{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:QSX7JTM7XF6WWC6M3OMJLYHKSN","short_pith_number":"pith:QSX7JTM7","canonical_record":{"source":{"id":"2604.27403","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-04-30T04:14:58Z","cross_cats_sorted":[],"title_canon_sha256":"4ed3f33b72e04b0909782a8826dc8534512801f58b7108b4331c5d82270ba6a5","abstract_canon_sha256":"304dff7e5ffd81de6d0ddf3d70f72ff3e0933202140b2f046e9c2748258ab37c"},"schema_version":"1.0"},"canonical_sha256":"84aff4cd9fb97d6b0bccdb9895e0ea934b2b1073542da811fe4c3329a884f647","source":{"kind":"arxiv","id":"2604.27403","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.27403","created_at":"2026-07-09T01:20:05Z"},{"alias_kind":"arxiv_version","alias_value":"2604.27403v2","created_at":"2026-07-09T01:20:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.27403","created_at":"2026-07-09T01:20:05Z"},{"alias_kind":"pith_short_12","alias_value":"QSX7JTM7XF6W","created_at":"2026-07-09T01:20:05Z"},{"alias_kind":"pith_short_16","alias_value":"QSX7JTM7XF6WWC6M","created_at":"2026-07-09T01:20:05Z"},{"alias_kind":"pith_short_8","alias_value":"QSX7JTM7","created_at":"2026-07-09T01:20:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:QSX7JTM7XF6WWC6M3OMJLYHKSN","target":"record","payload":{"canonical_record":{"source":{"id":"2604.27403","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-04-30T04:14:58Z","cross_cats_sorted":[],"title_canon_sha256":"4ed3f33b72e04b0909782a8826dc8534512801f58b7108b4331c5d82270ba6a5","abstract_canon_sha256":"304dff7e5ffd81de6d0ddf3d70f72ff3e0933202140b2f046e9c2748258ab37c"},"schema_version":"1.0"},"canonical_sha256":"84aff4cd9fb97d6b0bccdb9895e0ea934b2b1073542da811fe4c3329a884f647","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-09T01:20:05.078165Z","signature_b64":"2rw05X8Cru0I87dNrqfuifXqH0qS5bVOIc7c1ffRoxdvaL/OeQtAq/U/pkS+G6W3FKJ7o5jP4pqIhZY2bvOGBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84aff4cd9fb97d6b0bccdb9895e0ea934b2b1073542da811fe4c3329a884f647","last_reissued_at":"2026-07-09T01:20:05.077430Z","signature_status":"signed_v1","first_computed_at":"2026-07-09T01:20:05.077430Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.27403","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-09T01:20:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FUIa23Cac0xJ4VvkaEAT5933IDDyYymkJtA4687x08j3+QwBdjH7C5fUTOjZpkZvaDqmFF6kHxsPuENQIA1MCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T19:19:17.464100Z"},"content_sha256":"958870f85067307325e2672c6b25b51ce15ccf9f12ead40573daefc36200e5b6","schema_version":"1.0","event_id":"sha256:958870f85067307325e2672c6b25b51ce15ccf9f12ead40573daefc36200e5b6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:QSX7JTM7XF6WWC6M3OMJLYHKSN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Knowledge-Driven Approach to Target Speech Extraction in the Presence of Background Sound Effects for Cinematic Audio Source Separation (CASS)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Detecting manners of articulation from mixed audio and adding them as a knowledge vector improves target speech extraction amid cinematic background sounds.","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Chin-Hui Lee, Chun-wei Ho, Kai Li, Sabato Marco Siniscalchi","submitted_at":"2026-04-30T04:14:58Z","abstract_excerpt":"We propose a knowledge-driven approach to speech target extraction in the presence of background sound effects already recorded in cinematic audio. The specific knowledge sources studied are manners of articulation that are detected in speech frames and adopted to form a knowledge vector as a part of features to enhance speech separation and target speech extraction because some short speech segments are often difficult to separate from mixed background sounds. Testing on the recent Sound Demixing Challenge data for cinematic audio source separation (CASS) shows that utilizing articulator-awar"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"utilizing articulator-aware knowledge sources produces better separation results than those obtained without using any knowledge, especially for speech segments buried in unspecified background sound events.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That manners of articulation can be detected reliably from mixed audio frames and that the resulting knowledge vector supplies non-redundant, useful information that improves separation without introducing new errors or requiring extra labeled data.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Detecting manners of articulation and adding them as knowledge features improves target speech extraction in cinematic audio with background sounds.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Detecting manners of articulation from mixed audio and adding them as a knowledge vector improves target speech extraction amid cinematic background sounds.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"049044bdb1c3cea73bd714b664b80fff3ab9c1de8c0590fe3841f9a6a00cb884"},"source":{"id":"2604.27403","kind":"arxiv","version":2},"verdict":{"id":"90497f46-f8fb-4eca-8223-d4ddd69c6143","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-07T08:10:41.244649Z","strongest_claim":"utilizing articulator-aware knowledge sources produces better separation results than those obtained without using any knowledge, especially for speech segments buried in unspecified background sound events.","one_line_summary":"Detecting manners of articulation and adding them as knowledge features improves target speech extraction in cinematic audio with background sounds.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That manners of articulation can be detected reliably from mixed audio frames and that the resulting knowledge vector supplies non-redundant, useful information that improves separation without introducing new errors or requiring extra labeled data.","pith_extraction_headline":"Detecting manners of articulation from mixed audio and adding them as a knowledge vector improves target speech extraction amid cinematic background sounds."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.27403/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T22:37:05.152364Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T19:16:02.553960Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"e7769544d21432cc8015e71778b880582fa425cadd88d1735373ea32ab5045c2"},"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":"90497f46-f8fb-4eca-8223-d4ddd69c6143"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-09T01:20:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k4+DIHz7eVKLV2E0TQQrVOBCfgSPJJm1wiOTfyJIhNFUcSx/1khdl5HgtwgVTg5BOAnWACn/0glbldnkoZZ6Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T19:19:17.464853Z"},"content_sha256":"c48f4732476835508c0ed2e29e35424091c72ebf6e648bde1f3dfa004dd3f83f","schema_version":"1.0","event_id":"sha256:c48f4732476835508c0ed2e29e35424091c72ebf6e648bde1f3dfa004dd3f83f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QSX7JTM7XF6WWC6M3OMJLYHKSN/bundle.json","state_url":"https://pith.science/pith/QSX7JTM7XF6WWC6M3OMJLYHKSN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QSX7JTM7XF6WWC6M3OMJLYHKSN/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":"2026-08-13T19:19:17Z","links":{"resolver":"https://pith.science/pith/QSX7JTM7XF6WWC6M3OMJLYHKSN","bundle":"https://pith.science/pith/QSX7JTM7XF6WWC6M3OMJLYHKSN/bundle.json","state":"https://pith.science/pith/QSX7JTM7XF6WWC6M3OMJLYHKSN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QSX7JTM7XF6WWC6M3OMJLYHKSN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QSX7JTM7XF6WWC6M3OMJLYHKSN","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":"304dff7e5ffd81de6d0ddf3d70f72ff3e0933202140b2f046e9c2748258ab37c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-04-30T04:14:58Z","title_canon_sha256":"4ed3f33b72e04b0909782a8826dc8534512801f58b7108b4331c5d82270ba6a5"},"schema_version":"1.0","source":{"id":"2604.27403","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.27403","created_at":"2026-07-09T01:20:05Z"},{"alias_kind":"arxiv_version","alias_value":"2604.27403v2","created_at":"2026-07-09T01:20:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.27403","created_at":"2026-07-09T01:20:05Z"},{"alias_kind":"pith_short_12","alias_value":"QSX7JTM7XF6W","created_at":"2026-07-09T01:20:05Z"},{"alias_kind":"pith_short_16","alias_value":"QSX7JTM7XF6WWC6M","created_at":"2026-07-09T01:20:05Z"},{"alias_kind":"pith_short_8","alias_value":"QSX7JTM7","created_at":"2026-07-09T01:20:05Z"}],"graph_snapshots":[{"event_id":"sha256:c48f4732476835508c0ed2e29e35424091c72ebf6e648bde1f3dfa004dd3f83f","target":"graph","created_at":"2026-07-09T01:20:05Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"utilizing articulator-aware knowledge sources produces better separation results than those obtained without using any knowledge, especially for speech segments buried in unspecified background sound events."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That manners of articulation can be detected reliably from mixed audio frames and that the resulting knowledge vector supplies non-redundant, useful information that improves separation without introducing new errors or requiring extra labeled data."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Detecting manners of articulation and adding them as knowledge features improves target speech extraction in cinematic audio with background sounds."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Detecting manners of articulation from mixed audio and adding them as a knowledge vector improves target speech extraction amid cinematic background sounds."}],"snapshot_sha256":"049044bdb1c3cea73bd714b664b80fff3ab9c1de8c0590fe3841f9a6a00cb884"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T22:37:05.152364Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T19:16:02.553960Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2604.27403/integrity.json","findings":[],"snapshot_sha256":"e7769544d21432cc8015e71778b880582fa425cadd88d1735373ea32ab5045c2","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a knowledge-driven approach to speech target extraction in the presence of background sound effects already recorded in cinematic audio. The specific knowledge sources studied are manners of articulation that are detected in speech frames and adopted to form a knowledge vector as a part of features to enhance speech separation and target speech extraction because some short speech segments are often difficult to separate from mixed background sounds. Testing on the recent Sound Demixing Challenge data for cinematic audio source separation (CASS) shows that utilizing articulator-awar","authors_text":"Chin-Hui Lee, Chun-wei Ho, Kai Li, Sabato Marco Siniscalchi","cross_cats":[],"headline":"Detecting manners of articulation from mixed audio and adding them as a knowledge vector improves target speech extraction amid cinematic background sounds.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-04-30T04:14:58Z","title":"A Knowledge-Driven Approach to Target Speech Extraction in the Presence of Background Sound Effects for Cinematic Audio Source Separation (CASS)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.27403","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-07T08:10:41.244649Z","id":"90497f46-f8fb-4eca-8223-d4ddd69c6143","model_set":{"reader":"grok-4.3"},"one_line_summary":"Detecting manners of articulation and adding them as knowledge features improves target speech extraction in cinematic audio with background sounds.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Detecting manners of articulation from mixed audio and adding them as a knowledge vector improves target speech extraction amid cinematic background sounds.","strongest_claim":"utilizing articulator-aware knowledge sources produces better separation results than those obtained without using any knowledge, especially for speech segments buried in unspecified background sound events.","weakest_assumption":"That manners of articulation can be detected reliably from mixed audio frames and that the resulting knowledge vector supplies non-redundant, useful information that improves separation without introducing new errors or requiring extra labeled data."}},"verdict_id":"90497f46-f8fb-4eca-8223-d4ddd69c6143"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:958870f85067307325e2672c6b25b51ce15ccf9f12ead40573daefc36200e5b6","target":"record","created_at":"2026-07-09T01:20:05Z","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":"304dff7e5ffd81de6d0ddf3d70f72ff3e0933202140b2f046e9c2748258ab37c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-04-30T04:14:58Z","title_canon_sha256":"4ed3f33b72e04b0909782a8826dc8534512801f58b7108b4331c5d82270ba6a5"},"schema_version":"1.0","source":{"id":"2604.27403","kind":"arxiv","version":2}},"canonical_sha256":"84aff4cd9fb97d6b0bccdb9895e0ea934b2b1073542da811fe4c3329a884f647","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"84aff4cd9fb97d6b0bccdb9895e0ea934b2b1073542da811fe4c3329a884f647","first_computed_at":"2026-07-09T01:20:05.077430Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-09T01:20:05.077430Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2rw05X8Cru0I87dNrqfuifXqH0qS5bVOIc7c1ffRoxdvaL/OeQtAq/U/pkS+G6W3FKJ7o5jP4pqIhZY2bvOGBg==","signature_status":"signed_v1","signed_at":"2026-07-09T01:20:05.078165Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.27403","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:958870f85067307325e2672c6b25b51ce15ccf9f12ead40573daefc36200e5b6","sha256:c48f4732476835508c0ed2e29e35424091c72ebf6e648bde1f3dfa004dd3f83f"],"state_sha256":"798f030c332bf0658c544ae3dc89af33445eb613c4eebf8533ebf6d0c7940bba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LIkf0YESxcqYJorkym/ATrSP4EjdVPcpFg/eg+nQYCHmdTuRwRYL0HT82DyzrNSiW2Ct1qLF6VjSqCKQGJfeCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T19:19:17.481811Z","bundle_sha256":"7819ae8eb727fd8aac1cd9639885ad99b60457cc05ab74a1e635c3ff250eef03"}}