{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HOUUNOAL5ACGTLM4Z5JBNC4I56","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":"ac7637742d5478596be3ed76421b6e47a54823880adc11e8c9407ced0da608b1","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-14T15:44:19Z","title_canon_sha256":"965b3e5b5b87360c8215009b4ce6295ecafbc5fbf7c305715c6876b1a2389d51"},"schema_version":"1.0","source":{"id":"2403.09502","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.09502","created_at":"2026-07-05T08:34:15Z"},{"alias_kind":"arxiv_version","alias_value":"2403.09502v2","created_at":"2026-07-05T08:34:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09502","created_at":"2026-07-05T08:34:15Z"},{"alias_kind":"pith_short_12","alias_value":"HOUUNOAL5ACG","created_at":"2026-07-05T08:34:15Z"},{"alias_kind":"pith_short_16","alias_value":"HOUUNOAL5ACGTLM4","created_at":"2026-07-05T08:34:15Z"},{"alias_kind":"pith_short_8","alias_value":"HOUUNOAL","created_at":"2026-07-05T08:34:15Z"}],"graph_snapshots":[{"event_id":"sha256:2e65dd5af587081d1fa45e0bcbdeb0ca44603622bb04d0ecb3888f340f84d877","target":"graph","created_at":"2026-07-05T08:34:15Z","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/2403.09502/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in self-supervised audio-visual representation learning have demonstrated its potential to capture rich and comprehensive representations. However, despite the advantages of data augmentation verified in many learning methods, audio-visual learning has struggled to fully harness these benefits, as augmentations can easily disrupt the correspondence between input pairs. To address this limitation, we introduce EquiAV, a novel framework that leverages equivariance for audio-visual contrastive learning. Our approach begins with extending equivariance to audio-visual learning, ","authors_text":"Hyeongkeun Lee, Jongsuk Kim, Joon Son Chung, Junmo Kim, Kyeongha Rho","cross_cats":["cs.AI","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-14T15:44:19Z","title":"EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09502","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":"sha256:1b4a2102f5a79df537038276c40911ed642f835e512bcd40e972e6c755ab6b29","target":"record","created_at":"2026-07-05T08:34:15Z","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":"ac7637742d5478596be3ed76421b6e47a54823880adc11e8c9407ced0da608b1","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-14T15:44:19Z","title_canon_sha256":"965b3e5b5b87360c8215009b4ce6295ecafbc5fbf7c305715c6876b1a2389d51"},"schema_version":"1.0","source":{"id":"2403.09502","kind":"arxiv","version":2}},"canonical_sha256":"3ba946b80be80469ad9ccf52168b88efa95d72ecfcdf58c06d992229fa158253","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ba946b80be80469ad9ccf52168b88efa95d72ecfcdf58c06d992229fa158253","first_computed_at":"2026-07-05T08:34:15.448269Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:34:15.448269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eqa2moEa5ENP4Q/efP/09HHM3ujCIIMUL7LQImM/FxiwBDUR4UfsTNNcp1flyQ6FS7Rpt7vUzG16qElgAYklBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:34:15.448721Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.09502","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1b4a2102f5a79df537038276c40911ed642f835e512bcd40e972e6c755ab6b29","sha256:2e65dd5af587081d1fa45e0bcbdeb0ca44603622bb04d0ecb3888f340f84d877"],"state_sha256":"e79646eaedcaf87ec56dc6320ca19cd0493767d22fe31ce5e7efff1c9621aa38"}