{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FQNUZRRNYLFP5P5ZUYGK6VH62L","short_pith_number":"pith:FQNUZRRN","canonical_record":{"source":{"id":"2411.18953","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-11-28T06:50:13Z","cross_cats_sorted":[],"title_canon_sha256":"59b5f3bd908a6eb91e50e8c3d371d4443bb1ebf59b6d0eeb23109af781c6268c","abstract_canon_sha256":"67ed19cbc586d2ad89cd8df238092a61a95cc223054c245b7fe78f7555fb81a9"},"schema_version":"1.0"},"canonical_sha256":"2c1b4cc62dc2cafebfb9a60caf54fed2e7b966615fd777d07dcfc9435171da2b","source":{"kind":"arxiv","id":"2411.18953","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.18953","created_at":"2026-07-05T09:41:54Z"},{"alias_kind":"arxiv_version","alias_value":"2411.18953v1","created_at":"2026-07-05T09:41:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18953","created_at":"2026-07-05T09:41:54Z"},{"alias_kind":"pith_short_12","alias_value":"FQNUZRRNYLFP","created_at":"2026-07-05T09:41:54Z"},{"alias_kind":"pith_short_16","alias_value":"FQNUZRRNYLFP5P5Z","created_at":"2026-07-05T09:41:54Z"},{"alias_kind":"pith_short_8","alias_value":"FQNUZRRN","created_at":"2026-07-05T09:41:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FQNUZRRNYLFP5P5ZUYGK6VH62L","target":"record","payload":{"canonical_record":{"source":{"id":"2411.18953","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-11-28T06:50:13Z","cross_cats_sorted":[],"title_canon_sha256":"59b5f3bd908a6eb91e50e8c3d371d4443bb1ebf59b6d0eeb23109af781c6268c","abstract_canon_sha256":"67ed19cbc586d2ad89cd8df238092a61a95cc223054c245b7fe78f7555fb81a9"},"schema_version":"1.0"},"canonical_sha256":"2c1b4cc62dc2cafebfb9a60caf54fed2e7b966615fd777d07dcfc9435171da2b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:54.567477Z","signature_b64":"Ergd5MlMUUYlCDEgntV9UAoeSDquokmEmsElf64ygkjfLTIja2XBW6KVISOEOB+ZpIiYVZVlZtx+IgT/esFVDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c1b4cc62dc2cafebfb9a60caf54fed2e7b966615fd777d07dcfc9435171da2b","last_reissued_at":"2026-07-05T09:41:54.566963Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:54.566963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.18953","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":"2026-07-05T09:41:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uwOSRWFmCC9hoo4TsQB5WxwiPbJWFJjUZrachHdEE3FvQbNAPvPiyl6kcUOgcMk+ncX+dK0AdaljGTmY8gmaDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T19:59:04.994117Z"},"content_sha256":"836f3a0c93c63ce48237b0cf09cbb694c98fbe6fa0ee751659192d1250f4fc7e","schema_version":"1.0","event_id":"sha256:836f3a0c93c63ce48237b0cf09cbb694c98fbe6fa0ee751659192d1250f4fc7e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FQNUZRRNYLFP5P5ZUYGK6VH62L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AudioSetCaps: An Enriched Audio-Caption Dataset using Automated Generation Pipeline with Large Audio and Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Dongyuan Shi, Haohe Liu, Jianfeng Chen, Jisheng Bai, Mark D. Plumbley, Mou Wang, Wenwu Wang, Woon-Seng Gan","submitted_at":"2024-11-28T06:50:13Z","abstract_excerpt":"With the emergence of audio-language models, constructing large-scale paired audio-language datasets has become essential yet challenging for model development, primarily due to the time-intensive and labour-heavy demands involved. While large language models (LLMs) have improved the efficiency of synthetic audio caption generation, current approaches struggle to effectively extract and incorporate detailed audio information. In this paper, we propose an automated pipeline that integrates audio-language models for fine-grained content extraction, LLMs for synthetic caption generation, and a co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18953","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/2411.18953/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":"2026-07-05T09:41:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jj8N10zm2tYcz+Hn4/fTgooxaEmz44Xw6UcEExyyS2MfBVUGgWvnwl3mSWPiUXpoXwtCzijaGqBJSgJEzSUpDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T19:59:04.994784Z"},"content_sha256":"77a0fee86339a4e3ae5063e06635b0ddf53727b593d3bbfcb86b37498ebd4352","schema_version":"1.0","event_id":"sha256:77a0fee86339a4e3ae5063e06635b0ddf53727b593d3bbfcb86b37498ebd4352"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FQNUZRRNYLFP5P5ZUYGK6VH62L/bundle.json","state_url":"https://pith.science/pith/FQNUZRRNYLFP5P5ZUYGK6VH62L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FQNUZRRNYLFP5P5ZUYGK6VH62L/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":"2026-08-19T19:59:04Z","links":{"resolver":"https://pith.science/pith/FQNUZRRNYLFP5P5ZUYGK6VH62L","bundle":"https://pith.science/pith/FQNUZRRNYLFP5P5ZUYGK6VH62L/bundle.json","state":"https://pith.science/pith/FQNUZRRNYLFP5P5ZUYGK6VH62L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FQNUZRRNYLFP5P5ZUYGK6VH62L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FQNUZRRNYLFP5P5ZUYGK6VH62L","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":"67ed19cbc586d2ad89cd8df238092a61a95cc223054c245b7fe78f7555fb81a9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-11-28T06:50:13Z","title_canon_sha256":"59b5f3bd908a6eb91e50e8c3d371d4443bb1ebf59b6d0eeb23109af781c6268c"},"schema_version":"1.0","source":{"id":"2411.18953","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.18953","created_at":"2026-07-05T09:41:54Z"},{"alias_kind":"arxiv_version","alias_value":"2411.18953v1","created_at":"2026-07-05T09:41:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18953","created_at":"2026-07-05T09:41:54Z"},{"alias_kind":"pith_short_12","alias_value":"FQNUZRRNYLFP","created_at":"2026-07-05T09:41:54Z"},{"alias_kind":"pith_short_16","alias_value":"FQNUZRRNYLFP5P5Z","created_at":"2026-07-05T09:41:54Z"},{"alias_kind":"pith_short_8","alias_value":"FQNUZRRN","created_at":"2026-07-05T09:41:54Z"}],"graph_snapshots":[{"event_id":"sha256:77a0fee86339a4e3ae5063e06635b0ddf53727b593d3bbfcb86b37498ebd4352","target":"graph","created_at":"2026-07-05T09:41:54Z","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/2411.18953/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the emergence of audio-language models, constructing large-scale paired audio-language datasets has become essential yet challenging for model development, primarily due to the time-intensive and labour-heavy demands involved. While large language models (LLMs) have improved the efficiency of synthetic audio caption generation, current approaches struggle to effectively extract and incorporate detailed audio information. In this paper, we propose an automated pipeline that integrates audio-language models for fine-grained content extraction, LLMs for synthetic caption generation, and a co","authors_text":"Dongyuan Shi, Haohe Liu, Jianfeng Chen, Jisheng Bai, Mark D. Plumbley, Mou Wang, Wenwu Wang, Woon-Seng Gan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-11-28T06:50:13Z","title":"AudioSetCaps: An Enriched Audio-Caption Dataset using Automated Generation Pipeline with Large Audio and Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18953","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":"sha256:836f3a0c93c63ce48237b0cf09cbb694c98fbe6fa0ee751659192d1250f4fc7e","target":"record","created_at":"2026-07-05T09:41:54Z","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":"67ed19cbc586d2ad89cd8df238092a61a95cc223054c245b7fe78f7555fb81a9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-11-28T06:50:13Z","title_canon_sha256":"59b5f3bd908a6eb91e50e8c3d371d4443bb1ebf59b6d0eeb23109af781c6268c"},"schema_version":"1.0","source":{"id":"2411.18953","kind":"arxiv","version":1}},"canonical_sha256":"2c1b4cc62dc2cafebfb9a60caf54fed2e7b966615fd777d07dcfc9435171da2b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c1b4cc62dc2cafebfb9a60caf54fed2e7b966615fd777d07dcfc9435171da2b","first_computed_at":"2026-07-05T09:41:54.566963Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:41:54.566963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ergd5MlMUUYlCDEgntV9UAoeSDquokmEmsElf64ygkjfLTIja2XBW6KVISOEOB+ZpIiYVZVlZtx+IgT/esFVDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:41:54.567477Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.18953","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:836f3a0c93c63ce48237b0cf09cbb694c98fbe6fa0ee751659192d1250f4fc7e","sha256:77a0fee86339a4e3ae5063e06635b0ddf53727b593d3bbfcb86b37498ebd4352"],"state_sha256":"2876688393f6bcc9f5a4e55745501eb3495a5825a297965cb23857423e74afa0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rgCccbQDQz47G+Mjp3p0eatMdUNWv2bw0tKCa0j7Ml61Rw5UkjyyiRFBBOOx+yddCSo2zxuzakN55tCQ00cJAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T19:59:05.001889Z","bundle_sha256":"cf43c20fccd58e4c62356e9c9b77f09318a9173b6d91464622e947f487750e43"}}