{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:UL25MIH44O5EV46U5QWYEWLUI3","short_pith_number":"pith:UL25MIH4","canonical_record":{"source":{"id":"2310.02943","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-04T16:23:37Z","cross_cats_sorted":[],"title_canon_sha256":"f1aa1e43ecb654f9e43b0344456f1f3db6ad36c0d73f9e501b5154091b1cb7fd","abstract_canon_sha256":"3438e21604998c488af6f06140106290a2aa1d42d294d1f6e544c10f05150b19"},"schema_version":"1.0"},"canonical_sha256":"a2f5d620fce3ba4af3d4ec2d82597446c96adcd2c9d7bee6aa9fd9a71bf24b57","source":{"kind":"arxiv","id":"2310.02943","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.02943","created_at":"2026-07-05T06:57:15Z"},{"alias_kind":"arxiv_version","alias_value":"2310.02943v1","created_at":"2026-07-05T06:57:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02943","created_at":"2026-07-05T06:57:15Z"},{"alias_kind":"pith_short_12","alias_value":"UL25MIH44O5E","created_at":"2026-07-05T06:57:15Z"},{"alias_kind":"pith_short_16","alias_value":"UL25MIH44O5EV46U","created_at":"2026-07-05T06:57:15Z"},{"alias_kind":"pith_short_8","alias_value":"UL25MIH4","created_at":"2026-07-05T06:57:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:UL25MIH44O5EV46U5QWYEWLUI3","target":"record","payload":{"canonical_record":{"source":{"id":"2310.02943","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-04T16:23:37Z","cross_cats_sorted":[],"title_canon_sha256":"f1aa1e43ecb654f9e43b0344456f1f3db6ad36c0d73f9e501b5154091b1cb7fd","abstract_canon_sha256":"3438e21604998c488af6f06140106290a2aa1d42d294d1f6e544c10f05150b19"},"schema_version":"1.0"},"canonical_sha256":"a2f5d620fce3ba4af3d4ec2d82597446c96adcd2c9d7bee6aa9fd9a71bf24b57","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:57:15.761863Z","signature_b64":"F3IAaNGhGN5HMlm1zLTA3U01GsZ+1w4l/EWEXNc5vwQ2pRCmJJ1M2ibjW6puRdnJGF8jmS3WGH5Iip/0AS99Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2f5d620fce3ba4af3d4ec2d82597446c96adcd2c9d7bee6aa9fd9a71bf24b57","last_reissued_at":"2026-07-05T06:57:15.761390Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:57:15.761390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.02943","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":"2026-07-05T06:57:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4Ns3yeBx3UwEtmOHqqF056yfPxtr4fL+WwYztpQwxDfaE+1TZY2aHWOrzZTP0fPO/OVe8orURz1FlmZOZNlpAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:31:23.035696Z"},"content_sha256":"c8b4844917e136eafd7acbe4666942fc4c89ffb875053ec11c7f78124f320551","schema_version":"1.0","event_id":"sha256:c8b4844917e136eafd7acbe4666942fc4c89ffb875053ec11c7f78124f320551"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:UL25MIH44O5EV46U5QWYEWLUI3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LibriSpeech-PC: Benchmark for Evaluation of Punctuation and Capitalization Capabilities of end-to-end ASR Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aleksandr Meister, Boris Ginsburg, Evelina Bakhturina, Matvei Novikov, Nikolay Karpov, Vitaly Lavrukhin","submitted_at":"2023-10-04T16:23:37Z","abstract_excerpt":"Traditional automatic speech recognition (ASR) models output lower-cased words without punctuation marks, which reduces readability and necessitates a subsequent text processing model to convert ASR transcripts into a proper format. Simultaneously, the development of end-to-end ASR models capable of predicting punctuation and capitalization presents several challenges, primarily due to limited data availability and shortcomings in the existing evaluation methods, such as inadequate assessment of punctuation prediction. In this paper, we introduce a LibriSpeech-PC benchmark designed to assess t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02943","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/2310.02943/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":"2026-07-05T06:57:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rq6Kc8ySIPQxXEidyPGogY2dSCHRasveEs2KCsu4z0FnfptMOuzweUkeBfetXFTMZuEOVLaTk3P7ZXRgcBPmAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:31:23.036081Z"},"content_sha256":"197617c2308c7a37bc59f5527d3dfd77a1ab44f9a0cd64c7a7d2ff69d37089b6","schema_version":"1.0","event_id":"sha256:197617c2308c7a37bc59f5527d3dfd77a1ab44f9a0cd64c7a7d2ff69d37089b6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UL25MIH44O5EV46U5QWYEWLUI3/bundle.json","state_url":"https://pith.science/pith/UL25MIH44O5EV46U5QWYEWLUI3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UL25MIH44O5EV46U5QWYEWLUI3/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":"2026-07-06T08:31:23Z","links":{"resolver":"https://pith.science/pith/UL25MIH44O5EV46U5QWYEWLUI3","bundle":"https://pith.science/pith/UL25MIH44O5EV46U5QWYEWLUI3/bundle.json","state":"https://pith.science/pith/UL25MIH44O5EV46U5QWYEWLUI3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UL25MIH44O5EV46U5QWYEWLUI3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UL25MIH44O5EV46U5QWYEWLUI3","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":"3438e21604998c488af6f06140106290a2aa1d42d294d1f6e544c10f05150b19","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-04T16:23:37Z","title_canon_sha256":"f1aa1e43ecb654f9e43b0344456f1f3db6ad36c0d73f9e501b5154091b1cb7fd"},"schema_version":"1.0","source":{"id":"2310.02943","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.02943","created_at":"2026-07-05T06:57:15Z"},{"alias_kind":"arxiv_version","alias_value":"2310.02943v1","created_at":"2026-07-05T06:57:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02943","created_at":"2026-07-05T06:57:15Z"},{"alias_kind":"pith_short_12","alias_value":"UL25MIH44O5E","created_at":"2026-07-05T06:57:15Z"},{"alias_kind":"pith_short_16","alias_value":"UL25MIH44O5EV46U","created_at":"2026-07-05T06:57:15Z"},{"alias_kind":"pith_short_8","alias_value":"UL25MIH4","created_at":"2026-07-05T06:57:15Z"}],"graph_snapshots":[{"event_id":"sha256:197617c2308c7a37bc59f5527d3dfd77a1ab44f9a0cd64c7a7d2ff69d37089b6","target":"graph","created_at":"2026-07-05T06:57:15Z","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/2310.02943/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditional automatic speech recognition (ASR) models output lower-cased words without punctuation marks, which reduces readability and necessitates a subsequent text processing model to convert ASR transcripts into a proper format. Simultaneously, the development of end-to-end ASR models capable of predicting punctuation and capitalization presents several challenges, primarily due to limited data availability and shortcomings in the existing evaluation methods, such as inadequate assessment of punctuation prediction. In this paper, we introduce a LibriSpeech-PC benchmark designed to assess t","authors_text":"Aleksandr Meister, Boris Ginsburg, Evelina Bakhturina, Matvei Novikov, Nikolay Karpov, Vitaly Lavrukhin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-04T16:23:37Z","title":"LibriSpeech-PC: Benchmark for Evaluation of Punctuation and Capitalization Capabilities of end-to-end ASR Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02943","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:c8b4844917e136eafd7acbe4666942fc4c89ffb875053ec11c7f78124f320551","target":"record","created_at":"2026-07-05T06:57:15Z","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":"3438e21604998c488af6f06140106290a2aa1d42d294d1f6e544c10f05150b19","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-04T16:23:37Z","title_canon_sha256":"f1aa1e43ecb654f9e43b0344456f1f3db6ad36c0d73f9e501b5154091b1cb7fd"},"schema_version":"1.0","source":{"id":"2310.02943","kind":"arxiv","version":1}},"canonical_sha256":"a2f5d620fce3ba4af3d4ec2d82597446c96adcd2c9d7bee6aa9fd9a71bf24b57","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2f5d620fce3ba4af3d4ec2d82597446c96adcd2c9d7bee6aa9fd9a71bf24b57","first_computed_at":"2026-07-05T06:57:15.761390Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:57:15.761390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F3IAaNGhGN5HMlm1zLTA3U01GsZ+1w4l/EWEXNc5vwQ2pRCmJJ1M2ibjW6puRdnJGF8jmS3WGH5Iip/0AS99Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T06:57:15.761863Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.02943","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8b4844917e136eafd7acbe4666942fc4c89ffb875053ec11c7f78124f320551","sha256:197617c2308c7a37bc59f5527d3dfd77a1ab44f9a0cd64c7a7d2ff69d37089b6"],"state_sha256":"f2aedc12a72ea6b55ece2ac83e8441a1b905689e083533f82d65fceaa3161034"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yFVuk4/xYH+QqtNv52du58v6k6axqvW80YmrNqyMENm18noZ/SyBQ7MH8ypp9cQgaDmL068Qbdc5mXFaLDqRCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T08:31:23.038115Z","bundle_sha256":"4944d3a86b749654d81b4b0d2cb6f9bdd5f25e93d52c89356d851ef3e8bbdae1"}}