{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KZMVSYAVKGE45TIRHFO2IMBLPH","short_pith_number":"pith:KZMVSYAV","canonical_record":{"source":{"id":"2412.18609","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T18:59:56Z","cross_cats_sorted":[],"title_canon_sha256":"94f10b60626b826efac36b24a2f3c2a8f280bd4dbbeedd782903768594370281","abstract_canon_sha256":"413ff5ecb068d0025b8c70edc7af42baf465cd38c52778259a7579d4b2dcea11"},"schema_version":"1.0"},"canonical_sha256":"56595960155189cecd11395da4302b79edd9f9d7e724c8fa319b18da85165d67","source":{"kind":"arxiv","id":"2412.18609","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KZMVSYAVKGE45TIRHFO2IMBLPH","target":"record","payload":{"canonical_record":{"source":{"id":"2412.18609","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T18:59:56Z","cross_cats_sorted":[],"title_canon_sha256":"94f10b60626b826efac36b24a2f3c2a8f280bd4dbbeedd782903768594370281","abstract_canon_sha256":"413ff5ecb068d0025b8c70edc7af42baf465cd38c52778259a7579d4b2dcea11"},"schema_version":"1.0"},"canonical_sha256":"56595960155189cecd11395da4302b79edd9f9d7e724c8fa319b18da85165d67","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:40:15.946056Z","signature_b64":"3xNfWH9DcGsTFappR0Ts8DrDCzLayTNzNRjuFlXW/rzdz4Zph6EJ2QsGuaV/xal/hn5xXJFKLHqtE++NuiG8Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56595960155189cecd11395da4302b79edd9f9d7e724c8fa319b18da85165d67","last_reissued_at":"2026-07-05T10:40:15.945570Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:40:15.945570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.18609","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:40:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/mvWz2MjeWP+8xL+4VBUEqNRTqQbVrYonw76e9mC8m/MHIr6bQf7rIebg/EGBRS+RJKbdrfnJZjThbpUsMMtDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:20:41.799243Z"},"content_sha256":"8c7cc0e4ee7aab33ba3ccf2fc58c6b882bc2a20420c63e37fa554e4471b2273d","schema_version":"1.0","event_id":"sha256:8c7cc0e4ee7aab33ba3ccf2fc58c6b882bc2a20420c63e37fa554e4471b2273d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KZMVSYAVKGE45TIRHFO2IMBLPH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Video-Panda: Parameter-efficient Alignment for Encoder-free Video-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinhui Yi, Juergen Gall, Muzammal Naseer, Syed Talal Wasim, Yanan Luo","submitted_at":"2024-12-24T18:59:56Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18609","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/2412.18609/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:40:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ERibuwF7mN3NXWIPIUYNux8H4fQw/PBv5bIZGU6trPU3WoPuQXftsW5NTDEpiL6QiKDShV7wJ7lFcROasaEgCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:20:41.799631Z"},"content_sha256":"d0cd11db4dd9938c120c569277d5a401624f9f747ed36919a6125d98b662c273","schema_version":"1.0","event_id":"sha256:d0cd11db4dd9938c120c569277d5a401624f9f747ed36919a6125d98b662c273"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KZMVSYAVKGE45TIRHFO2IMBLPH/bundle.json","state_url":"https://pith.science/pith/KZMVSYAVKGE45TIRHFO2IMBLPH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KZMVSYAVKGE45TIRHFO2IMBLPH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T03:20:41Z","links":{"resolver":"https://pith.science/pith/KZMVSYAVKGE45TIRHFO2IMBLPH","bundle":"https://pith.science/pith/KZMVSYAVKGE45TIRHFO2IMBLPH/bundle.json","state":"https://pith.science/pith/KZMVSYAVKGE45TIRHFO2IMBLPH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KZMVSYAVKGE45TIRHFO2IMBLPH/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nn86N7VcwykxfJnaRov+C4FmPWcGaQELQE2Rmh9sv3ctwQf8aQNcSB980KwJ3gduWEXe7NeA/zi7QMx1Yx/VAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T03:20:41.801599Z","bundle_sha256":"1e841a4193218c5eb408d9682bf3341dea453561715aa361b6be5b719eaa5e4d"}}