{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:CNDVNB4VVCBDR6GZ5JRINF6YDW","short_pith_number":"pith:CNDVNB4V","canonical_record":{"source":{"id":"2104.02219","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-06T01:16:59Z","cross_cats_sorted":[],"title_canon_sha256":"a88a5c3ad3cfef39776b216ebf7048f0f2a6a5a99817abda41d51f792965a186","abstract_canon_sha256":"4422d8c7e89319d644807f6d18ec58af97a7386180a9686bdbf4f0ac3b3ec694"},"schema_version":"1.0"},"canonical_sha256":"1347568795a88238f8d9ea628697d81db064093fb70121ad5d5ab8255e7d1070","source":{"kind":"arxiv","id":"2104.02219","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.02219","created_at":"2026-07-05T02:29:15Z"},{"alias_kind":"arxiv_version","alias_value":"2104.02219v1","created_at":"2026-07-05T02:29:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.02219","created_at":"2026-07-05T02:29:15Z"},{"alias_kind":"pith_short_12","alias_value":"CNDVNB4VVCBD","created_at":"2026-07-05T02:29:15Z"},{"alias_kind":"pith_short_16","alias_value":"CNDVNB4VVCBDR6GZ","created_at":"2026-07-05T02:29:15Z"},{"alias_kind":"pith_short_8","alias_value":"CNDVNB4V","created_at":"2026-07-05T02:29:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:CNDVNB4VVCBDR6GZ5JRINF6YDW","target":"record","payload":{"canonical_record":{"source":{"id":"2104.02219","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-06T01:16:59Z","cross_cats_sorted":[],"title_canon_sha256":"a88a5c3ad3cfef39776b216ebf7048f0f2a6a5a99817abda41d51f792965a186","abstract_canon_sha256":"4422d8c7e89319d644807f6d18ec58af97a7386180a9686bdbf4f0ac3b3ec694"},"schema_version":"1.0"},"canonical_sha256":"1347568795a88238f8d9ea628697d81db064093fb70121ad5d5ab8255e7d1070","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:29:15.713262Z","signature_b64":"2OjDvqqIXYmqqjn0FDWAwxQNQFSKUlB7USPm2Q4h8cePtqgHoVLwcm1BLdaK08toMIPi7Eb2F8Uob9seAVmhDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1347568795a88238f8d9ea628697d81db064093fb70121ad5d5ab8255e7d1070","last_reissued_at":"2026-07-05T02:29:15.712855Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:29:15.712855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.02219","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":"2026-07-05T02:29:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9t0GFvI/JQd3+22KVzkb8G/5/BmLX0ipKrxUz2iLyl4gg/M4iTgwDWRgchaotdazOS28K08OkkfPf0Z8bd6DCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:45:07.001721Z"},"content_sha256":"38c4c6761536369cdb827c005ba353e5e28b3b169f8fb3ee46775a74d0aa03b8","schema_version":"1.0","event_id":"sha256:38c4c6761536369cdb827c005ba353e5e28b3b169f8fb3ee46775a74d0aa03b8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:CNDVNB4VVCBDR6GZ5JRINF6YDW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Understanding Medical Conversations: Rich Transcription, Confidence Scores & Information Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hagen Soltau, Izhak Shafran, Laurent El Shafey, Mingqiu Wang","submitted_at":"2021-04-06T01:16:59Z","abstract_excerpt":"In this paper, we describe novel components for extracting clinically relevant information from medical conversations which will be available as Google APIs. We describe a transformer-based Recurrent Neural Network Transducer (RNN-T) model tailored for long-form audio, which can produce rich transcriptions including speaker segmentation, speaker role labeling, punctuation and capitalization. On a representative test set, we compare performance of RNN-T models with different encoders, units and streaming constraints. Our transformer-based streaming model performs at about 20% WER on the ASR tas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.02219","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/2104.02219/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":"2026-07-05T02:29:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZaLPwtYDFsEPQX1K8GBO/wwYpntNd2NNA5cxgOn6R2EDrrEQ3I+745HYkCCBMeL0FRSGC6I+ODi0Ln+AvaZ1Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:45:07.002315Z"},"content_sha256":"81e03f1b94da9eba517947d4ed10bc75494b0cb4c9c0fbb6d2dfff7e2523fe48","schema_version":"1.0","event_id":"sha256:81e03f1b94da9eba517947d4ed10bc75494b0cb4c9c0fbb6d2dfff7e2523fe48"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CNDVNB4VVCBDR6GZ5JRINF6YDW/bundle.json","state_url":"https://pith.science/pith/CNDVNB4VVCBDR6GZ5JRINF6YDW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CNDVNB4VVCBDR6GZ5JRINF6YDW/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":"2026-08-04T07:45:07Z","links":{"resolver":"https://pith.science/pith/CNDVNB4VVCBDR6GZ5JRINF6YDW","bundle":"https://pith.science/pith/CNDVNB4VVCBDR6GZ5JRINF6YDW/bundle.json","state":"https://pith.science/pith/CNDVNB4VVCBDR6GZ5JRINF6YDW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CNDVNB4VVCBDR6GZ5JRINF6YDW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:CNDVNB4VVCBDR6GZ5JRINF6YDW","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":"4422d8c7e89319d644807f6d18ec58af97a7386180a9686bdbf4f0ac3b3ec694","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-06T01:16:59Z","title_canon_sha256":"a88a5c3ad3cfef39776b216ebf7048f0f2a6a5a99817abda41d51f792965a186"},"schema_version":"1.0","source":{"id":"2104.02219","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.02219","created_at":"2026-07-05T02:29:15Z"},{"alias_kind":"arxiv_version","alias_value":"2104.02219v1","created_at":"2026-07-05T02:29:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.02219","created_at":"2026-07-05T02:29:15Z"},{"alias_kind":"pith_short_12","alias_value":"CNDVNB4VVCBD","created_at":"2026-07-05T02:29:15Z"},{"alias_kind":"pith_short_16","alias_value":"CNDVNB4VVCBDR6GZ","created_at":"2026-07-05T02:29:15Z"},{"alias_kind":"pith_short_8","alias_value":"CNDVNB4V","created_at":"2026-07-05T02:29:15Z"}],"graph_snapshots":[{"event_id":"sha256:81e03f1b94da9eba517947d4ed10bc75494b0cb4c9c0fbb6d2dfff7e2523fe48","target":"graph","created_at":"2026-07-05T02:29:15Z","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/2104.02219/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we describe novel components for extracting clinically relevant information from medical conversations which will be available as Google APIs. We describe a transformer-based Recurrent Neural Network Transducer (RNN-T) model tailored for long-form audio, which can produce rich transcriptions including speaker segmentation, speaker role labeling, punctuation and capitalization. On a representative test set, we compare performance of RNN-T models with different encoders, units and streaming constraints. Our transformer-based streaming model performs at about 20% WER on the ASR tas","authors_text":"Hagen Soltau, Izhak Shafran, Laurent El Shafey, Mingqiu Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-06T01:16:59Z","title":"Understanding Medical Conversations: Rich Transcription, Confidence Scores & Information Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.02219","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":"sha256:38c4c6761536369cdb827c005ba353e5e28b3b169f8fb3ee46775a74d0aa03b8","target":"record","created_at":"2026-07-05T02:29:15Z","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":"4422d8c7e89319d644807f6d18ec58af97a7386180a9686bdbf4f0ac3b3ec694","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-06T01:16:59Z","title_canon_sha256":"a88a5c3ad3cfef39776b216ebf7048f0f2a6a5a99817abda41d51f792965a186"},"schema_version":"1.0","source":{"id":"2104.02219","kind":"arxiv","version":1}},"canonical_sha256":"1347568795a88238f8d9ea628697d81db064093fb70121ad5d5ab8255e7d1070","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1347568795a88238f8d9ea628697d81db064093fb70121ad5d5ab8255e7d1070","first_computed_at":"2026-07-05T02:29:15.712855Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:29:15.712855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2OjDvqqIXYmqqjn0FDWAwxQNQFSKUlB7USPm2Q4h8cePtqgHoVLwcm1BLdaK08toMIPi7Eb2F8Uob9seAVmhDA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:29:15.713262Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.02219","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:38c4c6761536369cdb827c005ba353e5e28b3b169f8fb3ee46775a74d0aa03b8","sha256:81e03f1b94da9eba517947d4ed10bc75494b0cb4c9c0fbb6d2dfff7e2523fe48"],"state_sha256":"72d48893ee96f169fdbbfc617bc06a7a640b57f377a2ae49c99e1d2adc50497f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F/d3O0h+CC8LXaorJd771W4k8HtZcHWD3w2fn/hzxurd+IiYFUsax6TD2cyDu8XtAyvcm/BtPnsQM1L79014AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T07:45:07.079927Z","bundle_sha256":"b89e177a9c48a4a917b4141a33692854539578ba6387a34187100ba367326791"}}