{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WWHFTDWXUPOEMFNJLVV4TVDS3X","short_pith_number":"pith:WWHFTDWX","canonical_record":{"source":{"id":"2401.04935","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-01-10T05:15:09Z","cross_cats_sorted":["cs.CL","cs.SD","eess.AS"],"title_canon_sha256":"467da2ec32f560ab18e28f77a1334ca4eed625d913ca0bcd001cbbc944247ecb","abstract_canon_sha256":"a446e4a76aec7cd21f993f3930ff613018a597971bd79bc41fd9fa10a5e97cb2"},"schema_version":"1.0"},"canonical_sha256":"b58e598ed7a3dc4615a95d6bc9d472ddf6216d1191834a26c1ca2945183bb752","source":{"kind":"arxiv","id":"2401.04935","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.04935","created_at":"2026-07-05T07:32:00Z"},{"alias_kind":"arxiv_version","alias_value":"2401.04935v1","created_at":"2026-07-05T07:32:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.04935","created_at":"2026-07-05T07:32:00Z"},{"alias_kind":"pith_short_12","alias_value":"WWHFTDWXUPOE","created_at":"2026-07-05T07:32:00Z"},{"alias_kind":"pith_short_16","alias_value":"WWHFTDWXUPOEMFNJ","created_at":"2026-07-05T07:32:00Z"},{"alias_kind":"pith_short_8","alias_value":"WWHFTDWX","created_at":"2026-07-05T07:32:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WWHFTDWXUPOEMFNJLVV4TVDS3X","target":"record","payload":{"canonical_record":{"source":{"id":"2401.04935","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-01-10T05:15:09Z","cross_cats_sorted":["cs.CL","cs.SD","eess.AS"],"title_canon_sha256":"467da2ec32f560ab18e28f77a1334ca4eed625d913ca0bcd001cbbc944247ecb","abstract_canon_sha256":"a446e4a76aec7cd21f993f3930ff613018a597971bd79bc41fd9fa10a5e97cb2"},"schema_version":"1.0"},"canonical_sha256":"b58e598ed7a3dc4615a95d6bc9d472ddf6216d1191834a26c1ca2945183bb752","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:32:00.712847Z","signature_b64":"OQFh1/hPk2VED6ZIMP8ujvRTfacP1flxMaSE8XIDfqlFkaJy+a4fAxg+SihIVKpTbDMOiSWqtDMwoQzthuJeCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b58e598ed7a3dc4615a95d6bc9d472ddf6216d1191834a26c1ca2945183bb752","last_reissued_at":"2026-07-05T07:32:00.712342Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:32:00.712342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.04935","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":"2026-07-05T07:32:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PIrM9XicrvQTjxwEvZ8U2aZIXd5ZpbFlzvwSWO+8Eyt2PhoOY96p1kxfG4mKn6w1Liauv4fEPtd5qMi2uLBjCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:12:47.728501Z"},"content_sha256":"df4d19cfbcb0a4284792c24eba2d88ca8202397affdab5554dfa6ee03098447b","schema_version":"1.0","event_id":"sha256:df4d19cfbcb0a4284792c24eba2d88ca8202397affdab5554dfa6ee03098447b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WWHFTDWXUPOEMFNJLVV4TVDS3X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Audio Concepts from Counterfactual Natural Language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Ali Vosoughi, Chenliang Xu, Ho-Hsiang Wu, Luca Bondi","submitted_at":"2024-01-10T05:15:09Z","abstract_excerpt":"Conventional audio classification relied on predefined classes, lacking the ability to learn from free-form text. Recent methods unlock learning joint audio-text embeddings from raw audio-text pairs describing audio in natural language. Despite recent advancements, there is little exploration of systematic methods to train models for recognizing sound events and sources in alternative scenarios, such as distinguishing fireworks from gunshots at outdoor events in similar situations. This study introduces causal reasoning and counterfactual analysis in the audio domain. We use counterfactual ins"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.04935","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/2401.04935/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":"2026-07-05T07:32:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KOZE78o8qigYVhiAxnb/yMZzSTx+T7MxNlhYnJdzuzxIscmNJqG3DTlKQKoTODgiQkDUD3aGyveB15Lui8V6BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:12:47.728906Z"},"content_sha256":"049de94b99f7fd893a8a8d769b72472844d2d560c315489019e8259fc14d31ec","schema_version":"1.0","event_id":"sha256:049de94b99f7fd893a8a8d769b72472844d2d560c315489019e8259fc14d31ec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WWHFTDWXUPOEMFNJLVV4TVDS3X/bundle.json","state_url":"https://pith.science/pith/WWHFTDWXUPOEMFNJLVV4TVDS3X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WWHFTDWXUPOEMFNJLVV4TVDS3X/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":"2026-07-07T15:12:47Z","links":{"resolver":"https://pith.science/pith/WWHFTDWXUPOEMFNJLVV4TVDS3X","bundle":"https://pith.science/pith/WWHFTDWXUPOEMFNJLVV4TVDS3X/bundle.json","state":"https://pith.science/pith/WWHFTDWXUPOEMFNJLVV4TVDS3X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WWHFTDWXUPOEMFNJLVV4TVDS3X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WWHFTDWXUPOEMFNJLVV4TVDS3X","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":"a446e4a76aec7cd21f993f3930ff613018a597971bd79bc41fd9fa10a5e97cb2","cross_cats_sorted":["cs.CL","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-01-10T05:15:09Z","title_canon_sha256":"467da2ec32f560ab18e28f77a1334ca4eed625d913ca0bcd001cbbc944247ecb"},"schema_version":"1.0","source":{"id":"2401.04935","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.04935","created_at":"2026-07-05T07:32:00Z"},{"alias_kind":"arxiv_version","alias_value":"2401.04935v1","created_at":"2026-07-05T07:32:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.04935","created_at":"2026-07-05T07:32:00Z"},{"alias_kind":"pith_short_12","alias_value":"WWHFTDWXUPOE","created_at":"2026-07-05T07:32:00Z"},{"alias_kind":"pith_short_16","alias_value":"WWHFTDWXUPOEMFNJ","created_at":"2026-07-05T07:32:00Z"},{"alias_kind":"pith_short_8","alias_value":"WWHFTDWX","created_at":"2026-07-05T07:32:00Z"}],"graph_snapshots":[{"event_id":"sha256:049de94b99f7fd893a8a8d769b72472844d2d560c315489019e8259fc14d31ec","target":"graph","created_at":"2026-07-05T07:32:00Z","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/2401.04935/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Conventional audio classification relied on predefined classes, lacking the ability to learn from free-form text. Recent methods unlock learning joint audio-text embeddings from raw audio-text pairs describing audio in natural language. Despite recent advancements, there is little exploration of systematic methods to train models for recognizing sound events and sources in alternative scenarios, such as distinguishing fireworks from gunshots at outdoor events in similar situations. This study introduces causal reasoning and counterfactual analysis in the audio domain. We use counterfactual ins","authors_text":"Ali Vosoughi, Chenliang Xu, Ho-Hsiang Wu, Luca Bondi","cross_cats":["cs.CL","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-01-10T05:15:09Z","title":"Learning Audio Concepts from Counterfactual Natural Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.04935","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:df4d19cfbcb0a4284792c24eba2d88ca8202397affdab5554dfa6ee03098447b","target":"record","created_at":"2026-07-05T07:32:00Z","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":"a446e4a76aec7cd21f993f3930ff613018a597971bd79bc41fd9fa10a5e97cb2","cross_cats_sorted":["cs.CL","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-01-10T05:15:09Z","title_canon_sha256":"467da2ec32f560ab18e28f77a1334ca4eed625d913ca0bcd001cbbc944247ecb"},"schema_version":"1.0","source":{"id":"2401.04935","kind":"arxiv","version":1}},"canonical_sha256":"b58e598ed7a3dc4615a95d6bc9d472ddf6216d1191834a26c1ca2945183bb752","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b58e598ed7a3dc4615a95d6bc9d472ddf6216d1191834a26c1ca2945183bb752","first_computed_at":"2026-07-05T07:32:00.712342Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:32:00.712342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OQFh1/hPk2VED6ZIMP8ujvRTfacP1flxMaSE8XIDfqlFkaJy+a4fAxg+SihIVKpTbDMOiSWqtDMwoQzthuJeCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:32:00.712847Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.04935","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df4d19cfbcb0a4284792c24eba2d88ca8202397affdab5554dfa6ee03098447b","sha256:049de94b99f7fd893a8a8d769b72472844d2d560c315489019e8259fc14d31ec"],"state_sha256":"c54849a330bc66fb2e10b5ca98d5fb185f06e8f396c29029282731dc576eba86"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XqhHMEMtWywYJ0CbsfidoTRAjhhkYcaQMYOl0y3rXHU0VxYy5oejqsOgv8c5aU/VA+Xa3uk2bUBTs/eNhrotDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T15:12:47.730865Z","bundle_sha256":"d77f8ebf48b579099d82f0bb38bf4c63ca39fa85701cac8a88e1ad963958f2e6"}}