{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:UJHZSYJDHBYJ5LZJ7QALJTRSYF","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":"13e474d1f43b94da4e46a9ef06d7906637beafe098512c0752ff4a40bad7c3e6","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-15T17:59:11Z","title_canon_sha256":"40a6cdfa88a4c61aca05db886ffc781bdf7d421b220c6db5d62cea1289f22807"},"schema_version":"1.0","source":{"id":"2207.07646","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.07646","created_at":"2026-07-05T04:40:34Z"},{"alias_kind":"arxiv_version","alias_value":"2207.07646v1","created_at":"2026-07-05T04:40:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.07646","created_at":"2026-07-05T04:40:34Z"},{"alias_kind":"pith_short_12","alias_value":"UJHZSYJDHBYJ","created_at":"2026-07-05T04:40:34Z"},{"alias_kind":"pith_short_16","alias_value":"UJHZSYJDHBYJ5LZJ","created_at":"2026-07-05T04:40:34Z"},{"alias_kind":"pith_short_8","alias_value":"UJHZSYJD","created_at":"2026-07-05T04:40:34Z"}],"graph_snapshots":[{"event_id":"sha256:1ff9bf24b16accd8662d346dba40309b4ac74b507df21de1dcdecee35194faea","target":"graph","created_at":"2026-07-05T04:40:34Z","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/2207.07646/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Utilizing vision and language models (VLMs) pre-trained on large-scale image-text pairs is becoming a promising paradigm for open-vocabulary visual recognition. In this work, we extend this paradigm by leveraging motion and audio that naturally exist in video. We present \\textbf{MOV}, a simple yet effective method for \\textbf{M}ultimodal \\textbf{O}pen-\\textbf{V}ocabulary video classification. In MOV, we directly use the vision encoder from pre-trained VLMs with minimal modifications to encode video, optical flow and audio spectrogram. We design a cross-modal fusion mechanism to aggregate compl","authors_text":"Ming-Hsuan Yang, Rui Qian, Serge Belongie, Yeqing Li, Yin Cui, Zheng Xu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-15T17:59:11Z","title":"Multimodal Open-Vocabulary Video Classification via Pre-Trained Vision and Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.07646","kind":"arxiv","version":1},"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":"sha256:0bb535c1b0f4c3e5881e7ae00a79894c7b261a749440746b95f2a2638431a93a","target":"record","created_at":"2026-07-05T04:40:34Z","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":"13e474d1f43b94da4e46a9ef06d7906637beafe098512c0752ff4a40bad7c3e6","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-15T17:59:11Z","title_canon_sha256":"40a6cdfa88a4c61aca05db886ffc781bdf7d421b220c6db5d62cea1289f22807"},"schema_version":"1.0","source":{"id":"2207.07646","kind":"arxiv","version":1}},"canonical_sha256":"a24f99612338709eaf29fc00b4ce32c158c39096ca00f471fcebaadcd3f7a5e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a24f99612338709eaf29fc00b4ce32c158c39096ca00f471fcebaadcd3f7a5e4","first_computed_at":"2026-07-05T04:40:34.771819Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:40:34.771819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S8uUQ3Kdqxc0EwNhhOMytDJYEQqHYRzw+N2S54Au8CN3CIbC6LaFxalCxWHY5AchsUTm8Y2ZUuXHhDxG2dW2CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:40:34.772227Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.07646","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0bb535c1b0f4c3e5881e7ae00a79894c7b261a749440746b95f2a2638431a93a","sha256:1ff9bf24b16accd8662d346dba40309b4ac74b507df21de1dcdecee35194faea"],"state_sha256":"9154e52463d98c3becb4348f90a717a01906aaede6a32a03204c5749b0c4e1b8"}