{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HKLIZNIZVLCRDHSQ6GBUNUCD4X","short_pith_number":"pith:HKLIZNIZ","canonical_record":{"source":{"id":"2410.17589","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-23T06:35:41Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM","eess.AS"],"title_canon_sha256":"78965f5c33570f779de74565ebcbebf2163271d2bc60c037b9a63f34f8f3d1d9","abstract_canon_sha256":"be3e023f5f8c25143483794d4e8bd395467b0d62ad81148b4b3273fb6d9ee631"},"schema_version":"1.0"},"canonical_sha256":"3a968cb519aac5119e50f18346d043e5d1f220656abaaef23678099866aada48","source":{"kind":"arxiv","id":"2410.17589","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.17589","created_at":"2026-07-05T09:24:41Z"},{"alias_kind":"arxiv_version","alias_value":"2410.17589v1","created_at":"2026-07-05T09:24:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17589","created_at":"2026-07-05T09:24:41Z"},{"alias_kind":"pith_short_12","alias_value":"HKLIZNIZVLCR","created_at":"2026-07-05T09:24:41Z"},{"alias_kind":"pith_short_16","alias_value":"HKLIZNIZVLCRDHSQ","created_at":"2026-07-05T09:24:41Z"},{"alias_kind":"pith_short_8","alias_value":"HKLIZNIZ","created_at":"2026-07-05T09:24:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HKLIZNIZVLCRDHSQ6GBUNUCD4X","target":"record","payload":{"canonical_record":{"source":{"id":"2410.17589","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-23T06:35:41Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM","eess.AS"],"title_canon_sha256":"78965f5c33570f779de74565ebcbebf2163271d2bc60c037b9a63f34f8f3d1d9","abstract_canon_sha256":"be3e023f5f8c25143483794d4e8bd395467b0d62ad81148b4b3273fb6d9ee631"},"schema_version":"1.0"},"canonical_sha256":"3a968cb519aac5119e50f18346d043e5d1f220656abaaef23678099866aada48","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:41.001293Z","signature_b64":"W1O2spMw48Aohk8zFrvykysL9FyCiZ7z/teWBbn3KyeovXxL9w2MGZCSgouzROOQpl1vv/a8VIVeLCF2yYCqAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a968cb519aac5119e50f18346d043e5d1f220656abaaef23678099866aada48","last_reissued_at":"2026-07-05T09:24:41.000716Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:41.000716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.17589","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":"2026-07-05T09:24:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NrRSVZa+qZoKhsjdbaUL70TKkfQF7sV1PMFVPRPMVU6vg1HK7iYPQYrXP5dkgJrVeMzQ/gYlu6jT6j/X8Mx1DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T15:56:01.804758Z"},"content_sha256":"1d125ee2e063a5c1f7a16ad7d23cc2df86d552cdcaca4f1769160d4884ef67d8","schema_version":"1.0","event_id":"sha256:1d125ee2e063a5c1f7a16ad7d23cc2df86d552cdcaca4f1769160d4884ef67d8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HKLIZNIZVLCRDHSQ6GBUNUCD4X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Challenge on Sound Scene Synthesis: Evaluating Text-to-Audio Generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Brian McFee, Junwon Lee, Keisuke Imoto, Keunwoo Choi, Laurie M. Heller, Mathieu Lagrange, Modan Tailleur, Yuki Okamoto","submitted_at":"2024-10-23T06:35:41Z","abstract_excerpt":"Despite significant advancements in neural text-to-audio generation, challenges persist in controllability and evaluation. This paper addresses these issues through the Sound Scene Synthesis challenge held as part of the Detection and Classification of Acoustic Scenes and Events 2024. We present an evaluation protocol combining objective metric, namely Fr\\'echet Audio Distance, with perceptual assessments, utilizing a structured prompt format to enable diverse captions and effective evaluation. Our analysis reveals varying performance across sound categories and model architectures, with large"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.17589","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/2410.17589/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":"2026-07-05T09:24:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Aorl/3IXZU2XnucDwAOmMcpdUA795y4hoswqlx5PIZgLhV8bVai7vyO4/HBCUaAGKp/zNZsdEqXR8hsv9csCAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T15:56:01.805713Z"},"content_sha256":"09f59d4c6ff019d3b3a9981ba7c87851507d50d83f24beff72acb665e4c65e89","schema_version":"1.0","event_id":"sha256:09f59d4c6ff019d3b3a9981ba7c87851507d50d83f24beff72acb665e4c65e89"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HKLIZNIZVLCRDHSQ6GBUNUCD4X/bundle.json","state_url":"https://pith.science/pith/HKLIZNIZVLCRDHSQ6GBUNUCD4X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HKLIZNIZVLCRDHSQ6GBUNUCD4X/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":"2026-08-23T15:56:01Z","links":{"resolver":"https://pith.science/pith/HKLIZNIZVLCRDHSQ6GBUNUCD4X","bundle":"https://pith.science/pith/HKLIZNIZVLCRDHSQ6GBUNUCD4X/bundle.json","state":"https://pith.science/pith/HKLIZNIZVLCRDHSQ6GBUNUCD4X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HKLIZNIZVLCRDHSQ6GBUNUCD4X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HKLIZNIZVLCRDHSQ6GBUNUCD4X","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":"be3e023f5f8c25143483794d4e8bd395467b0d62ad81148b4b3273fb6d9ee631","cross_cats_sorted":["cs.AI","cs.LG","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-23T06:35:41Z","title_canon_sha256":"78965f5c33570f779de74565ebcbebf2163271d2bc60c037b9a63f34f8f3d1d9"},"schema_version":"1.0","source":{"id":"2410.17589","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.17589","created_at":"2026-07-05T09:24:41Z"},{"alias_kind":"arxiv_version","alias_value":"2410.17589v1","created_at":"2026-07-05T09:24:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17589","created_at":"2026-07-05T09:24:41Z"},{"alias_kind":"pith_short_12","alias_value":"HKLIZNIZVLCR","created_at":"2026-07-05T09:24:41Z"},{"alias_kind":"pith_short_16","alias_value":"HKLIZNIZVLCRDHSQ","created_at":"2026-07-05T09:24:41Z"},{"alias_kind":"pith_short_8","alias_value":"HKLIZNIZ","created_at":"2026-07-05T09:24:41Z"}],"graph_snapshots":[{"event_id":"sha256:09f59d4c6ff019d3b3a9981ba7c87851507d50d83f24beff72acb665e4c65e89","target":"graph","created_at":"2026-07-05T09:24:41Z","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/2410.17589/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite significant advancements in neural text-to-audio generation, challenges persist in controllability and evaluation. This paper addresses these issues through the Sound Scene Synthesis challenge held as part of the Detection and Classification of Acoustic Scenes and Events 2024. We present an evaluation protocol combining objective metric, namely Fr\\'echet Audio Distance, with perceptual assessments, utilizing a structured prompt format to enable diverse captions and effective evaluation. Our analysis reveals varying performance across sound categories and model architectures, with large","authors_text":"Brian McFee, Junwon Lee, Keisuke Imoto, Keunwoo Choi, Laurie M. Heller, Mathieu Lagrange, Modan Tailleur, Yuki Okamoto","cross_cats":["cs.AI","cs.LG","cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-23T06:35:41Z","title":"Challenge on Sound Scene Synthesis: Evaluating Text-to-Audio Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.17589","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":"sha256:1d125ee2e063a5c1f7a16ad7d23cc2df86d552cdcaca4f1769160d4884ef67d8","target":"record","created_at":"2026-07-05T09:24:41Z","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":"be3e023f5f8c25143483794d4e8bd395467b0d62ad81148b4b3273fb6d9ee631","cross_cats_sorted":["cs.AI","cs.LG","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-23T06:35:41Z","title_canon_sha256":"78965f5c33570f779de74565ebcbebf2163271d2bc60c037b9a63f34f8f3d1d9"},"schema_version":"1.0","source":{"id":"2410.17589","kind":"arxiv","version":1}},"canonical_sha256":"3a968cb519aac5119e50f18346d043e5d1f220656abaaef23678099866aada48","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a968cb519aac5119e50f18346d043e5d1f220656abaaef23678099866aada48","first_computed_at":"2026-07-05T09:24:41.000716Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:24:41.000716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W1O2spMw48Aohk8zFrvykysL9FyCiZ7z/teWBbn3KyeovXxL9w2MGZCSgouzROOQpl1vv/a8VIVeLCF2yYCqAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:24:41.001293Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.17589","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d125ee2e063a5c1f7a16ad7d23cc2df86d552cdcaca4f1769160d4884ef67d8","sha256:09f59d4c6ff019d3b3a9981ba7c87851507d50d83f24beff72acb665e4c65e89"],"state_sha256":"aea157dac433c7ff2f9708ce8d8b588c7f8be1c400c20884767943ecca2664ec"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VXc/bOO0XMv1Pyit4ZxG/bU7aXBswTfvkQB5hO1yMXGc/bZ9M9v5uCFEiQF78bzn0O/Y2avdICJFuO8dYWeUCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T15:56:01.812198Z","bundle_sha256":"227837bb5c08b842b2630d5e38967d570c3cd19468cd25c86d05938ad2860534"}}