{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:34YASO6O3TNJ37X2JUREXJUSF4","short_pith_number":"pith:34YASO6O","schema_version":"1.0","canonical_sha256":"df30093bcedcda9dfefa4d224ba6922f1bdf5c467c1aeb7d2c55b875078d0ca8","source":{"kind":"arxiv","id":"2504.20384","version":1},"attestation_state":"computed","paper":{"title":"FiLA-Video: Spatio-Temporal Compression for Fine-Grained Long Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Zheng, Hanqing Yang, Jun Song, Shiding Zhu, Wenhui Dong, Xianing Chen, Xuan Zhang, Yanan Guo, Yang Du, Yingbo Wang","submitted_at":"2025-04-29T03:09:46Z","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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2504.20384","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-29T03:09:46Z","cross_cats_sorted":[],"title_canon_sha256":"a49505782c82423a5ace6790c5f1361887e92352facc0035ad0a3c847a2cc9e6","abstract_canon_sha256":"41a634760f3dac420e73b5674596bbe703535a3bc3dabd3256001e2b5db9f1b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:55:41.667829Z","signature_b64":"YP46IYyX7MTWs3N6KTLdrPOxFHWByxngfpm/v2rGg0QJVwYI3JKF/TkQDjrKQiuZI5zjJC3NiDGqEBLSPxSoAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df30093bcedcda9dfefa4d224ba6922f1bdf5c467c1aeb7d2c55b875078d0ca8","last_reissued_at":"2026-07-05T10:55:41.667338Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:55:41.667338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FiLA-Video: Spatio-Temporal Compression for Fine-Grained Long Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Zheng, Hanqing Yang, Jun Song, Shiding Zhu, Wenhui Dong, Xianing Chen, Xuan Zhang, Yanan Guo, Yang Du, Yingbo Wang","submitted_at":"2025-04-29T03:09:46Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.20384","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2504.20384/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2504.20384","created_at":"2026-07-05T10:55:41.667400+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.20384v1","created_at":"2026-07-05T10:55:41.667400+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.20384","created_at":"2026-07-05T10:55:41.667400+00:00"},{"alias_kind":"pith_short_12","alias_value":"34YASO6O3TNJ","created_at":"2026-07-05T10:55:41.667400+00:00"},{"alias_kind":"pith_short_16","alias_value":"34YASO6O3TNJ37X2","created_at":"2026-07-05T10:55:41.667400+00:00"},{"alias_kind":"pith_short_8","alias_value":"34YASO6O","created_at":"2026-07-05T10:55:41.667400+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16909","citing_title":"TOBench: A Task-Oriented Omni-Modal Benchmark for Real-World Tool-Using Agents","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/34YASO6O3TNJ37X2JUREXJUSF4","json":"https://pith.science/pith/34YASO6O3TNJ37X2JUREXJUSF4.json","graph_json":"https://pith.science/api/pith-number/34YASO6O3TNJ37X2JUREXJUSF4/graph.json","events_json":"https://pith.science/api/pith-number/34YASO6O3TNJ37X2JUREXJUSF4/events.json","paper":"https://pith.science/paper/34YASO6O"},"agent_actions":{"view_html":"https://pith.science/pith/34YASO6O3TNJ37X2JUREXJUSF4","download_json":"https://pith.science/pith/34YASO6O3TNJ37X2JUREXJUSF4.json","view_paper":"https://pith.science/paper/34YASO6O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.20384&json=true","fetch_graph":"https://pith.science/api/pith-number/34YASO6O3TNJ37X2JUREXJUSF4/graph.json","fetch_events":"https://pith.science/api/pith-number/34YASO6O3TNJ37X2JUREXJUSF4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/34YASO6O3TNJ37X2JUREXJUSF4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/34YASO6O3TNJ37X2JUREXJUSF4/action/storage_attestation","attest_author":"https://pith.science/pith/34YASO6O3TNJ37X2JUREXJUSF4/action/author_attestation","sign_citation":"https://pith.science/pith/34YASO6O3TNJ37X2JUREXJUSF4/action/citation_signature","submit_replication":"https://pith.science/pith/34YASO6O3TNJ37X2JUREXJUSF4/action/replication_record"}},"created_at":"2026-07-05T10:55:41.667400+00:00","updated_at":"2026-07-05T10:55:41.667400+00:00"}