{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ID2LEUVHPZCXHOBKGQEDRZRGO5","short_pith_number":"pith:ID2LEUVH","canonical_record":{"source":{"id":"2310.11713","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-18T05:03:57Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"fc98139977e21fdf5c95b9a96b6deca5f2045f75f31830ae9167a0639e39dac6","abstract_canon_sha256":"36810adec713e2ca94664a447f5918742da8a626866b274cec7dd734b69aa275"},"schema_version":"1.0"},"canonical_sha256":"40f4b252a77e4573b82a340838e62677541c3109e8db002c46ae2128e74198c4","source":{"kind":"arxiv","id":"2310.11713","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.11713","created_at":"2026-07-05T07:02:11Z"},{"alias_kind":"arxiv_version","alias_value":"2310.11713v1","created_at":"2026-07-05T07:02:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.11713","created_at":"2026-07-05T07:02:11Z"},{"alias_kind":"pith_short_12","alias_value":"ID2LEUVHPZCX","created_at":"2026-07-05T07:02:11Z"},{"alias_kind":"pith_short_16","alias_value":"ID2LEUVHPZCXHOBK","created_at":"2026-07-05T07:02:11Z"},{"alias_kind":"pith_short_8","alias_value":"ID2LEUVH","created_at":"2026-07-05T07:02:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ID2LEUVHPZCXHOBKGQEDRZRGO5","target":"record","payload":{"canonical_record":{"source":{"id":"2310.11713","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-18T05:03:57Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"fc98139977e21fdf5c95b9a96b6deca5f2045f75f31830ae9167a0639e39dac6","abstract_canon_sha256":"36810adec713e2ca94664a447f5918742da8a626866b274cec7dd734b69aa275"},"schema_version":"1.0"},"canonical_sha256":"40f4b252a77e4573b82a340838e62677541c3109e8db002c46ae2128e74198c4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:11.273136Z","signature_b64":"W9SbpN0vjkiWBkHLLruiSJyN5eHNxLtD9c2PT9ruYXEoruKBI95gbyR5IkSmVmjAHqmb2Ad+zq3nEyqrK3C8CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40f4b252a77e4573b82a340838e62677541c3109e8db002c46ae2128e74198c4","last_reissued_at":"2026-07-05T07:02:11.272683Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:11.272683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.11713","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":"2026-07-05T07:02:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"35uxN8dg69Rr8ejGvQjvdOejEA9YK0xw+zIDaDrRtJwwDRAHlEEE30e+z614cs+ahBtPF1Yfer/9UfG5GR2YDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T01:20:41.959078Z"},"content_sha256":"8d770c2479ab8b10af27ffe6deacc1548a9d6fc126738539e55078a8fbd7bda6","schema_version":"1.0","event_id":"sha256:8d770c2479ab8b10af27ffe6deacc1548a9d6fc126738539e55078a8fbd7bda6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ID2LEUVHPZCXHOBKGQEDRZRGO5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Separating Invisible Sounds Toward Universal Audiovisual Scene-Aware Sound Separation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Ali Vosoughi, Chenliang Xu, Shijian Deng, Yapeng Tian, Yiyang Su","submitted_at":"2023-10-18T05:03:57Z","abstract_excerpt":"The audio-visual sound separation field assumes visible sources in videos, but this excludes invisible sounds beyond the camera's view. Current methods struggle with such sounds lacking visible cues. This paper introduces a novel \"Audio-Visual Scene-Aware Separation\" (AVSA-Sep) framework. It includes a semantic parser for visible and invisible sounds and a separator for scene-informed separation. AVSA-Sep successfully separates both sound types, with joint training and cross-modal alignment enhancing effectiveness."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.11713","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/2310.11713/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":"2026-07-05T07:02:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tOdYYQZi9AC6R5IzUQ5n/kOaVlmCLXRhncHV1EKchYAjDWF9T9UZaElaZwq9HEw+ir2mhKWQu+J3DI1F4SmoCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T01:20:41.959728Z"},"content_sha256":"8a43de0e98cf533ff6918f247c3118af4edc8fa189473e9c4cebe551763f32da","schema_version":"1.0","event_id":"sha256:8a43de0e98cf533ff6918f247c3118af4edc8fa189473e9c4cebe551763f32da"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ID2LEUVHPZCXHOBKGQEDRZRGO5/bundle.json","state_url":"https://pith.science/pith/ID2LEUVHPZCXHOBKGQEDRZRGO5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ID2LEUVHPZCXHOBKGQEDRZRGO5/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":"2026-08-19T01:20:41Z","links":{"resolver":"https://pith.science/pith/ID2LEUVHPZCXHOBKGQEDRZRGO5","bundle":"https://pith.science/pith/ID2LEUVHPZCXHOBKGQEDRZRGO5/bundle.json","state":"https://pith.science/pith/ID2LEUVHPZCXHOBKGQEDRZRGO5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ID2LEUVHPZCXHOBKGQEDRZRGO5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ID2LEUVHPZCXHOBKGQEDRZRGO5","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":"36810adec713e2ca94664a447f5918742da8a626866b274cec7dd734b69aa275","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-18T05:03:57Z","title_canon_sha256":"fc98139977e21fdf5c95b9a96b6deca5f2045f75f31830ae9167a0639e39dac6"},"schema_version":"1.0","source":{"id":"2310.11713","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.11713","created_at":"2026-07-05T07:02:11Z"},{"alias_kind":"arxiv_version","alias_value":"2310.11713v1","created_at":"2026-07-05T07:02:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.11713","created_at":"2026-07-05T07:02:11Z"},{"alias_kind":"pith_short_12","alias_value":"ID2LEUVHPZCX","created_at":"2026-07-05T07:02:11Z"},{"alias_kind":"pith_short_16","alias_value":"ID2LEUVHPZCXHOBK","created_at":"2026-07-05T07:02:11Z"},{"alias_kind":"pith_short_8","alias_value":"ID2LEUVH","created_at":"2026-07-05T07:02:11Z"}],"graph_snapshots":[{"event_id":"sha256:8a43de0e98cf533ff6918f247c3118af4edc8fa189473e9c4cebe551763f32da","target":"graph","created_at":"2026-07-05T07:02:11Z","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/2310.11713/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The audio-visual sound separation field assumes visible sources in videos, but this excludes invisible sounds beyond the camera's view. Current methods struggle with such sounds lacking visible cues. This paper introduces a novel \"Audio-Visual Scene-Aware Separation\" (AVSA-Sep) framework. It includes a semantic parser for visible and invisible sounds and a separator for scene-informed separation. AVSA-Sep successfully separates both sound types, with joint training and cross-modal alignment enhancing effectiveness.","authors_text":"Ali Vosoughi, Chenliang Xu, Shijian Deng, Yapeng Tian, Yiyang Su","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-18T05:03:57Z","title":"Separating Invisible Sounds Toward Universal Audiovisual Scene-Aware Sound Separation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.11713","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":"sha256:8d770c2479ab8b10af27ffe6deacc1548a9d6fc126738539e55078a8fbd7bda6","target":"record","created_at":"2026-07-05T07:02:11Z","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":"36810adec713e2ca94664a447f5918742da8a626866b274cec7dd734b69aa275","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-18T05:03:57Z","title_canon_sha256":"fc98139977e21fdf5c95b9a96b6deca5f2045f75f31830ae9167a0639e39dac6"},"schema_version":"1.0","source":{"id":"2310.11713","kind":"arxiv","version":1}},"canonical_sha256":"40f4b252a77e4573b82a340838e62677541c3109e8db002c46ae2128e74198c4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"40f4b252a77e4573b82a340838e62677541c3109e8db002c46ae2128e74198c4","first_computed_at":"2026-07-05T07:02:11.272683Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:02:11.272683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W9SbpN0vjkiWBkHLLruiSJyN5eHNxLtD9c2PT9ruYXEoruKBI95gbyR5IkSmVmjAHqmb2Ad+zq3nEyqrK3C8CA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:02:11.273136Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.11713","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d770c2479ab8b10af27ffe6deacc1548a9d6fc126738539e55078a8fbd7bda6","sha256:8a43de0e98cf533ff6918f247c3118af4edc8fa189473e9c4cebe551763f32da"],"state_sha256":"cd6a283230de642f6f8889c2998fe7492c50b8958fa0035bfdac2359485f672b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2dpvz5nSrtV4dXyXzX+rz5DUapV2u67A+XhRgEapP/u48w971mFtuLvcwweuPMnlGJlCFJjrVbpqlnVO5GVrCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T01:20:41.963873Z","bundle_sha256":"a0d046b3e660a097abd82edd52fb7a313d6ad5f171110729ee71bfacd62d3f76"}}