{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AOFVIHTTCM65I74ZJJ2WZT7TQD","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":"e50a3e0ad3039878438a8e27ac56ac4b459643b522a470d5f3c51bd89e107a81","cross_cats_sorted":["cs.CV","cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-09-27T20:26:34Z","title_canon_sha256":"0120b2c1327f405f02be6ac77676b63c3af88bc754d75e43785f391a0d6314c0"},"schema_version":"1.0","source":{"id":"2409.19132","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.19132","created_at":"2026-07-05T09:13:11Z"},{"alias_kind":"arxiv_version","alias_value":"2409.19132v1","created_at":"2026-07-05T09:13:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19132","created_at":"2026-07-05T09:13:11Z"},{"alias_kind":"pith_short_12","alias_value":"AOFVIHTTCM65","created_at":"2026-07-05T09:13:11Z"},{"alias_kind":"pith_short_16","alias_value":"AOFVIHTTCM65I74Z","created_at":"2026-07-05T09:13:11Z"},{"alias_kind":"pith_short_8","alias_value":"AOFVIHTT","created_at":"2026-07-05T09:13:11Z"}],"graph_snapshots":[{"event_id":"sha256:2e6634bcd4ed046e20cf836d1efe158774a45c51f1066e359210a1743f3a27b5","target":"graph","created_at":"2026-07-05T09:13:11Z","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/2409.19132/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video encompasses both visual and auditory data, creating a perceptually rich experience where these two modalities complement each other. As such, videos are a valuable type of media for the investigation of the interplay between audio and visual elements. Previous studies of audio-visual modalities primarily focused on either audio-visual representation learning or generative modeling of a modality conditioned on the other, creating a disconnect between these two branches. A unified framework that learns representation and generates modalities has not been developed yet. In this work, we int","authors_text":"Eli Shlizerman, Kun Su, Xiulong Liu","cross_cats":["cs.CV","cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-09-27T20:26:34Z","title":"From Vision to Audio and Beyond: A Unified Model for Audio-Visual Representation and Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19132","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":"sha256:80de2bbae38715052e44d8c1aee5c31c3a1338f649b494627f3c84afb54e8fe3","target":"record","created_at":"2026-07-05T09:13:11Z","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":"e50a3e0ad3039878438a8e27ac56ac4b459643b522a470d5f3c51bd89e107a81","cross_cats_sorted":["cs.CV","cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-09-27T20:26:34Z","title_canon_sha256":"0120b2c1327f405f02be6ac77676b63c3af88bc754d75e43785f391a0d6314c0"},"schema_version":"1.0","source":{"id":"2409.19132","kind":"arxiv","version":1}},"canonical_sha256":"038b541e73133dd47f994a756ccff380f2ffa9b93a48bdf319627bb02da91191","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"038b541e73133dd47f994a756ccff380f2ffa9b93a48bdf319627bb02da91191","first_computed_at":"2026-07-05T09:13:11.061198Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:13:11.061198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JSFwRQUj8FU2QssMu/dNT+xm0r13rJqFDq/IsoX5jmbPFluEfOp4te5nbaW0r4YkJ/g3W0mTfRzsJ22vMLuSAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:13:11.061653Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.19132","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80de2bbae38715052e44d8c1aee5c31c3a1338f649b494627f3c84afb54e8fe3","sha256:2e6634bcd4ed046e20cf836d1efe158774a45c51f1066e359210a1743f3a27b5"],"state_sha256":"a90392a411d160355d98fa3be1ba9894f375260a63003f5c1ccb67ec4f5baa18"}