{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CYPNHBW7IQCJZ3VPDWMYJF2BXV","short_pith_number":"pith:CYPNHBW7","schema_version":"1.0","canonical_sha256":"161ed386df44049ceeaf1d99849741bd7260d01c49e0d99b40f782042911b0dd","source":{"kind":"arxiv","id":"2606.00620","version":1},"attestation_state":"computed","paper":{"title":"FlowNar: Scalable Streaming Narration for Long-Form Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengzhi Wu, David Schneider, Frederik Diederichs, Juergen Beyerer, Juergen Gall, Manuel Martin, Zeyun Zhong","submitted_at":"2026-05-30T08:51:28Z","abstract_excerpt":"Recent Large Multimodal Models (LMMs), primarily designed for offline settings, are ill-suited for the dynamic requirements of streaming video. While recent online adaptations improve real-time processing, they still face critical scalability challenges, with resource demands typically growing at least linearly with video duration. To overcome this bottleneck, we propose FlowNar, a novel framework for scalable streaming video narration. The core of FlowNar is a dynamic context management strategy for historical visual context removal, combined with our CLAM (Cross Linear Attentive Memory) modu"},"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":"2606.00620","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-30T08:51:28Z","cross_cats_sorted":[],"title_canon_sha256":"7eb6e77d75952b407f94897ad2b80de071fac4a4801a5a6a5cfbaa82631bab5b","abstract_canon_sha256":"6741af132951df6525967f481ba407c6f4ff58620c59e164657327a74cacd361"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:04:00.030564Z","signature_b64":"XOpi9yS6sujoGK0uPBZUgguMl/4TMEQ+HoKFsXGA47m7EhTBBrS3QgKUYmi9tVzM1YJTdDgp7E6Z1u1VXdANBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"161ed386df44049ceeaf1d99849741bd7260d01c49e0d99b40f782042911b0dd","last_reissued_at":"2026-06-02T01:04:00.030153Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:04:00.030153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FlowNar: Scalable Streaming Narration for Long-Form Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengzhi Wu, David Schneider, Frederik Diederichs, Juergen Beyerer, Juergen Gall, Manuel Martin, Zeyun Zhong","submitted_at":"2026-05-30T08:51:28Z","abstract_excerpt":"Recent Large Multimodal Models (LMMs), primarily designed for offline settings, are ill-suited for the dynamic requirements of streaming video. While recent online adaptations improve real-time processing, they still face critical scalability challenges, with resource demands typically growing at least linearly with video duration. To overcome this bottleneck, we propose FlowNar, a novel framework for scalable streaming video narration. The core of FlowNar is a dynamic context management strategy for historical visual context removal, combined with our CLAM (Cross Linear Attentive Memory) modu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00620","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/2606.00620/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":"2606.00620","created_at":"2026-06-02T01:04:00.030213+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00620v1","created_at":"2026-06-02T01:04:00.030213+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00620","created_at":"2026-06-02T01:04:00.030213+00:00"},{"alias_kind":"pith_short_12","alias_value":"CYPNHBW7IQCJ","created_at":"2026-06-02T01:04:00.030213+00:00"},{"alias_kind":"pith_short_16","alias_value":"CYPNHBW7IQCJZ3VP","created_at":"2026-06-02T01:04:00.030213+00:00"},{"alias_kind":"pith_short_8","alias_value":"CYPNHBW7","created_at":"2026-06-02T01:04:00.030213+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CYPNHBW7IQCJZ3VPDWMYJF2BXV","json":"https://pith.science/pith/CYPNHBW7IQCJZ3VPDWMYJF2BXV.json","graph_json":"https://pith.science/api/pith-number/CYPNHBW7IQCJZ3VPDWMYJF2BXV/graph.json","events_json":"https://pith.science/api/pith-number/CYPNHBW7IQCJZ3VPDWMYJF2BXV/events.json","paper":"https://pith.science/paper/CYPNHBW7"},"agent_actions":{"view_html":"https://pith.science/pith/CYPNHBW7IQCJZ3VPDWMYJF2BXV","download_json":"https://pith.science/pith/CYPNHBW7IQCJZ3VPDWMYJF2BXV.json","view_paper":"https://pith.science/paper/CYPNHBW7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00620&json=true","fetch_graph":"https://pith.science/api/pith-number/CYPNHBW7IQCJZ3VPDWMYJF2BXV/graph.json","fetch_events":"https://pith.science/api/pith-number/CYPNHBW7IQCJZ3VPDWMYJF2BXV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CYPNHBW7IQCJZ3VPDWMYJF2BXV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CYPNHBW7IQCJZ3VPDWMYJF2BXV/action/storage_attestation","attest_author":"https://pith.science/pith/CYPNHBW7IQCJZ3VPDWMYJF2BXV/action/author_attestation","sign_citation":"https://pith.science/pith/CYPNHBW7IQCJZ3VPDWMYJF2BXV/action/citation_signature","submit_replication":"https://pith.science/pith/CYPNHBW7IQCJZ3VPDWMYJF2BXV/action/replication_record"}},"created_at":"2026-06-02T01:04:00.030213+00:00","updated_at":"2026-06-02T01:04:00.030213+00:00"}