{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:E6ERBT23RQQDLTPZMNLAYL6FMW","short_pith_number":"pith:E6ERBT23","canonical_record":{"source":{"id":"2303.17395","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2023-03-30T14:07:47Z","cross_cats_sorted":["cs.CL","cs.MM","cs.SD"],"title_canon_sha256":"40d166df9667c68feccb45f5a09c01d54f31a94c9e551eea1478af068b9c4dba","abstract_canon_sha256":"1f723ec8210909aabf5b7303cc9f34291d2b362906f1a967d9794fda214fadb0"},"schema_version":"1.0"},"canonical_sha256":"278910cf5b8c2035cdf963560c2fc565afa48ec9bd5b8b45ae60749f59ce3c8b","source":{"kind":"arxiv","id":"2303.17395","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.17395","created_at":"2026-07-05T08:45:45Z"},{"alias_kind":"arxiv_version","alias_value":"2303.17395v2","created_at":"2026-07-05T08:45:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.17395","created_at":"2026-07-05T08:45:45Z"},{"alias_kind":"pith_short_12","alias_value":"E6ERBT23RQQD","created_at":"2026-07-05T08:45:45Z"},{"alias_kind":"pith_short_16","alias_value":"E6ERBT23RQQDLTPZ","created_at":"2026-07-05T08:45:45Z"},{"alias_kind":"pith_short_8","alias_value":"E6ERBT23","created_at":"2026-07-05T08:45:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:E6ERBT23RQQDLTPZMNLAYL6FMW","target":"record","payload":{"canonical_record":{"source":{"id":"2303.17395","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2023-03-30T14:07:47Z","cross_cats_sorted":["cs.CL","cs.MM","cs.SD"],"title_canon_sha256":"40d166df9667c68feccb45f5a09c01d54f31a94c9e551eea1478af068b9c4dba","abstract_canon_sha256":"1f723ec8210909aabf5b7303cc9f34291d2b362906f1a967d9794fda214fadb0"},"schema_version":"1.0"},"canonical_sha256":"278910cf5b8c2035cdf963560c2fc565afa48ec9bd5b8b45ae60749f59ce3c8b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:45.651601Z","signature_b64":"FEmEZZGC4LNBZOoePcaAeFbbiHf7PIgeMdu4f/M8TXdPWfSWWuHpBy6jMerCir5XmJixLUOp5zksgWLz1cs6Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"278910cf5b8c2035cdf963560c2fc565afa48ec9bd5b8b45ae60749f59ce3c8b","last_reissued_at":"2026-07-05T08:45:45.651152Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:45.651152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.17395","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":"2026-07-05T08:45:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NIhFBHjaMA8Epf3kAVURKx9rA7S+uFo9GMJVLQfoL294X5LSxeVLgOlNgJW0KpxXR0MORS9bFLO/0miRJtHEBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T05:10:50.441120Z"},"content_sha256":"225af21cc3e44abbda584cef906a4d0cd19d98abd17488649c3c911e91d21c2e","schema_version":"1.0","event_id":"sha256:225af21cc3e44abbda584cef906a4d0cd19d98abd17488649c3c911e91d21c2e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:E6ERBT23RQQDLTPZMNLAYL6FMW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.MM","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chengqi Zhao, Chutong Meng, Haohe Liu, Mark D. Plumbley, Qiuqiang Kong, Tom Ko, Wenwu Wang, Xinhao Mei, Yuexian Zou","submitted_at":"2023-03-30T14:07:47Z","abstract_excerpt":"The advancement of audio-language (AL) multimodal learning tasks has been significant in recent years. However, researchers face challenges due to the costly and time-consuming collection process of existing audio-language datasets, which are limited in size. To address this data scarcity issue, we introduce WavCaps, the first large-scale weakly-labelled audio captioning dataset, comprising approximately 400k audio clips with paired captions. We sourced audio clips and their raw descriptions from web sources and a sound event detection dataset. However, the online-harvested raw descriptions ar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.17395","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/2303.17395/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":"2026-07-05T08:45:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"685uUzU/pa6OkIq+UQ5bdr9YP14PtK+wLkuZzL/UDPcmpHjUPCoG7ok1uBij5EX2OZYhYJ9dzalCjfGjDq8lCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T05:10:50.441657Z"},"content_sha256":"eac79eb92828e4d53f3741803f934a42bf7488f6a242844eca5c7a98bf06350d","schema_version":"1.0","event_id":"sha256:eac79eb92828e4d53f3741803f934a42bf7488f6a242844eca5c7a98bf06350d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E6ERBT23RQQDLTPZMNLAYL6FMW/bundle.json","state_url":"https://pith.science/pith/E6ERBT23RQQDLTPZMNLAYL6FMW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E6ERBT23RQQDLTPZMNLAYL6FMW/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":"2026-08-07T05:10:50Z","links":{"resolver":"https://pith.science/pith/E6ERBT23RQQDLTPZMNLAYL6FMW","bundle":"https://pith.science/pith/E6ERBT23RQQDLTPZMNLAYL6FMW/bundle.json","state":"https://pith.science/pith/E6ERBT23RQQDLTPZMNLAYL6FMW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E6ERBT23RQQDLTPZMNLAYL6FMW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:E6ERBT23RQQDLTPZMNLAYL6FMW","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":"1f723ec8210909aabf5b7303cc9f34291d2b362906f1a967d9794fda214fadb0","cross_cats_sorted":["cs.CL","cs.MM","cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2023-03-30T14:07:47Z","title_canon_sha256":"40d166df9667c68feccb45f5a09c01d54f31a94c9e551eea1478af068b9c4dba"},"schema_version":"1.0","source":{"id":"2303.17395","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.17395","created_at":"2026-07-05T08:45:45Z"},{"alias_kind":"arxiv_version","alias_value":"2303.17395v2","created_at":"2026-07-05T08:45:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.17395","created_at":"2026-07-05T08:45:45Z"},{"alias_kind":"pith_short_12","alias_value":"E6ERBT23RQQD","created_at":"2026-07-05T08:45:45Z"},{"alias_kind":"pith_short_16","alias_value":"E6ERBT23RQQDLTPZ","created_at":"2026-07-05T08:45:45Z"},{"alias_kind":"pith_short_8","alias_value":"E6ERBT23","created_at":"2026-07-05T08:45:45Z"}],"graph_snapshots":[{"event_id":"sha256:eac79eb92828e4d53f3741803f934a42bf7488f6a242844eca5c7a98bf06350d","target":"graph","created_at":"2026-07-05T08:45:45Z","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/2303.17395/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The advancement of audio-language (AL) multimodal learning tasks has been significant in recent years. However, researchers face challenges due to the costly and time-consuming collection process of existing audio-language datasets, which are limited in size. To address this data scarcity issue, we introduce WavCaps, the first large-scale weakly-labelled audio captioning dataset, comprising approximately 400k audio clips with paired captions. We sourced audio clips and their raw descriptions from web sources and a sound event detection dataset. However, the online-harvested raw descriptions ar","authors_text":"Chengqi Zhao, Chutong Meng, Haohe Liu, Mark D. Plumbley, Qiuqiang Kong, Tom Ko, Wenwu Wang, Xinhao Mei, Yuexian Zou","cross_cats":["cs.CL","cs.MM","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2023-03-30T14:07:47Z","title":"WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.17395","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":"sha256:225af21cc3e44abbda584cef906a4d0cd19d98abd17488649c3c911e91d21c2e","target":"record","created_at":"2026-07-05T08:45:45Z","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":"1f723ec8210909aabf5b7303cc9f34291d2b362906f1a967d9794fda214fadb0","cross_cats_sorted":["cs.CL","cs.MM","cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2023-03-30T14:07:47Z","title_canon_sha256":"40d166df9667c68feccb45f5a09c01d54f31a94c9e551eea1478af068b9c4dba"},"schema_version":"1.0","source":{"id":"2303.17395","kind":"arxiv","version":2}},"canonical_sha256":"278910cf5b8c2035cdf963560c2fc565afa48ec9bd5b8b45ae60749f59ce3c8b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"278910cf5b8c2035cdf963560c2fc565afa48ec9bd5b8b45ae60749f59ce3c8b","first_computed_at":"2026-07-05T08:45:45.651152Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:45.651152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FEmEZZGC4LNBZOoePcaAeFbbiHf7PIgeMdu4f/M8TXdPWfSWWuHpBy6jMerCir5XmJixLUOp5zksgWLz1cs6Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:45.651601Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.17395","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:225af21cc3e44abbda584cef906a4d0cd19d98abd17488649c3c911e91d21c2e","sha256:eac79eb92828e4d53f3741803f934a42bf7488f6a242844eca5c7a98bf06350d"],"state_sha256":"358d11a927391f47467fd1cc87672b14e9a463af72b5510564f672999abcf3f6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DcNDRzCaX0x0TbpoYNvkkSgn3ymQwOaQlUd63B3QjKRw9GSEhjJSLBTQrcAmJ8cLCh/yjWF8z/8M7Br3re/nDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T05:10:50.446540Z","bundle_sha256":"5cada5179a9573cab78f0016222870901b991621ddce18dee5b36477040c003e"}}