{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ODZO5FCBZHCED7L27DTBAN34V4","short_pith_number":"pith:ODZO5FCB","canonical_record":{"source":{"id":"2305.14580","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T23:37:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"57122409ef1919e67d19e4fd4a2b454a80b08654c2dde035564220325715f2db","abstract_canon_sha256":"6f28b05d90f75c5504bdd92cdb4b6d083297be47b20cbb46892b9bd6b84f547a"},"schema_version":"1.0"},"canonical_sha256":"70f2ee9441c9c441fd7af8e610377caf032864c19e2a1bf0962515e0614d76e8","source":{"kind":"arxiv","id":"2305.14580","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14580","created_at":"2026-07-05T06:14:11Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14580v2","created_at":"2026-07-05T06:14:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14580","created_at":"2026-07-05T06:14:11Z"},{"alias_kind":"pith_short_12","alias_value":"ODZO5FCBZHCE","created_at":"2026-07-05T06:14:11Z"},{"alias_kind":"pith_short_16","alias_value":"ODZO5FCBZHCED7L2","created_at":"2026-07-05T06:14:11Z"},{"alias_kind":"pith_short_8","alias_value":"ODZO5FCB","created_at":"2026-07-05T06:14:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ODZO5FCBZHCED7L27DTBAN34V4","target":"record","payload":{"canonical_record":{"source":{"id":"2305.14580","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T23:37:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"57122409ef1919e67d19e4fd4a2b454a80b08654c2dde035564220325715f2db","abstract_canon_sha256":"6f28b05d90f75c5504bdd92cdb4b6d083297be47b20cbb46892b9bd6b84f547a"},"schema_version":"1.0"},"canonical_sha256":"70f2ee9441c9c441fd7af8e610377caf032864c19e2a1bf0962515e0614d76e8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:11.146155Z","signature_b64":"8Lk11IkdqlLVfA8ZbUu9ZdXJOz3aXjsMIyi4rDoGUgTjGDz4P2UgeZci4JfCiZnKXr16nj49ncScDMf7PGbmCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70f2ee9441c9c441fd7af8e610377caf032864c19e2a1bf0962515e0614d76e8","last_reissued_at":"2026-07-05T06:14:11.145743Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:11.145743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.14580","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":"2026-07-05T06:14:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CWdLUNlfooG39HWLA6fHHwdA7jNXa6TOTL9jWEo6gTR3pzQsIUArUKghtxcMrUOYyeWcuYzqK+zX+GgqL3HZAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T18:50:52.892303Z"},"content_sha256":"f694d3c62a993da786ebd109773f9f6c13ab273d5d130331d6b450d5b1de671d","schema_version":"1.0","event_id":"sha256:f694d3c62a993da786ebd109773f9f6c13ab273d5d130331d6b450d5b1de671d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ODZO5FCBZHCED7L27DTBAN34V4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating OpenAI's Whisper ASR for Punctuation Prediction and Topic Modeling of life histories of the Museum of the Person","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anderson Soares, Arnaldo Candido Junior, Edresson Casanova, Lucas Rafael Stefanel Gris, Ricardo Marcacini, Sandra Maria Alu\\'isio","submitted_at":"2023-05-23T23:37:29Z","abstract_excerpt":"Automatic speech recognition (ASR) systems play a key role in applications involving human-machine interactions. Despite their importance, ASR models for the Portuguese language proposed in the last decade have limitations in relation to the correct identification of punctuation marks in automatic transcriptions, which hinder the use of transcriptions by other systems, models, and even by humans. However, recently Whisper ASR was proposed by OpenAI, a general-purpose speech recognition model that has generated great expectations in dealing with such limitations. This chapter presents the first"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14580","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/2305.14580/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":"2026-07-05T06:14:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f7PfqItEmeppP7zZn50870/WvHaJB2DL8W2n5IeUs1fLqcT8qqR9eUb6O9o3cCOuNHjYm8fOXYnpMb8E1SbVBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T18:50:52.892919Z"},"content_sha256":"b00fde0fdaa74dd5ded27ba0510a999f5148706c3b3e65f13300ae17f4db9493","schema_version":"1.0","event_id":"sha256:b00fde0fdaa74dd5ded27ba0510a999f5148706c3b3e65f13300ae17f4db9493"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ODZO5FCBZHCED7L27DTBAN34V4/bundle.json","state_url":"https://pith.science/pith/ODZO5FCBZHCED7L27DTBAN34V4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ODZO5FCBZHCED7L27DTBAN34V4/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":"2026-08-20T18:50:52Z","links":{"resolver":"https://pith.science/pith/ODZO5FCBZHCED7L27DTBAN34V4","bundle":"https://pith.science/pith/ODZO5FCBZHCED7L27DTBAN34V4/bundle.json","state":"https://pith.science/pith/ODZO5FCBZHCED7L27DTBAN34V4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ODZO5FCBZHCED7L27DTBAN34V4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ODZO5FCBZHCED7L27DTBAN34V4","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":"6f28b05d90f75c5504bdd92cdb4b6d083297be47b20cbb46892b9bd6b84f547a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T23:37:29Z","title_canon_sha256":"57122409ef1919e67d19e4fd4a2b454a80b08654c2dde035564220325715f2db"},"schema_version":"1.0","source":{"id":"2305.14580","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14580","created_at":"2026-07-05T06:14:11Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14580v2","created_at":"2026-07-05T06:14:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14580","created_at":"2026-07-05T06:14:11Z"},{"alias_kind":"pith_short_12","alias_value":"ODZO5FCBZHCE","created_at":"2026-07-05T06:14:11Z"},{"alias_kind":"pith_short_16","alias_value":"ODZO5FCBZHCED7L2","created_at":"2026-07-05T06:14:11Z"},{"alias_kind":"pith_short_8","alias_value":"ODZO5FCB","created_at":"2026-07-05T06:14:11Z"}],"graph_snapshots":[{"event_id":"sha256:b00fde0fdaa74dd5ded27ba0510a999f5148706c3b3e65f13300ae17f4db9493","target":"graph","created_at":"2026-07-05T06:14:11Z","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/2305.14580/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatic speech recognition (ASR) systems play a key role in applications involving human-machine interactions. Despite their importance, ASR models for the Portuguese language proposed in the last decade have limitations in relation to the correct identification of punctuation marks in automatic transcriptions, which hinder the use of transcriptions by other systems, models, and even by humans. However, recently Whisper ASR was proposed by OpenAI, a general-purpose speech recognition model that has generated great expectations in dealing with such limitations. This chapter presents the first","authors_text":"Anderson Soares, Arnaldo Candido Junior, Edresson Casanova, Lucas Rafael Stefanel Gris, Ricardo Marcacini, Sandra Maria Alu\\'isio","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T23:37:29Z","title":"Evaluating OpenAI's Whisper ASR for Punctuation Prediction and Topic Modeling of life histories of the Museum of the Person"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14580","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:f694d3c62a993da786ebd109773f9f6c13ab273d5d130331d6b450d5b1de671d","target":"record","created_at":"2026-07-05T06:14:11Z","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":"6f28b05d90f75c5504bdd92cdb4b6d083297be47b20cbb46892b9bd6b84f547a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T23:37:29Z","title_canon_sha256":"57122409ef1919e67d19e4fd4a2b454a80b08654c2dde035564220325715f2db"},"schema_version":"1.0","source":{"id":"2305.14580","kind":"arxiv","version":2}},"canonical_sha256":"70f2ee9441c9c441fd7af8e610377caf032864c19e2a1bf0962515e0614d76e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"70f2ee9441c9c441fd7af8e610377caf032864c19e2a1bf0962515e0614d76e8","first_computed_at":"2026-07-05T06:14:11.145743Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:14:11.145743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8Lk11IkdqlLVfA8ZbUu9ZdXJOz3aXjsMIyi4rDoGUgTjGDz4P2UgeZci4JfCiZnKXr16nj49ncScDMf7PGbmCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:14:11.146155Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.14580","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f694d3c62a993da786ebd109773f9f6c13ab273d5d130331d6b450d5b1de671d","sha256:b00fde0fdaa74dd5ded27ba0510a999f5148706c3b3e65f13300ae17f4db9493"],"state_sha256":"24c54b8bbe8ba4bb8ba1da71b960cae832f0c5f420bb6b100544a51e134212ea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sh2b7A4AtU3AWSPuOBCGwMhtk7XFWhA5UW28XjEJCxlAnChBJNlGqgYFyAfwz93u+3IqASav+NFUJsUe1GSABw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T18:50:52.899972Z","bundle_sha256":"0971faaf8916aa2c3dbd213f5592180e35fa05a8acea4824e963925363cee092"}}