{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OTBVAD6YJBLZ2NDP7NNLWSIUGL","short_pith_number":"pith:OTBVAD6Y","canonical_record":{"source":{"id":"2504.05702","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-08T05:49:53Z","cross_cats_sorted":[],"title_canon_sha256":"b45a4b2044a844f937d29eac8a325274dfbe0b5d5931b15dbddec549407efdfa","abstract_canon_sha256":"c470102d1452e41b8541b33e9a70c68f2ade1f46d23540efa6a405a302891cba"},"schema_version":"1.0"},"canonical_sha256":"74c3500fd848579d346ffb5abb491432fa6f96cd379a052e69f67ebbf66c7320","source":{"kind":"arxiv","id":"2504.05702","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.05702","created_at":"2026-07-05T10:46:08Z"},{"alias_kind":"arxiv_version","alias_value":"2504.05702v1","created_at":"2026-07-05T10:46:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.05702","created_at":"2026-07-05T10:46:08Z"},{"alias_kind":"pith_short_12","alias_value":"OTBVAD6YJBLZ","created_at":"2026-07-05T10:46:08Z"},{"alias_kind":"pith_short_16","alias_value":"OTBVAD6YJBLZ2NDP","created_at":"2026-07-05T10:46:08Z"},{"alias_kind":"pith_short_8","alias_value":"OTBVAD6Y","created_at":"2026-07-05T10:46:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OTBVAD6YJBLZ2NDP7NNLWSIUGL","target":"record","payload":{"canonical_record":{"source":{"id":"2504.05702","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-08T05:49:53Z","cross_cats_sorted":[],"title_canon_sha256":"b45a4b2044a844f937d29eac8a325274dfbe0b5d5931b15dbddec549407efdfa","abstract_canon_sha256":"c470102d1452e41b8541b33e9a70c68f2ade1f46d23540efa6a405a302891cba"},"schema_version":"1.0"},"canonical_sha256":"74c3500fd848579d346ffb5abb491432fa6f96cd379a052e69f67ebbf66c7320","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:46:08.214399Z","signature_b64":"ergrMXV/0WJlxOYgiSbLYGCdeYkqF02KitRnBzaDqM+MwBx7d39kwgRsS3B2sxtJFKg8Qb3IoT6CsgyCHInZBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74c3500fd848579d346ffb5abb491432fa6f96cd379a052e69f67ebbf66c7320","last_reissued_at":"2026-07-05T10:46:08.213952Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:46:08.213952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.05702","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":"2026-07-05T10:46:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YNJim1CHKPfp7Xx0UQD9JThG38UphkTD2eIiD7HnwKeZKPA0cEbj2holY4j8Udy0sKAejhmeU1is8InmUBB8BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T03:24:43.347754Z"},"content_sha256":"f38f0cbb5040b3d1900d9eca1d4eb4aa11a479a31ce4697f63076ec471c64eaa","schema_version":"1.0","event_id":"sha256:f38f0cbb5040b3d1900d9eca1d4eb4aa11a479a31ce4697f63076ec471c64eaa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OTBVAD6YJBLZ2NDP7NNLWSIUGL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating Speech-to-Text Systems with PennSound","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"James Fiumara, Jonathan Wright, Mark Liberman, Neville Ryant","submitted_at":"2025-04-08T05:49:53Z","abstract_excerpt":"A random sample of nearly 10 hours of speech from PennSound, the world's largest online collection of poetry readings and discussions, was used as a benchmark to evaluate several commercial and open-source speech-to-text systems. PennSound's wide variation in recording conditions and speech styles makes it a good representative for many other untranscribed audio collections. Reference transcripts were created by trained annotators, and system transcripts were produced from AWS, Azure, Google, IBM, NeMo, Rev.ai, Whisper, and Whisper.cpp. Based on word error rate, Rev.ai was the top performer, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.05702","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/2504.05702/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":"2026-07-05T10:46:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qmJge50fKT0H0rjkEQJ42gaka4nYcACXbuaHCXifYoXpwbRDCqIalXPGNmf9VwhtPcEh8e1qnstTTyJxdRPKDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T03:24:43.348129Z"},"content_sha256":"6a0dbd4d93193e5d4a2f6e7a75bfbc9ae8e572c265a069a0071d33fcf07d70c0","schema_version":"1.0","event_id":"sha256:6a0dbd4d93193e5d4a2f6e7a75bfbc9ae8e572c265a069a0071d33fcf07d70c0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OTBVAD6YJBLZ2NDP7NNLWSIUGL/bundle.json","state_url":"https://pith.science/pith/OTBVAD6YJBLZ2NDP7NNLWSIUGL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OTBVAD6YJBLZ2NDP7NNLWSIUGL/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":"2026-07-17T03:24:43Z","links":{"resolver":"https://pith.science/pith/OTBVAD6YJBLZ2NDP7NNLWSIUGL","bundle":"https://pith.science/pith/OTBVAD6YJBLZ2NDP7NNLWSIUGL/bundle.json","state":"https://pith.science/pith/OTBVAD6YJBLZ2NDP7NNLWSIUGL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OTBVAD6YJBLZ2NDP7NNLWSIUGL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OTBVAD6YJBLZ2NDP7NNLWSIUGL","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":"c470102d1452e41b8541b33e9a70c68f2ade1f46d23540efa6a405a302891cba","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-08T05:49:53Z","title_canon_sha256":"b45a4b2044a844f937d29eac8a325274dfbe0b5d5931b15dbddec549407efdfa"},"schema_version":"1.0","source":{"id":"2504.05702","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.05702","created_at":"2026-07-05T10:46:08Z"},{"alias_kind":"arxiv_version","alias_value":"2504.05702v1","created_at":"2026-07-05T10:46:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.05702","created_at":"2026-07-05T10:46:08Z"},{"alias_kind":"pith_short_12","alias_value":"OTBVAD6YJBLZ","created_at":"2026-07-05T10:46:08Z"},{"alias_kind":"pith_short_16","alias_value":"OTBVAD6YJBLZ2NDP","created_at":"2026-07-05T10:46:08Z"},{"alias_kind":"pith_short_8","alias_value":"OTBVAD6Y","created_at":"2026-07-05T10:46:08Z"}],"graph_snapshots":[{"event_id":"sha256:6a0dbd4d93193e5d4a2f6e7a75bfbc9ae8e572c265a069a0071d33fcf07d70c0","target":"graph","created_at":"2026-07-05T10:46:08Z","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/2504.05702/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A random sample of nearly 10 hours of speech from PennSound, the world's largest online collection of poetry readings and discussions, was used as a benchmark to evaluate several commercial and open-source speech-to-text systems. PennSound's wide variation in recording conditions and speech styles makes it a good representative for many other untranscribed audio collections. Reference transcripts were created by trained annotators, and system transcripts were produced from AWS, Azure, Google, IBM, NeMo, Rev.ai, Whisper, and Whisper.cpp. Based on word error rate, Rev.ai was the top performer, a","authors_text":"James Fiumara, Jonathan Wright, Mark Liberman, Neville Ryant","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-08T05:49:53Z","title":"Evaluating Speech-to-Text Systems with PennSound"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.05702","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:f38f0cbb5040b3d1900d9eca1d4eb4aa11a479a31ce4697f63076ec471c64eaa","target":"record","created_at":"2026-07-05T10:46:08Z","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":"c470102d1452e41b8541b33e9a70c68f2ade1f46d23540efa6a405a302891cba","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-08T05:49:53Z","title_canon_sha256":"b45a4b2044a844f937d29eac8a325274dfbe0b5d5931b15dbddec549407efdfa"},"schema_version":"1.0","source":{"id":"2504.05702","kind":"arxiv","version":1}},"canonical_sha256":"74c3500fd848579d346ffb5abb491432fa6f96cd379a052e69f67ebbf66c7320","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74c3500fd848579d346ffb5abb491432fa6f96cd379a052e69f67ebbf66c7320","first_computed_at":"2026-07-05T10:46:08.213952Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:46:08.213952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ergrMXV/0WJlxOYgiSbLYGCdeYkqF02KitRnBzaDqM+MwBx7d39kwgRsS3B2sxtJFKg8Qb3IoT6CsgyCHInZBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:46:08.214399Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.05702","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f38f0cbb5040b3d1900d9eca1d4eb4aa11a479a31ce4697f63076ec471c64eaa","sha256:6a0dbd4d93193e5d4a2f6e7a75bfbc9ae8e572c265a069a0071d33fcf07d70c0"],"state_sha256":"68af0330bfa940f1a657a31fbb877fff8abd2299f5acf6f2da3042aba9dbe1d3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gjOnBfHbMWaqHI/zRtu2yMoSfyRhXQzYwT+ibj9oWoQ8Eq+Ka0zKxCnhapv+zD3AtxSTZQk/IBqAwgLniW2RCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T03:24:43.350328Z","bundle_sha256":"81701cba87e26a2dcbf47c3e9178320c518ac8a31e1f7c43ca5571143072d7f5"}}