{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HRY57KKZRTCXEPC47IBUSJOBPK","short_pith_number":"pith:HRY57KKZ","canonical_record":{"source":{"id":"2403.04594","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-03-07T15:40:01Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"36abefd9eeb7206ae454d58f8b9ae079ec4c9c08fc9260025d7a0ca21c883884","abstract_canon_sha256":"aa6aa978fedf11879357ca05745fd5f80710cf449833d98b0ffa96340e03a5fd"},"schema_version":"1.0"},"canonical_sha256":"3c71dfa9598cc5723c5cfa034925c17a94308bf734dbaca92219644275176c9b","source":{"kind":"arxiv","id":"2403.04594","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.04594","created_at":"2026-07-05T07:53:25Z"},{"alias_kind":"arxiv_version","alias_value":"2403.04594v1","created_at":"2026-07-05T07:53:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.04594","created_at":"2026-07-05T07:53:25Z"},{"alias_kind":"pith_short_12","alias_value":"HRY57KKZRTCX","created_at":"2026-07-05T07:53:25Z"},{"alias_kind":"pith_short_16","alias_value":"HRY57KKZRTCXEPC4","created_at":"2026-07-05T07:53:25Z"},{"alias_kind":"pith_short_8","alias_value":"HRY57KKZ","created_at":"2026-07-05T07:53:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HRY57KKZRTCXEPC47IBUSJOBPK","target":"record","payload":{"canonical_record":{"source":{"id":"2403.04594","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-03-07T15:40:01Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"36abefd9eeb7206ae454d58f8b9ae079ec4c9c08fc9260025d7a0ca21c883884","abstract_canon_sha256":"aa6aa978fedf11879357ca05745fd5f80710cf449833d98b0ffa96340e03a5fd"},"schema_version":"1.0"},"canonical_sha256":"3c71dfa9598cc5723c5cfa034925c17a94308bf734dbaca92219644275176c9b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:53:25.679357Z","signature_b64":"QrusDaICDkKFPlbq+bYNTPkmEmaKfWW1hnne47sk2bYMoIuP4PkZEm8KS13tZFbRdgiTKLsaZq8Lgg1miMvzDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c71dfa9598cc5723c5cfa034925c17a94308bf734dbaca92219644275176c9b","last_reissued_at":"2026-07-05T07:53:25.678837Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:53:25.678837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.04594","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":"2026-07-05T07:53:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CBAapEtQeEk87SFFlpww8jYSJc1HE9/pih9aciQzVCqNDsN1FncPHZkDiGTvkXLO+9SVnak7mX/aLji6iTxtBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T20:31:44.886849Z"},"content_sha256":"3ae0e8a3bd9e000b2bdd3581676c19be823b82d7729ab18eff1c8ce19bd917c4","schema_version":"1.0","event_id":"sha256:3ae0e8a3bd9e000b2bdd3581676c19be823b82d7729ab18eff1c8ce19bd917c4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HRY57KKZRTCXEPC47IBUSJOBPK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Detailed Audio-Text Data Simulation Pipeline using Single-Event Sounds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Kai Yu, Mengyue Wu, Pingyue Zhang, Xiaohang Xu, Xuenan Xu, Zeyu Xie","submitted_at":"2024-03-07T15:40:01Z","abstract_excerpt":"Recently, there has been an increasing focus on audio-text cross-modal learning. However, most of the existing audio-text datasets contain only simple descriptions of sound events. Compared with classification labels, the advantages of such descriptions are significantly limited. In this paper, we first analyze the detailed information that human descriptions of audio may contain beyond sound event labels. Based on the analysis, we propose an automatic pipeline for curating audio-text pairs with rich details. Leveraging the property that sounds can be mixed and concatenated in the time domain,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.04594","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/2403.04594/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":"2026-07-05T07:53:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"swfrahPgHq1t8G+2YKQWqRnNnYM5Z6rkEbPSbHeKZK0iuSHKoqm82A6yjwi+E9uSfLupDSKYsUrS2uZbqWN+BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T20:31:44.887202Z"},"content_sha256":"ed6c0a402233f4f1f05cba6894439a65cfb12df33bbc736b5cf9ea0332335b74","schema_version":"1.0","event_id":"sha256:ed6c0a402233f4f1f05cba6894439a65cfb12df33bbc736b5cf9ea0332335b74"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HRY57KKZRTCXEPC47IBUSJOBPK/bundle.json","state_url":"https://pith.science/pith/HRY57KKZRTCXEPC47IBUSJOBPK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HRY57KKZRTCXEPC47IBUSJOBPK/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":"2026-07-18T20:31:44Z","links":{"resolver":"https://pith.science/pith/HRY57KKZRTCXEPC47IBUSJOBPK","bundle":"https://pith.science/pith/HRY57KKZRTCXEPC47IBUSJOBPK/bundle.json","state":"https://pith.science/pith/HRY57KKZRTCXEPC47IBUSJOBPK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HRY57KKZRTCXEPC47IBUSJOBPK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HRY57KKZRTCXEPC47IBUSJOBPK","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":"aa6aa978fedf11879357ca05745fd5f80710cf449833d98b0ffa96340e03a5fd","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-03-07T15:40:01Z","title_canon_sha256":"36abefd9eeb7206ae454d58f8b9ae079ec4c9c08fc9260025d7a0ca21c883884"},"schema_version":"1.0","source":{"id":"2403.04594","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.04594","created_at":"2026-07-05T07:53:25Z"},{"alias_kind":"arxiv_version","alias_value":"2403.04594v1","created_at":"2026-07-05T07:53:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.04594","created_at":"2026-07-05T07:53:25Z"},{"alias_kind":"pith_short_12","alias_value":"HRY57KKZRTCX","created_at":"2026-07-05T07:53:25Z"},{"alias_kind":"pith_short_16","alias_value":"HRY57KKZRTCXEPC4","created_at":"2026-07-05T07:53:25Z"},{"alias_kind":"pith_short_8","alias_value":"HRY57KKZ","created_at":"2026-07-05T07:53:25Z"}],"graph_snapshots":[{"event_id":"sha256:ed6c0a402233f4f1f05cba6894439a65cfb12df33bbc736b5cf9ea0332335b74","target":"graph","created_at":"2026-07-05T07:53:25Z","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/2403.04594/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, there has been an increasing focus on audio-text cross-modal learning. However, most of the existing audio-text datasets contain only simple descriptions of sound events. Compared with classification labels, the advantages of such descriptions are significantly limited. In this paper, we first analyze the detailed information that human descriptions of audio may contain beyond sound event labels. Based on the analysis, we propose an automatic pipeline for curating audio-text pairs with rich details. Leveraging the property that sounds can be mixed and concatenated in the time domain,","authors_text":"Kai Yu, Mengyue Wu, Pingyue Zhang, Xiaohang Xu, Xuenan Xu, Zeyu Xie","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-03-07T15:40:01Z","title":"A Detailed Audio-Text Data Simulation Pipeline using Single-Event Sounds"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.04594","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":"sha256:3ae0e8a3bd9e000b2bdd3581676c19be823b82d7729ab18eff1c8ce19bd917c4","target":"record","created_at":"2026-07-05T07:53:25Z","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":"aa6aa978fedf11879357ca05745fd5f80710cf449833d98b0ffa96340e03a5fd","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-03-07T15:40:01Z","title_canon_sha256":"36abefd9eeb7206ae454d58f8b9ae079ec4c9c08fc9260025d7a0ca21c883884"},"schema_version":"1.0","source":{"id":"2403.04594","kind":"arxiv","version":1}},"canonical_sha256":"3c71dfa9598cc5723c5cfa034925c17a94308bf734dbaca92219644275176c9b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3c71dfa9598cc5723c5cfa034925c17a94308bf734dbaca92219644275176c9b","first_computed_at":"2026-07-05T07:53:25.678837Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:53:25.678837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QrusDaICDkKFPlbq+bYNTPkmEmaKfWW1hnne47sk2bYMoIuP4PkZEm8KS13tZFbRdgiTKLsaZq8Lgg1miMvzDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:53:25.679357Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.04594","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ae0e8a3bd9e000b2bdd3581676c19be823b82d7729ab18eff1c8ce19bd917c4","sha256:ed6c0a402233f4f1f05cba6894439a65cfb12df33bbc736b5cf9ea0332335b74"],"state_sha256":"c9d8b478b34a1203bd17ef23126f2cbfc92fe069075d33cc5fa35321cffc8eea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yr7jyhZpZpBcVpOepbWpmmwNTQ/eLtwbHPqqUBEuRFBM+LETu3rV7pa88g3YvLvta8cU3R8cME2jxsokxoLQBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-18T20:31:44.889758Z","bundle_sha256":"4f9cd410769460627e2db753f8e374f74e20de215997988295a2895096d326f6"}}