{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KZMVSYAVKGE45TIRHFO2IMBLPH","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":"413ff5ecb068d0025b8c70edc7af42baf465cd38c52778259a7579d4b2dcea11","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T18:59:56Z","title_canon_sha256":"94f10b60626b826efac36b24a2f3c2a8f280bd4dbbeedd782903768594370281"},"schema_version":"1.0","source":{"id":"2412.18609","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.18609","created_at":"2026-07-05T10:40:15Z"},{"alias_kind":"arxiv_version","alias_value":"2412.18609v2","created_at":"2026-07-05T10:40:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18609","created_at":"2026-07-05T10:40:15Z"},{"alias_kind":"pith_short_12","alias_value":"KZMVSYAVKGE4","created_at":"2026-07-05T10:40:15Z"},{"alias_kind":"pith_short_16","alias_value":"KZMVSYAVKGE45TIR","created_at":"2026-07-05T10:40:15Z"},{"alias_kind":"pith_short_8","alias_value":"KZMVSYAV","created_at":"2026-07-05T10:40:15Z"}],"graph_snapshots":[{"event_id":"sha256:d0cd11db4dd9938c120c569277d5a401624f9f747ed36919a6125d98b662c273","target":"graph","created_at":"2026-07-05T10:40:15Z","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/2412.18609/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present an efficient encoder-free approach for video-language understanding that achieves competitive performance while significantly reducing computational overhead. Current video-language models typically rely on heavyweight image encoders (300M-1.1B parameters) or video encoders (1B-1.4B parameters), creating a substantial computational burden when processing multi-frame videos. Our method introduces a novel Spatio-Temporal Alignment Block (STAB) that directly processes video inputs without requiring pre-trained encoders while using only 45M parameters for visual processing - at least a ","authors_text":"Jinhui Yi, Juergen Gall, Muzammal Naseer, Syed Talal Wasim, Yanan Luo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T18:59:56Z","title":"Video-Panda: Parameter-efficient Alignment for Encoder-free Video-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18609","kind":"arxiv","version":2},"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":"sha256:8c7cc0e4ee7aab33ba3ccf2fc58c6b882bc2a20420c63e37fa554e4471b2273d","target":"record","created_at":"2026-07-05T10:40:15Z","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":"413ff5ecb068d0025b8c70edc7af42baf465cd38c52778259a7579d4b2dcea11","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T18:59:56Z","title_canon_sha256":"94f10b60626b826efac36b24a2f3c2a8f280bd4dbbeedd782903768594370281"},"schema_version":"1.0","source":{"id":"2412.18609","kind":"arxiv","version":2}},"canonical_sha256":"56595960155189cecd11395da4302b79edd9f9d7e724c8fa319b18da85165d67","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"56595960155189cecd11395da4302b79edd9f9d7e724c8fa319b18da85165d67","first_computed_at":"2026-07-05T10:40:15.945570Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:40:15.945570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3xNfWH9DcGsTFappR0Ts8DrDCzLayTNzNRjuFlXW/rzdz4Zph6EJ2QsGuaV/xal/hn5xXJFKLHqtE++NuiG8Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:40:15.946056Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.18609","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c7cc0e4ee7aab33ba3ccf2fc58c6b882bc2a20420c63e37fa554e4471b2273d","sha256:d0cd11db4dd9938c120c569277d5a401624f9f747ed36919a6125d98b662c273"],"state_sha256":"15d4d4bc9a7c0ec06da020ac4056e0d9da20e2255553342c34518cdade12f8b9"}