{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:RBP7KLT2WVV45J4EMZSSASLOID","short_pith_number":"pith:RBP7KLT2","canonical_record":{"source":{"id":"2303.07902","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-03-14T13:42:26Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"ab98a6d023eff6429f60f1c2f289e8ebb7b98214716fcc0f3b65f2bea7c70631","abstract_canon_sha256":"0b633d7508f233c8347cd7c679dd2d1c4a97a50b2867350b7ef096e9c6f2b91d"},"schema_version":"1.0"},"canonical_sha256":"885ff52e7ab56bcea784666520496e40f4c4d223edd935dacde331b9eb0774bc","source":{"kind":"arxiv","id":"2303.07902","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.07902","created_at":"2026-07-05T07:52:08Z"},{"alias_kind":"arxiv_version","alias_value":"2303.07902v2","created_at":"2026-07-05T07:52:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.07902","created_at":"2026-07-05T07:52:08Z"},{"alias_kind":"pith_short_12","alias_value":"RBP7KLT2WVV4","created_at":"2026-07-05T07:52:08Z"},{"alias_kind":"pith_short_16","alias_value":"RBP7KLT2WVV45J4E","created_at":"2026-07-05T07:52:08Z"},{"alias_kind":"pith_short_8","alias_value":"RBP7KLT2","created_at":"2026-07-05T07:52:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:RBP7KLT2WVV45J4EMZSSASLOID","target":"record","payload":{"canonical_record":{"source":{"id":"2303.07902","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-03-14T13:42:26Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"ab98a6d023eff6429f60f1c2f289e8ebb7b98214716fcc0f3b65f2bea7c70631","abstract_canon_sha256":"0b633d7508f233c8347cd7c679dd2d1c4a97a50b2867350b7ef096e9c6f2b91d"},"schema_version":"1.0"},"canonical_sha256":"885ff52e7ab56bcea784666520496e40f4c4d223edd935dacde331b9eb0774bc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:52:08.801495Z","signature_b64":"xgMqOpWGQ8t5KSzlLMECQtiVHsI8hoiv9DHlnCYcOnoZ3RGCpjA4nNVa93ULG3G2OC4aqJaqV4YI4SpUut1rBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"885ff52e7ab56bcea784666520496e40f4c4d223edd935dacde331b9eb0774bc","last_reissued_at":"2026-07-05T07:52:08.800985Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:52:08.800985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.07902","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":"2026-07-05T07:52:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Iwp434gYMgtbVFuXU35kcuIGUdgElM7tsd5F4zLYaF7AHqhWzm4h6PPCp36CfdsQkG4BvPbvAB5U/v31NeFsCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T07:23:39.875294Z"},"content_sha256":"d15b10a830890b2ff1650a54346cade8be7d5568c26a1bde7572dc752baa2a87","schema_version":"1.0","event_id":"sha256:d15b10a830890b2ff1650a54346cade8be7d5568c26a1bde7572dc752baa2a87"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:RBP7KLT2WVV45J4EMZSSASLOID","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BLAT: Bootstrapping Language-Audio Pre-training based on AudioSet Tag-guided Synthetic Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Kenny Q. Zhu, Mengyue Wu, Pingyue Zhang, Xuenan Xu, Zelin Zhou, Zeyu Xie, Zhiling Zhang","submitted_at":"2023-03-14T13:42:26Z","abstract_excerpt":"Compared with ample visual-text pre-training research, few works explore audio-text pre-training, mostly due to the lack of sufficient parallel audio-text data. Most existing methods incorporate the visual modality as a pivot for audio-text pre-training, which inevitably induces data noise. In this paper, we propose to utilize audio captioning to generate text directly from audio, without the aid of the visual modality so that potential noise from modality mismatch is eliminated. Furthermore, we propose caption generation under the guidance of AudioSet tags, leading to more accurate captions. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.07902","kind":"arxiv","version":2},"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/2303.07902/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":"2026-07-05T07:52:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ChgXwDdFQPqm4m26NNSZ10R7C/PAu97NpCpRaVVpLdeXKJmQ+0Tt4XgApSmYsJOxqfBOjD9OGzDDhfxjgKriCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T07:23:39.875679Z"},"content_sha256":"005c5a4a91adbbfdef372eac2836519350fffa87fd13463da8f7616504d9e80b","schema_version":"1.0","event_id":"sha256:005c5a4a91adbbfdef372eac2836519350fffa87fd13463da8f7616504d9e80b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RBP7KLT2WVV45J4EMZSSASLOID/bundle.json","state_url":"https://pith.science/pith/RBP7KLT2WVV45J4EMZSSASLOID/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RBP7KLT2WVV45J4EMZSSASLOID/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":"2026-07-10T07:23:39Z","links":{"resolver":"https://pith.science/pith/RBP7KLT2WVV45J4EMZSSASLOID","bundle":"https://pith.science/pith/RBP7KLT2WVV45J4EMZSSASLOID/bundle.json","state":"https://pith.science/pith/RBP7KLT2WVV45J4EMZSSASLOID/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RBP7KLT2WVV45J4EMZSSASLOID/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RBP7KLT2WVV45J4EMZSSASLOID","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":"0b633d7508f233c8347cd7c679dd2d1c4a97a50b2867350b7ef096e9c6f2b91d","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-03-14T13:42:26Z","title_canon_sha256":"ab98a6d023eff6429f60f1c2f289e8ebb7b98214716fcc0f3b65f2bea7c70631"},"schema_version":"1.0","source":{"id":"2303.07902","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.07902","created_at":"2026-07-05T07:52:08Z"},{"alias_kind":"arxiv_version","alias_value":"2303.07902v2","created_at":"2026-07-05T07:52:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.07902","created_at":"2026-07-05T07:52:08Z"},{"alias_kind":"pith_short_12","alias_value":"RBP7KLT2WVV4","created_at":"2026-07-05T07:52:08Z"},{"alias_kind":"pith_short_16","alias_value":"RBP7KLT2WVV45J4E","created_at":"2026-07-05T07:52:08Z"},{"alias_kind":"pith_short_8","alias_value":"RBP7KLT2","created_at":"2026-07-05T07:52:08Z"}],"graph_snapshots":[{"event_id":"sha256:005c5a4a91adbbfdef372eac2836519350fffa87fd13463da8f7616504d9e80b","target":"graph","created_at":"2026-07-05T07:52:08Z","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/2303.07902/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Compared with ample visual-text pre-training research, few works explore audio-text pre-training, mostly due to the lack of sufficient parallel audio-text data. Most existing methods incorporate the visual modality as a pivot for audio-text pre-training, which inevitably induces data noise. In this paper, we propose to utilize audio captioning to generate text directly from audio, without the aid of the visual modality so that potential noise from modality mismatch is eliminated. Furthermore, we propose caption generation under the guidance of AudioSet tags, leading to more accurate captions. ","authors_text":"Kenny Q. Zhu, Mengyue Wu, Pingyue Zhang, Xuenan Xu, Zelin Zhou, Zeyu Xie, Zhiling Zhang","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-03-14T13:42:26Z","title":"BLAT: Bootstrapping Language-Audio Pre-training based on AudioSet Tag-guided Synthetic Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.07902","kind":"arxiv","version":2},"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:d15b10a830890b2ff1650a54346cade8be7d5568c26a1bde7572dc752baa2a87","target":"record","created_at":"2026-07-05T07:52:08Z","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":"0b633d7508f233c8347cd7c679dd2d1c4a97a50b2867350b7ef096e9c6f2b91d","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-03-14T13:42:26Z","title_canon_sha256":"ab98a6d023eff6429f60f1c2f289e8ebb7b98214716fcc0f3b65f2bea7c70631"},"schema_version":"1.0","source":{"id":"2303.07902","kind":"arxiv","version":2}},"canonical_sha256":"885ff52e7ab56bcea784666520496e40f4c4d223edd935dacde331b9eb0774bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"885ff52e7ab56bcea784666520496e40f4c4d223edd935dacde331b9eb0774bc","first_computed_at":"2026-07-05T07:52:08.800985Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:52:08.800985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xgMqOpWGQ8t5KSzlLMECQtiVHsI8hoiv9DHlnCYcOnoZ3RGCpjA4nNVa93ULG3G2OC4aqJaqV4YI4SpUut1rBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:52:08.801495Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.07902","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d15b10a830890b2ff1650a54346cade8be7d5568c26a1bde7572dc752baa2a87","sha256:005c5a4a91adbbfdef372eac2836519350fffa87fd13463da8f7616504d9e80b"],"state_sha256":"9bc2b6026b834e0c3f0252dbea6aab06a1a15e93034fb94333525465224654c8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"np/EV+lu3tuzdAjf18vtjmVBHzUropWE28kU/J6RtT367G6dIvCRwNwpCc/rxRLWdlI+R1Wer7c7OgyjxpHCCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T07:23:39.877613Z","bundle_sha256":"fee10693e7800be24afe4725fa79c114ae9781d419ea3efa9b067f78dab33c8e"}}