Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.03051","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5c9df4fc5e014fdd400bc988c0ee43f8242560dc23bbc80c0fc773fd7d17699b","sha256:99e7f59a5324e0aa1d43f65db2b12c59aecbc1c4b9b70c157ba5cee8ffc31d08"],"state_sha256":"386b570c2a0d43fb20d5cc4ee9009f4935642b796a7935b3be97ef7b98353dc3"}