{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JM3HSGUYNZXJHOIDI765ZLJZ7D","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":"1501f926f745fab85c39899047e5b03d1f5e33efc66f505b42712bb5b224828c","cross_cats_sorted":["cs.CL","cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-29T15:18:06Z","title_canon_sha256":"3735ab76c10f0013efad43c39ff56f993f8d443f5fffa66ec3cd4ab02acac1fd"},"schema_version":"1.0","source":{"id":"2411.19772","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.19772","created_at":"2026-07-05T10:35:42Z"},{"alias_kind":"arxiv_version","alias_value":"2411.19772v3","created_at":"2026-07-05T10:35:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19772","created_at":"2026-07-05T10:35:42Z"},{"alias_kind":"pith_short_12","alias_value":"JM3HSGUYNZXJ","created_at":"2026-07-05T10:35:42Z"},{"alias_kind":"pith_short_16","alias_value":"JM3HSGUYNZXJHOID","created_at":"2026-07-05T10:35:42Z"},{"alias_kind":"pith_short_8","alias_value":"JM3HSGUY","created_at":"2026-07-05T10:35:42Z"}],"graph_snapshots":[{"event_id":"sha256:bc5ab958b4169462ecb7e0f4648d5b99ca5c5e597d3bafa99db2a3396e0ae73e","target":"graph","created_at":"2026-07-05T10:35:42Z","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/2411.19772/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite impressive advancements in video understanding, most efforts remain limited to coarse-grained or visual-only video tasks. However, real-world videos encompass omni-modal information (vision, audio, and speech) with a series of events forming a cohesive storyline. The lack of multi-modal video data with fine-grained event annotations and the high cost of manual labeling are major obstacles to comprehensive omni-modality video perception. To address this gap, we propose an automatic pipeline consisting of high-quality multi-modal video filtering, semantically coherent omni-modal event bo","authors_text":"Feng Zheng, Jinming Duan, Jinrui Zhang, Qingni Wang, Teng Wang, TianTian Geng","cross_cats":["cs.CL","cs.LG","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-29T15:18:06Z","title":"LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19772","kind":"arxiv","version":3},"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:d65b39d895b5af1785a33154e4e0d8aeddc1e1fa2684f22a5a331b15c87a0c03","target":"record","created_at":"2026-07-05T10:35:42Z","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":"1501f926f745fab85c39899047e5b03d1f5e33efc66f505b42712bb5b224828c","cross_cats_sorted":["cs.CL","cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-29T15:18:06Z","title_canon_sha256":"3735ab76c10f0013efad43c39ff56f993f8d443f5fffa66ec3cd4ab02acac1fd"},"schema_version":"1.0","source":{"id":"2411.19772","kind":"arxiv","version":3}},"canonical_sha256":"4b36791a986e6e93b90347fddcad39f8fd830b38da0e915afc33a22336a9194d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b36791a986e6e93b90347fddcad39f8fd830b38da0e915afc33a22336a9194d","first_computed_at":"2026-07-05T10:35:42.511849Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:35:42.511849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GnPgFUP3UnWNnFxFB7tg62lcopcfIhbg8Be6Dds2LvpcGcztEA1JVjw3WGdmIgVWUWo37YdbSMwjgiKPnPg/Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:35:42.512514Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.19772","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d65b39d895b5af1785a33154e4e0d8aeddc1e1fa2684f22a5a331b15c87a0c03","sha256:bc5ab958b4169462ecb7e0f4648d5b99ca5c5e597d3bafa99db2a3396e0ae73e"],"state_sha256":"836c7d43751fc0763b0ef796d13ebdf19398bf3a1d96ffa7fb40668413539ec4"}