{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:ICQOKRG2EVV36TZ6YM6OE227RR","short_pith_number":"pith:ICQOKRG2","canonical_record":{"source":{"id":"2210.16472","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-10-29T02:55:39Z","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"title_canon_sha256":"2d8f11f2f962cc21865e3f80e69a137fc60438ff13d871b49a03065b131ba5c8","abstract_canon_sha256":"87209e460d7b66c432772e192fb198a31bd82769fe9a2ea6860bddebc8c07e24"},"schema_version":"1.0"},"canonical_sha256":"40a0e544da256bbf4f3ec33ce26b5f8c61e7bf4c976b0179d4cd7583c65579af","source":{"kind":"arxiv","id":"2210.16472","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.16472","created_at":"2026-07-05T05:11:46Z"},{"alias_kind":"arxiv_version","alias_value":"2210.16472v1","created_at":"2026-07-05T05:11:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.16472","created_at":"2026-07-05T05:11:46Z"},{"alias_kind":"pith_short_12","alias_value":"ICQOKRG2EVV3","created_at":"2026-07-05T05:11:46Z"},{"alias_kind":"pith_short_16","alias_value":"ICQOKRG2EVV36TZ6","created_at":"2026-07-05T05:11:46Z"},{"alias_kind":"pith_short_8","alias_value":"ICQOKRG2","created_at":"2026-07-05T05:11:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:ICQOKRG2EVV36TZ6YM6OE227RR","target":"record","payload":{"canonical_record":{"source":{"id":"2210.16472","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-10-29T02:55:39Z","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"title_canon_sha256":"2d8f11f2f962cc21865e3f80e69a137fc60438ff13d871b49a03065b131ba5c8","abstract_canon_sha256":"87209e460d7b66c432772e192fb198a31bd82769fe9a2ea6860bddebc8c07e24"},"schema_version":"1.0"},"canonical_sha256":"40a0e544da256bbf4f3ec33ce26b5f8c61e7bf4c976b0179d4cd7583c65579af","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:11:46.808546Z","signature_b64":"2rqs6u5s61IhNquriXNiXY5fEiRIlS8BIcJMCVDWNm9FP3ZktYonbf2J0pvWGro+9X5dG3QvlzQVuwVC3hZeDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40a0e544da256bbf4f3ec33ce26b5f8c61e7bf4c976b0179d4cd7583c65579af","last_reissued_at":"2026-07-05T05:11:46.808047Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:11:46.808047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.16472","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":"2026-07-05T05:11:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zStp6idBBj5uETd/TDdkACrN8Q7hFvsWZV0O1OP8PHf2FSgi7Bes26vZuEqG0+gaSGpCMfSEtEsJqONgPZwhDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:28:39.912124Z"},"content_sha256":"14a1a9a9f4c6c79fb32a13a61782ca79d4c094cde12afb31153fc80ebb477e80","schema_version":"1.0","event_id":"sha256:14a1a9a9f4c6c79fb32a13a61782ca79d4c094cde12afb31153fc80ebb477e80"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:ICQOKRG2EVV36TZ6YM6OE227RR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Audio-Visual Dynamics Using Scene Graphs for Audio Source Separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Anoop Cherian, Moitreya Chatterjee, Narendra Ahuja","submitted_at":"2022-10-29T02:55:39Z","abstract_excerpt":"There exists an unequivocal distinction between the sound produced by a static source and that produced by a moving one, especially when the source moves towards or away from the microphone. In this paper, we propose to use this connection between audio and visual dynamics for solving two challenging tasks simultaneously, namely: (i) separating audio sources from a mixture using visual cues, and (ii) predicting the 3D visual motion of a sounding source using its separated audio. Towards this end, we present Audio Separator and Motion Predictor (ASMP) -- a deep learning framework that leverages"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.16472","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/2210.16472/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":"2026-07-05T05:11:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ibCyUIdYTKrvSZXyggkNaI+H2d8kk1N7MPj0xaQgN4j/otASPVHAPPJmc1Ci4HZS8/ykd6QtyM0ymtXMcE+8Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:28:39.913116Z"},"content_sha256":"0f370692b0d1b4fc57d45a579635df7cf3394079337007932f6de5e8e445cb84","schema_version":"1.0","event_id":"sha256:0f370692b0d1b4fc57d45a579635df7cf3394079337007932f6de5e8e445cb84"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ICQOKRG2EVV36TZ6YM6OE227RR/bundle.json","state_url":"https://pith.science/pith/ICQOKRG2EVV36TZ6YM6OE227RR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ICQOKRG2EVV36TZ6YM6OE227RR/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":"2026-08-04T03:28:39Z","links":{"resolver":"https://pith.science/pith/ICQOKRG2EVV36TZ6YM6OE227RR","bundle":"https://pith.science/pith/ICQOKRG2EVV36TZ6YM6OE227RR/bundle.json","state":"https://pith.science/pith/ICQOKRG2EVV36TZ6YM6OE227RR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ICQOKRG2EVV36TZ6YM6OE227RR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ICQOKRG2EVV36TZ6YM6OE227RR","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":"87209e460d7b66c432772e192fb198a31bd82769fe9a2ea6860bddebc8c07e24","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-10-29T02:55:39Z","title_canon_sha256":"2d8f11f2f962cc21865e3f80e69a137fc60438ff13d871b49a03065b131ba5c8"},"schema_version":"1.0","source":{"id":"2210.16472","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.16472","created_at":"2026-07-05T05:11:46Z"},{"alias_kind":"arxiv_version","alias_value":"2210.16472v1","created_at":"2026-07-05T05:11:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.16472","created_at":"2026-07-05T05:11:46Z"},{"alias_kind":"pith_short_12","alias_value":"ICQOKRG2EVV3","created_at":"2026-07-05T05:11:46Z"},{"alias_kind":"pith_short_16","alias_value":"ICQOKRG2EVV36TZ6","created_at":"2026-07-05T05:11:46Z"},{"alias_kind":"pith_short_8","alias_value":"ICQOKRG2","created_at":"2026-07-05T05:11:46Z"}],"graph_snapshots":[{"event_id":"sha256:0f370692b0d1b4fc57d45a579635df7cf3394079337007932f6de5e8e445cb84","target":"graph","created_at":"2026-07-05T05:11:46Z","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/2210.16472/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There exists an unequivocal distinction between the sound produced by a static source and that produced by a moving one, especially when the source moves towards or away from the microphone. In this paper, we propose to use this connection between audio and visual dynamics for solving two challenging tasks simultaneously, namely: (i) separating audio sources from a mixture using visual cues, and (ii) predicting the 3D visual motion of a sounding source using its separated audio. Towards this end, we present Audio Separator and Motion Predictor (ASMP) -- a deep learning framework that leverages","authors_text":"Anoop Cherian, Moitreya Chatterjee, Narendra Ahuja","cross_cats":["cs.CV","cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-10-29T02:55:39Z","title":"Learning Audio-Visual Dynamics Using Scene Graphs for Audio Source Separation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.16472","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":"sha256:14a1a9a9f4c6c79fb32a13a61782ca79d4c094cde12afb31153fc80ebb477e80","target":"record","created_at":"2026-07-05T05:11:46Z","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":"87209e460d7b66c432772e192fb198a31bd82769fe9a2ea6860bddebc8c07e24","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-10-29T02:55:39Z","title_canon_sha256":"2d8f11f2f962cc21865e3f80e69a137fc60438ff13d871b49a03065b131ba5c8"},"schema_version":"1.0","source":{"id":"2210.16472","kind":"arxiv","version":1}},"canonical_sha256":"40a0e544da256bbf4f3ec33ce26b5f8c61e7bf4c976b0179d4cd7583c65579af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"40a0e544da256bbf4f3ec33ce26b5f8c61e7bf4c976b0179d4cd7583c65579af","first_computed_at":"2026-07-05T05:11:46.808047Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:11:46.808047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2rqs6u5s61IhNquriXNiXY5fEiRIlS8BIcJMCVDWNm9FP3ZktYonbf2J0pvWGro+9X5dG3QvlzQVuwVC3hZeDg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:11:46.808546Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.16472","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:14a1a9a9f4c6c79fb32a13a61782ca79d4c094cde12afb31153fc80ebb477e80","sha256:0f370692b0d1b4fc57d45a579635df7cf3394079337007932f6de5e8e445cb84"],"state_sha256":"7662f9fe74fae2c28f00ed96d24c2917cb616b036bd4fe6351456c8631b31ca0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o11MCc3TB7z0ppeQ/pIydtbaUty1JxDu4OCoyQbrPyTYMDHabxsDGNw10ZqdkWbTBA5+EG9T6venKloWeryyBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T03:28:39.922635Z","bundle_sha256":"98c927bdd9206248c7a7bf32de04dba391e9a3be9c9ced0a8b68dd17d9609905"}}