{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:BW6F5RNE2A2BMNQ3P6Y6GAOMFP","short_pith_number":"pith:BW6F5RNE","canonical_record":{"source":{"id":"2303.08372","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-03-15T05:17:53Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"452f8fb4c3914e8d15c84990c88f56871ecdb476543ea92435bc403d44a31f55","abstract_canon_sha256":"715d3e610cbc676f4d2c61183e74190efb133d93eaafad32ea0bf521f5e79009"},"schema_version":"1.0"},"canonical_sha256":"0dbc5ec5a4d03416361b7fb1e301cc2bd30a26450051d1ff8c5cb56563e9a850","source":{"kind":"arxiv","id":"2303.08372","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.08372","created_at":"2026-07-05T05:51:32Z"},{"alias_kind":"arxiv_version","alias_value":"2303.08372v1","created_at":"2026-07-05T05:51:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.08372","created_at":"2026-07-05T05:51:32Z"},{"alias_kind":"pith_short_12","alias_value":"BW6F5RNE2A2B","created_at":"2026-07-05T05:51:32Z"},{"alias_kind":"pith_short_16","alias_value":"BW6F5RNE2A2BMNQ3","created_at":"2026-07-05T05:51:32Z"},{"alias_kind":"pith_short_8","alias_value":"BW6F5RNE","created_at":"2026-07-05T05:51:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:BW6F5RNE2A2BMNQ3P6Y6GAOMFP","target":"record","payload":{"canonical_record":{"source":{"id":"2303.08372","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-03-15T05:17:53Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"452f8fb4c3914e8d15c84990c88f56871ecdb476543ea92435bc403d44a31f55","abstract_canon_sha256":"715d3e610cbc676f4d2c61183e74190efb133d93eaafad32ea0bf521f5e79009"},"schema_version":"1.0"},"canonical_sha256":"0dbc5ec5a4d03416361b7fb1e301cc2bd30a26450051d1ff8c5cb56563e9a850","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:51:32.245952Z","signature_b64":"+b13NM9++XeQ5aSlodmNxSAILwYrIVW4nzG4gROw57NI5F7LzdJPQxQlgOOPuXz2ebcfrPDVX9lngWFr8E0UCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0dbc5ec5a4d03416361b7fb1e301cc2bd30a26450051d1ff8c5cb56563e9a850","last_reissued_at":"2026-07-05T05:51:32.245581Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:51:32.245581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.08372","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":"2026-07-05T05:51:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IT2Cnoj7pQfTmWIhPgGby5MDzWEhcFrjYOw+BlAgXnvMR/6TamhAJUNfHt1rILzLWRXlExOc8xi1Ig2L+n2ZCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:42:20.934857Z"},"content_sha256":"73a7898c3cd21943eef62a5509a4652d94a2f9ff63227055b2e4d98012df2177","schema_version":"1.0","event_id":"sha256:73a7898c3cd21943eef62a5509a4652d94a2f9ff63227055b2e4d98012df2177"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:BW6F5RNE2A2BMNQ3P6Y6GAOMFP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Target Sound Extraction with Variable Cross-modality Clues","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chenda Li, Dongmei Wang, Michael Zeng, Shujie Liu, Takuya Yoshioka, Yanmin Qian, Yao Qian, Zhuo Chen","submitted_at":"2023-03-15T05:17:53Z","abstract_excerpt":"Automatic target sound extraction (TSE) is a machine learning approach to mimic the human auditory perception capability of attending to a sound source of interest from a mixture of sources. It often uses a model conditioned on a fixed form of target sound clues, such as a sound class label, which limits the ways in which users can interact with the model to specify the target sounds. To leverage variable number of clues cross modalities available in the inference phase, including a video, a sound event class, and a text caption, we propose a unified transformer-based TSE model architecture, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.08372","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/2303.08372/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":"2026-07-05T05:51:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AOG9xL7fG0NXrAOs/VAd+w5tJA9R30HbGc4gDks7qwm9ZGOQdEIG1P5T3C84JvdMl+vvROCwl+XV/ODnKra+Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:42:20.935409Z"},"content_sha256":"54e9994d7113cd00176be1e3bf78aeadb24f9304bc8148a01583753d968ee805","schema_version":"1.0","event_id":"sha256:54e9994d7113cd00176be1e3bf78aeadb24f9304bc8148a01583753d968ee805"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BW6F5RNE2A2BMNQ3P6Y6GAOMFP/bundle.json","state_url":"https://pith.science/pith/BW6F5RNE2A2BMNQ3P6Y6GAOMFP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BW6F5RNE2A2BMNQ3P6Y6GAOMFP/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":"2026-08-09T00:42:20Z","links":{"resolver":"https://pith.science/pith/BW6F5RNE2A2BMNQ3P6Y6GAOMFP","bundle":"https://pith.science/pith/BW6F5RNE2A2BMNQ3P6Y6GAOMFP/bundle.json","state":"https://pith.science/pith/BW6F5RNE2A2BMNQ3P6Y6GAOMFP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BW6F5RNE2A2BMNQ3P6Y6GAOMFP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BW6F5RNE2A2BMNQ3P6Y6GAOMFP","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":"715d3e610cbc676f4d2c61183e74190efb133d93eaafad32ea0bf521f5e79009","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-03-15T05:17:53Z","title_canon_sha256":"452f8fb4c3914e8d15c84990c88f56871ecdb476543ea92435bc403d44a31f55"},"schema_version":"1.0","source":{"id":"2303.08372","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.08372","created_at":"2026-07-05T05:51:32Z"},{"alias_kind":"arxiv_version","alias_value":"2303.08372v1","created_at":"2026-07-05T05:51:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.08372","created_at":"2026-07-05T05:51:32Z"},{"alias_kind":"pith_short_12","alias_value":"BW6F5RNE2A2B","created_at":"2026-07-05T05:51:32Z"},{"alias_kind":"pith_short_16","alias_value":"BW6F5RNE2A2BMNQ3","created_at":"2026-07-05T05:51:32Z"},{"alias_kind":"pith_short_8","alias_value":"BW6F5RNE","created_at":"2026-07-05T05:51:32Z"}],"graph_snapshots":[{"event_id":"sha256:54e9994d7113cd00176be1e3bf78aeadb24f9304bc8148a01583753d968ee805","target":"graph","created_at":"2026-07-05T05:51:32Z","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/2303.08372/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatic target sound extraction (TSE) is a machine learning approach to mimic the human auditory perception capability of attending to a sound source of interest from a mixture of sources. It often uses a model conditioned on a fixed form of target sound clues, such as a sound class label, which limits the ways in which users can interact with the model to specify the target sounds. To leverage variable number of clues cross modalities available in the inference phase, including a video, a sound event class, and a text caption, we propose a unified transformer-based TSE model architecture, w","authors_text":"Chenda Li, Dongmei Wang, Michael Zeng, Shujie Liu, Takuya Yoshioka, Yanmin Qian, Yao Qian, Zhuo Chen","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-03-15T05:17:53Z","title":"Target Sound Extraction with Variable Cross-modality Clues"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.08372","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":"sha256:73a7898c3cd21943eef62a5509a4652d94a2f9ff63227055b2e4d98012df2177","target":"record","created_at":"2026-07-05T05:51:32Z","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":"715d3e610cbc676f4d2c61183e74190efb133d93eaafad32ea0bf521f5e79009","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-03-15T05:17:53Z","title_canon_sha256":"452f8fb4c3914e8d15c84990c88f56871ecdb476543ea92435bc403d44a31f55"},"schema_version":"1.0","source":{"id":"2303.08372","kind":"arxiv","version":1}},"canonical_sha256":"0dbc5ec5a4d03416361b7fb1e301cc2bd30a26450051d1ff8c5cb56563e9a850","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0dbc5ec5a4d03416361b7fb1e301cc2bd30a26450051d1ff8c5cb56563e9a850","first_computed_at":"2026-07-05T05:51:32.245581Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:51:32.245581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+b13NM9++XeQ5aSlodmNxSAILwYrIVW4nzG4gROw57NI5F7LzdJPQxQlgOOPuXz2ebcfrPDVX9lngWFr8E0UCw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:51:32.245952Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.08372","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73a7898c3cd21943eef62a5509a4652d94a2f9ff63227055b2e4d98012df2177","sha256:54e9994d7113cd00176be1e3bf78aeadb24f9304bc8148a01583753d968ee805"],"state_sha256":"c6264d2e8fe5bc0a422a49c0150fe3866daab0485f960ecaba0ac6e464731c22"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jwhk05HyBHswbKhg+nJg6+E7+luEv4RScqI9jps1H5SmoNnFxfONzXQjUeoXJcUoEoLhsb9ObQC547UK5TCSAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T00:42:20.938849Z","bundle_sha256":"975cbeb8e36e2e1a1f66535d7fe96872623592396a93d0c03f99fa5dd735fea5"}}