{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:G6J7YWRE6CMTDQYJDP73D5KYVV","short_pith_number":"pith:G6J7YWRE","schema_version":"1.0","canonical_sha256":"3793fc5a24f09931c3091bffb1f558ad75046b6ff167154ef33f44220b01ad85","source":{"kind":"arxiv","id":"2503.03663","version":2},"attestation_state":"computed","paper":{"title":"LION-FS: Fast & Slow Video-Language Thinker as Online Video Assistant","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Hu, Leyang Shen, Liqiang Nie, Rui Shao, Wei Li","submitted_at":"2025-03-05T16:52:34Z","abstract_excerpt":"First-person video assistants are highly anticipated to enhance our daily lives through online video dialogue. However, existing online video assistants often sacrifice assistant efficacy for real-time efficiency by processing low-frame-rate videos with coarse-grained visual features.To overcome the trade-off between efficacy and efficiency, we propose \"Fast & Slow Video-Language Thinker\" as an onLIne videO assistaNt, LION-FS, achieving real-time, proactive, temporally accurate, and contextually precise responses. LION-FS adopts a two-stage optimization strategy: 1)Fast Path: Routing-Based Res"},"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":"2503.03663","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-05T16:52:34Z","cross_cats_sorted":[],"title_canon_sha256":"1e7817760752998ac952a3e24623991bec4fd3c8942712eb38c9bfe418187f7d","abstract_canon_sha256":"06d58e2eaddb364953e176eedac75a2733109cb46a7747dab1c9f1324d8e9e75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:25:20.283144Z","signature_b64":"u/xxiQhZq7W7tVdxNqgtH1ynJx1ahe6iShYrU59u8TOtUNV4C38YwT4fD2fHWZ9nZv6/yz6G1lqW9BPcnffRDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3793fc5a24f09931c3091bffb1f558ad75046b6ff167154ef33f44220b01ad85","last_reissued_at":"2026-07-05T10:25:20.282612Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:25:20.282612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LION-FS: Fast & Slow Video-Language Thinker as Online Video Assistant","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Hu, Leyang Shen, Liqiang Nie, Rui Shao, Wei Li","submitted_at":"2025-03-05T16:52:34Z","abstract_excerpt":"First-person video assistants are highly anticipated to enhance our daily lives through online video dialogue. However, existing online video assistants often sacrifice assistant efficacy for real-time efficiency by processing low-frame-rate videos with coarse-grained visual features.To overcome the trade-off between efficacy and efficiency, we propose \"Fast & Slow Video-Language Thinker\" as an onLIne videO assistaNt, LION-FS, achieving real-time, proactive, temporally accurate, and contextually precise responses. LION-FS adopts a two-stage optimization strategy: 1)Fast Path: Routing-Based Res"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.03663","kind":"arxiv","version":2},"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/2503.03663/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":"2503.03663","created_at":"2026-07-05T10:25:20.282684+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.03663v2","created_at":"2026-07-05T10:25:20.282684+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.03663","created_at":"2026-07-05T10:25:20.282684+00:00"},{"alias_kind":"pith_short_12","alias_value":"G6J7YWRE6CMT","created_at":"2026-07-05T10:25:20.282684+00:00"},{"alias_kind":"pith_short_16","alias_value":"G6J7YWRE6CMTDQYJ","created_at":"2026-07-05T10:25:20.282684+00:00"},{"alias_kind":"pith_short_8","alias_value":"G6J7YWRE","created_at":"2026-07-05T10:25:20.282684+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17798","citing_title":"LiveStarPro: Proactive Streaming Video Understanding with Hierarchical Memory for Long-Horizon Streams","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06991","citing_title":"Don't Pause: Streaming Video-Language Synchrony for Online Video Understanding","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G6J7YWRE6CMTDQYJDP73D5KYVV","json":"https://pith.science/pith/G6J7YWRE6CMTDQYJDP73D5KYVV.json","graph_json":"https://pith.science/api/pith-number/G6J7YWRE6CMTDQYJDP73D5KYVV/graph.json","events_json":"https://pith.science/api/pith-number/G6J7YWRE6CMTDQYJDP73D5KYVV/events.json","paper":"https://pith.science/paper/G6J7YWRE"},"agent_actions":{"view_html":"https://pith.science/pith/G6J7YWRE6CMTDQYJDP73D5KYVV","download_json":"https://pith.science/pith/G6J7YWRE6CMTDQYJDP73D5KYVV.json","view_paper":"https://pith.science/paper/G6J7YWRE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.03663&json=true","fetch_graph":"https://pith.science/api/pith-number/G6J7YWRE6CMTDQYJDP73D5KYVV/graph.json","fetch_events":"https://pith.science/api/pith-number/G6J7YWRE6CMTDQYJDP73D5KYVV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G6J7YWRE6CMTDQYJDP73D5KYVV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G6J7YWRE6CMTDQYJDP73D5KYVV/action/storage_attestation","attest_author":"https://pith.science/pith/G6J7YWRE6CMTDQYJDP73D5KYVV/action/author_attestation","sign_citation":"https://pith.science/pith/G6J7YWRE6CMTDQYJDP73D5KYVV/action/citation_signature","submit_replication":"https://pith.science/pith/G6J7YWRE6CMTDQYJDP73D5KYVV/action/replication_record"}},"created_at":"2026-07-05T10:25:20.282684+00:00","updated_at":"2026-07-05T10:25:20.282684+00:00"}