{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:W237ARI7DLYDFU7BCL66N4G2SN","short_pith_number":"pith:W237ARI7","canonical_record":{"source":{"id":"2607.10299","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-11T13:04:24Z","cross_cats_sorted":[],"title_canon_sha256":"400ccdc3d711dca5e0c1294cac48f890529afce6b11387fa7462136bbc549b02","abstract_canon_sha256":"f84b64fcb7e8c91d2976650e43cec5d3133eb6d50063ded7382ba1b45143221b"},"schema_version":"1.0"},"canonical_sha256":"b6b7f0451f1af032d3e112fde6f0da9359a9e410cd230ab7b13d57268bfd0558","source":{"kind":"arxiv","id":"2607.10299","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.10299","created_at":"2026-07-14T01:21:08Z"},{"alias_kind":"arxiv_version","alias_value":"2607.10299v1","created_at":"2026-07-14T01:21:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10299","created_at":"2026-07-14T01:21:08Z"},{"alias_kind":"pith_short_12","alias_value":"W237ARI7DLYD","created_at":"2026-07-14T01:21:08Z"},{"alias_kind":"pith_short_16","alias_value":"W237ARI7DLYDFU7B","created_at":"2026-07-14T01:21:08Z"},{"alias_kind":"pith_short_8","alias_value":"W237ARI7","created_at":"2026-07-14T01:21:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:W237ARI7DLYDFU7BCL66N4G2SN","target":"record","payload":{"canonical_record":{"source":{"id":"2607.10299","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-11T13:04:24Z","cross_cats_sorted":[],"title_canon_sha256":"400ccdc3d711dca5e0c1294cac48f890529afce6b11387fa7462136bbc549b02","abstract_canon_sha256":"f84b64fcb7e8c91d2976650e43cec5d3133eb6d50063ded7382ba1b45143221b"},"schema_version":"1.0"},"canonical_sha256":"b6b7f0451f1af032d3e112fde6f0da9359a9e410cd230ab7b13d57268bfd0558","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:21:08.212187Z","signature_b64":"NSt3+Idu0uPme+vbPsEtq54cDpvlj//LJXX+X0R6CxKPbdt7ZjL1zWVpVRFFWyyKAgd4en+2w5VTcW68IpJyAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6b7f0451f1af032d3e112fde6f0da9359a9e410cd230ab7b13d57268bfd0558","last_reissued_at":"2026-07-14T01:21:08.211384Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:21:08.211384Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.10299","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-14T01:21:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BitLWIMvSSi6A67OfQ+FuOmRcRyTrTs+TlShY+03moIIg7UGP5WoUBujM+Annd4H5vjkanvN9SepDBiYrr+vCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-22T04:08:36.972854Z"},"content_sha256":"e0734965f61d9000e47e9497bedfc1a3214608566c69a213d3c1e7e6fb70607a","schema_version":"1.0","event_id":"sha256:e0734965f61d9000e47e9497bedfc1a3214608566c69a213d3c1e7e6fb70607a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:W237ARI7DLYDFU7BCL66N4G2SN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Empowering Long-form Omni-modal Understanding with Robust Audio Perception","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Kaiying Yan, Luoyi Sun, Weidi Xie, Xiao Zhou","submitted_at":"2026-07-11T13:04:24Z","abstract_excerpt":"Recent advances in large-scale multimodal models have drivenremarkable progress in vision-language tasks; however, comprehensiveomni-modal understanding remains under-explored, largely due to thescarcity of datasets with rich, explicitly aligned auditory cues. To bridgethis gap, we present AVDC (Audio-Visual Decoupled Captions), a large-scaledataset designed to disentangle visual and auditory semantics. Specifi-cally, we propose an automated pipeline that leverages off-the-shelf mod-els to annotate videos with tripartite captions: visual-only (V), audio-only (A), and joint audio-visual (AV). T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10299","kind":"arxiv","version":1},"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/2607.10299/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":"2026-07-14T01:21:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZX4eIZ4qBSCMO1hgGPhOa0O/WNDkSwLDm+lzpRkHalBJENG/C1ma9MOcCcrnRZrlFL1hT8LT2SgWXFyTA20aCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-22T04:08:36.973215Z"},"content_sha256":"678d7e7b4c08e9301d875068305941a430b0eabca121bcfc8583d25def3e7b3c","schema_version":"1.0","event_id":"sha256:678d7e7b4c08e9301d875068305941a430b0eabca121bcfc8583d25def3e7b3c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W237ARI7DLYDFU7BCL66N4G2SN/bundle.json","state_url":"https://pith.science/pith/W237ARI7DLYDFU7BCL66N4G2SN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W237ARI7DLYDFU7BCL66N4G2SN/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":"2026-07-22T04:08:36Z","links":{"resolver":"https://pith.science/pith/W237ARI7DLYDFU7BCL66N4G2SN","bundle":"https://pith.science/pith/W237ARI7DLYDFU7BCL66N4G2SN/bundle.json","state":"https://pith.science/pith/W237ARI7DLYDFU7BCL66N4G2SN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W237ARI7DLYDFU7BCL66N4G2SN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:W237ARI7DLYDFU7BCL66N4G2SN","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":"f84b64fcb7e8c91d2976650e43cec5d3133eb6d50063ded7382ba1b45143221b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-11T13:04:24Z","title_canon_sha256":"400ccdc3d711dca5e0c1294cac48f890529afce6b11387fa7462136bbc549b02"},"schema_version":"1.0","source":{"id":"2607.10299","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.10299","created_at":"2026-07-14T01:21:08Z"},{"alias_kind":"arxiv_version","alias_value":"2607.10299v1","created_at":"2026-07-14T01:21:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10299","created_at":"2026-07-14T01:21:08Z"},{"alias_kind":"pith_short_12","alias_value":"W237ARI7DLYD","created_at":"2026-07-14T01:21:08Z"},{"alias_kind":"pith_short_16","alias_value":"W237ARI7DLYDFU7B","created_at":"2026-07-14T01:21:08Z"},{"alias_kind":"pith_short_8","alias_value":"W237ARI7","created_at":"2026-07-14T01:21:08Z"}],"graph_snapshots":[{"event_id":"sha256:678d7e7b4c08e9301d875068305941a430b0eabca121bcfc8583d25def3e7b3c","target":"graph","created_at":"2026-07-14T01:21:08Z","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/2607.10299/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in large-scale multimodal models have drivenremarkable progress in vision-language tasks; however, comprehensiveomni-modal understanding remains under-explored, largely due to thescarcity of datasets with rich, explicitly aligned auditory cues. To bridgethis gap, we present AVDC (Audio-Visual Decoupled Captions), a large-scaledataset designed to disentangle visual and auditory semantics. Specifi-cally, we propose an automated pipeline that leverages off-the-shelf mod-els to annotate videos with tripartite captions: visual-only (V), audio-only (A), and joint audio-visual (AV). T","authors_text":"Kaiying Yan, Luoyi Sun, Weidi Xie, Xiao Zhou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-11T13:04:24Z","title":"Empowering Long-form Omni-modal Understanding with Robust Audio Perception"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10299","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:e0734965f61d9000e47e9497bedfc1a3214608566c69a213d3c1e7e6fb70607a","target":"record","created_at":"2026-07-14T01:21:08Z","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":"f84b64fcb7e8c91d2976650e43cec5d3133eb6d50063ded7382ba1b45143221b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-11T13:04:24Z","title_canon_sha256":"400ccdc3d711dca5e0c1294cac48f890529afce6b11387fa7462136bbc549b02"},"schema_version":"1.0","source":{"id":"2607.10299","kind":"arxiv","version":1}},"canonical_sha256":"b6b7f0451f1af032d3e112fde6f0da9359a9e410cd230ab7b13d57268bfd0558","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b6b7f0451f1af032d3e112fde6f0da9359a9e410cd230ab7b13d57268bfd0558","first_computed_at":"2026-07-14T01:21:08.211384Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-14T01:21:08.211384Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NSt3+Idu0uPme+vbPsEtq54cDpvlj//LJXX+X0R6CxKPbdt7ZjL1zWVpVRFFWyyKAgd4en+2w5VTcW68IpJyAg==","signature_status":"signed_v1","signed_at":"2026-07-14T01:21:08.212187Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.10299","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e0734965f61d9000e47e9497bedfc1a3214608566c69a213d3c1e7e6fb70607a","sha256:678d7e7b4c08e9301d875068305941a430b0eabca121bcfc8583d25def3e7b3c"],"state_sha256":"1b2460c702a5a3f932c2558fd3bf737191c9cbb87bb95154c8c1eb7557d96133"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YRETCETxvkLd8qvBMzxTqSRfsxfkJRD36OJ1HGSBfA+mDb5jKb0CLScygPc8ibuQN5tkDXW4rDDpQRPQwlTFDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-22T04:08:36.975355Z","bundle_sha256":"98d72e4c4f61cdabe1618ced97733d5b3e1c9e13cb68bfd4430fae79a7477931"}}