{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:BZCJATN2Y3EMX7OIXGCDFRKANG","short_pith_number":"pith:BZCJATN2","canonical_record":{"source":{"id":"2004.04438","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-09T09:26:42Z","cross_cats_sorted":[],"title_canon_sha256":"29df7da92e9304a1aaf04f5714657a6e138ad054fdaae092daa243cc54894bba","abstract_canon_sha256":"834ab9be915b643ae552c8679b6acd028d59f897c2832f31fc5da21e97bf5351"},"schema_version":"1.0"},"canonical_sha256":"0e44904dbac6c8cbfdc8b98432c54069a2af6c3d9ac7b3c5a5b73654c786e38b","source":{"kind":"arxiv","id":"2004.04438","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.04438","created_at":"2026-07-05T00:54:07Z"},{"alias_kind":"arxiv_version","alias_value":"2004.04438v1","created_at":"2026-07-05T00:54:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.04438","created_at":"2026-07-05T00:54:07Z"},{"alias_kind":"pith_short_12","alias_value":"BZCJATN2Y3EM","created_at":"2026-07-05T00:54:07Z"},{"alias_kind":"pith_short_16","alias_value":"BZCJATN2Y3EMX7OI","created_at":"2026-07-05T00:54:07Z"},{"alias_kind":"pith_short_8","alias_value":"BZCJATN2","created_at":"2026-07-05T00:54:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:BZCJATN2Y3EMX7OIXGCDFRKANG","target":"record","payload":{"canonical_record":{"source":{"id":"2004.04438","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-09T09:26:42Z","cross_cats_sorted":[],"title_canon_sha256":"29df7da92e9304a1aaf04f5714657a6e138ad054fdaae092daa243cc54894bba","abstract_canon_sha256":"834ab9be915b643ae552c8679b6acd028d59f897c2832f31fc5da21e97bf5351"},"schema_version":"1.0"},"canonical_sha256":"0e44904dbac6c8cbfdc8b98432c54069a2af6c3d9ac7b3c5a5b73654c786e38b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:54:07.971460Z","signature_b64":"B74mZ9AtqEIoPXRW/NlcX6LP9/tJWPhH1tQ5KF+tT6AmuI86H6QnEvlZ/xfPwyyMoSncaqWT3R99LTAAFdwPCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e44904dbac6c8cbfdc8b98432c54069a2af6c3d9ac7b3c5a5b73654c786e38b","last_reissued_at":"2026-07-05T00:54:07.971106Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:54:07.971106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.04438","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":"2026-07-05T00:54:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7JrhQNau/w5Fos34L7pcspj6ICQIMc/AYuSxKroS0Zs1c5rxe4HeU7WwhY3AYtoQurZH8TPAE2WwXAgvOg8uCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:09:04.975900Z"},"content_sha256":"f2ab1d7caed771c0bafa3077d8b133fa5202ef1bb6c0db7d5e6ca003f219e085","schema_version":"1.0","event_id":"sha256:f2ab1d7caed771c0bafa3077d8b133fa5202ef1bb6c0db7d5e6ca003f219e085"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:BZCJATN2Y3EMX7OIXGCDFRKANG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Readability for Automatic Speech Recognition Transcription","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hong Qu, Junwei Liao, Linjun Shou, Liyang Lu, Michael Zeng, Ming Gong, Sefik Emre Eskimez, Yu Shi","submitted_at":"2020-04-09T09:26:42Z","abstract_excerpt":"Modern Automatic Speech Recognition (ASR) systems can achieve high performance in terms of recognition accuracy. However, a perfectly accurate transcript still can be challenging to read due to grammatical errors, disfluency, and other errata common in spoken communication. Many downstream tasks and human readers rely on the output of the ASR system; therefore, errors introduced by the speaker and ASR system alike will be propagated to the next task in the pipeline. In this work, we propose a novel NLP task called ASR post-processing for readability (APR) that aims to transform the noisy ASR o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.04438","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/2004.04438/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":"2026-07-05T00:54:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NBZd4QuYpImTGkQsDmsMjZxOWWYalCWOKfr0xcYCTRrMihioDgObHkojq/IMmdoWcdCA0jVYJhTK+81n68u+Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:09:04.976277Z"},"content_sha256":"ac442a81edfa9af66e36f84d67933b11e8daf46ceec55e0161ce079d82f1d55f","schema_version":"1.0","event_id":"sha256:ac442a81edfa9af66e36f84d67933b11e8daf46ceec55e0161ce079d82f1d55f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BZCJATN2Y3EMX7OIXGCDFRKANG/bundle.json","state_url":"https://pith.science/pith/BZCJATN2Y3EMX7OIXGCDFRKANG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BZCJATN2Y3EMX7OIXGCDFRKANG/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":"2026-07-07T14:09:04Z","links":{"resolver":"https://pith.science/pith/BZCJATN2Y3EMX7OIXGCDFRKANG","bundle":"https://pith.science/pith/BZCJATN2Y3EMX7OIXGCDFRKANG/bundle.json","state":"https://pith.science/pith/BZCJATN2Y3EMX7OIXGCDFRKANG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BZCJATN2Y3EMX7OIXGCDFRKANG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:BZCJATN2Y3EMX7OIXGCDFRKANG","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":"834ab9be915b643ae552c8679b6acd028d59f897c2832f31fc5da21e97bf5351","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-09T09:26:42Z","title_canon_sha256":"29df7da92e9304a1aaf04f5714657a6e138ad054fdaae092daa243cc54894bba"},"schema_version":"1.0","source":{"id":"2004.04438","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.04438","created_at":"2026-07-05T00:54:07Z"},{"alias_kind":"arxiv_version","alias_value":"2004.04438v1","created_at":"2026-07-05T00:54:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.04438","created_at":"2026-07-05T00:54:07Z"},{"alias_kind":"pith_short_12","alias_value":"BZCJATN2Y3EM","created_at":"2026-07-05T00:54:07Z"},{"alias_kind":"pith_short_16","alias_value":"BZCJATN2Y3EMX7OI","created_at":"2026-07-05T00:54:07Z"},{"alias_kind":"pith_short_8","alias_value":"BZCJATN2","created_at":"2026-07-05T00:54:07Z"}],"graph_snapshots":[{"event_id":"sha256:ac442a81edfa9af66e36f84d67933b11e8daf46ceec55e0161ce079d82f1d55f","target":"graph","created_at":"2026-07-05T00:54:07Z","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/2004.04438/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern Automatic Speech Recognition (ASR) systems can achieve high performance in terms of recognition accuracy. However, a perfectly accurate transcript still can be challenging to read due to grammatical errors, disfluency, and other errata common in spoken communication. Many downstream tasks and human readers rely on the output of the ASR system; therefore, errors introduced by the speaker and ASR system alike will be propagated to the next task in the pipeline. In this work, we propose a novel NLP task called ASR post-processing for readability (APR) that aims to transform the noisy ASR o","authors_text":"Hong Qu, Junwei Liao, Linjun Shou, Liyang Lu, Michael Zeng, Ming Gong, Sefik Emre Eskimez, Yu Shi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-09T09:26:42Z","title":"Improving Readability for Automatic Speech Recognition Transcription"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.04438","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:f2ab1d7caed771c0bafa3077d8b133fa5202ef1bb6c0db7d5e6ca003f219e085","target":"record","created_at":"2026-07-05T00:54:07Z","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":"834ab9be915b643ae552c8679b6acd028d59f897c2832f31fc5da21e97bf5351","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-09T09:26:42Z","title_canon_sha256":"29df7da92e9304a1aaf04f5714657a6e138ad054fdaae092daa243cc54894bba"},"schema_version":"1.0","source":{"id":"2004.04438","kind":"arxiv","version":1}},"canonical_sha256":"0e44904dbac6c8cbfdc8b98432c54069a2af6c3d9ac7b3c5a5b73654c786e38b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e44904dbac6c8cbfdc8b98432c54069a2af6c3d9ac7b3c5a5b73654c786e38b","first_computed_at":"2026-07-05T00:54:07.971106Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:54:07.971106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B74mZ9AtqEIoPXRW/NlcX6LP9/tJWPhH1tQ5KF+tT6AmuI86H6QnEvlZ/xfPwyyMoSncaqWT3R99LTAAFdwPCA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:54:07.971460Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.04438","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f2ab1d7caed771c0bafa3077d8b133fa5202ef1bb6c0db7d5e6ca003f219e085","sha256:ac442a81edfa9af66e36f84d67933b11e8daf46ceec55e0161ce079d82f1d55f"],"state_sha256":"18cdd8a64529a518344cbe9064ffb2baf440690f3407794b7105452514195089"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QTzSJl1S4pKJtWkgMVewVU5kfnq6eBMMBpBm3UtkLJOnidYxOcMzYNtOLEzsrIOSvEFne114rhCaaq485geeBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T14:09:04.981201Z","bundle_sha256":"9aaf3a5d796751f32089a59787c23ba44aafb4dce3275a9dbbca8b7acc66787a"}}