{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XOLJKWRPRYNHH3NM4DS5XVPS33","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":"98388e3964b14db300e7c28b1999206d8fc39b8c74506c08fdd68ca0472ba2ec","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-29T16:25:32Z","title_canon_sha256":"a1758bd11fecf6c5c261dfa6417e83916c0cb3d6150b8f683ae73a8ad7c0bde7"},"schema_version":"1.0","source":{"id":"2310.19060","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.19060","created_at":"2026-07-05T07:06:45Z"},{"alias_kind":"arxiv_version","alias_value":"2310.19060v1","created_at":"2026-07-05T07:06:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19060","created_at":"2026-07-05T07:06:45Z"},{"alias_kind":"pith_short_12","alias_value":"XOLJKWRPRYNH","created_at":"2026-07-05T07:06:45Z"},{"alias_kind":"pith_short_16","alias_value":"XOLJKWRPRYNHH3NM","created_at":"2026-07-05T07:06:45Z"},{"alias_kind":"pith_short_8","alias_value":"XOLJKWRP","created_at":"2026-07-05T07:06:45Z"}],"graph_snapshots":[{"event_id":"sha256:69fb24e6cad7de3707773bee4b076d6b8473e4bede76aec971b8936706ee948d","target":"graph","created_at":"2026-07-05T07:06:45Z","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/2310.19060/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale video-language pre-training has made remarkable strides in advancing video-language understanding tasks. However, the heavy computational burden of video encoding remains a formidable efficiency bottleneck, particularly for long-form videos. These videos contain massive visual tokens due to their inherent 3D properties and spatiotemporal redundancy, making it challenging to capture complex temporal and spatial relationships. To tackle this issue, we propose an efficient method called TEmporal-Spatial Token Aggregation (TESTA). TESTA condenses video semantics by adaptively aggregati","authors_text":"Lu Hou, Shicheng Li, Shuhuai Ren, Sishuo Chen, Xu Sun","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-29T16:25:32Z","title":"TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.19060","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:c76a14e3e0feca2ca283979785d6944497d82f4872d0c831a153ab6db138b6bf","target":"record","created_at":"2026-07-05T07:06:45Z","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":"98388e3964b14db300e7c28b1999206d8fc39b8c74506c08fdd68ca0472ba2ec","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-29T16:25:32Z","title_canon_sha256":"a1758bd11fecf6c5c261dfa6417e83916c0cb3d6150b8f683ae73a8ad7c0bde7"},"schema_version":"1.0","source":{"id":"2310.19060","kind":"arxiv","version":1}},"canonical_sha256":"bb96955a2f8e1a73edace0e5dbd5f2deefc012353d0a25e785d00f2f79cd4060","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb96955a2f8e1a73edace0e5dbd5f2deefc012353d0a25e785d00f2f79cd4060","first_computed_at":"2026-07-05T07:06:45.465251Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:06:45.465251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m59c2Mi4HFTePHVQMcLH+SVtM7BzOS07GOaZFliN6ANNl0YWxnv8RKQR4Z2tcQwwHI3207onfIFujRCfd5cRCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:06:45.465768Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.19060","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c76a14e3e0feca2ca283979785d6944497d82f4872d0c831a153ab6db138b6bf","sha256:69fb24e6cad7de3707773bee4b076d6b8473e4bede76aec971b8936706ee948d"],"state_sha256":"81720eb92e30a8ad0abf956759a2961ebac2b20b694f6f8a520eb412e0dc5f62"}