{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:34YASO6O3TNJ37X2JUREXJUSF4","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":"41a634760f3dac420e73b5674596bbe703535a3bc3dabd3256001e2b5db9f1b0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-29T03:09:46Z","title_canon_sha256":"a49505782c82423a5ace6790c5f1361887e92352facc0035ad0a3c847a2cc9e6"},"schema_version":"1.0","source":{"id":"2504.20384","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.20384","created_at":"2026-07-05T10:55:41Z"},{"alias_kind":"arxiv_version","alias_value":"2504.20384v1","created_at":"2026-07-05T10:55:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.20384","created_at":"2026-07-05T10:55:41Z"},{"alias_kind":"pith_short_12","alias_value":"34YASO6O3TNJ","created_at":"2026-07-05T10:55:41Z"},{"alias_kind":"pith_short_16","alias_value":"34YASO6O3TNJ37X2","created_at":"2026-07-05T10:55:41Z"},{"alias_kind":"pith_short_8","alias_value":"34YASO6O","created_at":"2026-07-05T10:55:41Z"}],"graph_snapshots":[{"event_id":"sha256:41d2aa3542ef8744a07adf61b7a7ca85774ed0bfc5328009d9314078a4edae88","target":"graph","created_at":"2026-07-05T10:55:41Z","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/2504.20384/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in video understanding within visual large language models (VLLMs) have led to notable progress. However, the complexity of video data and contextual processing limitations still hinder long-video comprehension. A common approach is video feature compression to reduce token input to large language models, yet many methods either fail to prioritize essential features, leading to redundant inter-frame information, or introduce computationally expensive modules.To address these issues, we propose FiLA(Fine-grained Vision Language Model)-Video, a novel framework that leverages ","authors_text":"Bo Zheng, Hanqing Yang, Jun Song, Shiding Zhu, Wenhui Dong, Xianing Chen, Xuan Zhang, Yanan Guo, Yang Du, Yingbo Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-29T03:09:46Z","title":"FiLA-Video: Spatio-Temporal Compression for Fine-Grained Long Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.20384","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":"sha256:0ac3c378ac0cb9398a9b415fe316b9f4aef3f30fddd375efbd74998acef67572","target":"record","created_at":"2026-07-05T10:55:41Z","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":"41a634760f3dac420e73b5674596bbe703535a3bc3dabd3256001e2b5db9f1b0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-29T03:09:46Z","title_canon_sha256":"a49505782c82423a5ace6790c5f1361887e92352facc0035ad0a3c847a2cc9e6"},"schema_version":"1.0","source":{"id":"2504.20384","kind":"arxiv","version":1}},"canonical_sha256":"df30093bcedcda9dfefa4d224ba6922f1bdf5c467c1aeb7d2c55b875078d0ca8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df30093bcedcda9dfefa4d224ba6922f1bdf5c467c1aeb7d2c55b875078d0ca8","first_computed_at":"2026-07-05T10:55:41.667338Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:55:41.667338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YP46IYyX7MTWs3N6KTLdrPOxFHWByxngfpm/v2rGg0QJVwYI3JKF/TkQDjrKQiuZI5zjJC3NiDGqEBLSPxSoAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:55:41.667829Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.20384","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0ac3c378ac0cb9398a9b415fe316b9f4aef3f30fddd375efbd74998acef67572","sha256:41d2aa3542ef8744a07adf61b7a7ca85774ed0bfc5328009d9314078a4edae88"],"state_sha256":"239740bbf65af098215b032a8389e6955c23c6d2a57af44dd366abe9218cbb4c"}