{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:QTS2I5ZE5TYLYKRJXR5OTM2VKP","short_pith_number":"pith:QTS2I5ZE","canonical_record":{"source":{"id":"2110.07356","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-09T18:32:56Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e3ca4e7a9c715c969816ea98effe7d64507f3c5c40eef23c4e3c4d3e8c37a776","abstract_canon_sha256":"6f0d34196ef208a1d6936ea2260dd3f7c75515f71e98737feadcb4860d9130b8"},"schema_version":"1.0"},"canonical_sha256":"84e5a47724ecf0bc2a29bc7ae9b35553f5ce3b2abbb37b01de757cc3c01c1147","source":{"kind":"arxiv","id":"2110.07356","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.07356","created_at":"2026-07-05T03:22:41Z"},{"alias_kind":"arxiv_version","alias_value":"2110.07356v1","created_at":"2026-07-05T03:22:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.07356","created_at":"2026-07-05T03:22:41Z"},{"alias_kind":"pith_short_12","alias_value":"QTS2I5ZE5TYL","created_at":"2026-07-05T03:22:41Z"},{"alias_kind":"pith_short_16","alias_value":"QTS2I5ZE5TYLYKRJ","created_at":"2026-07-05T03:22:41Z"},{"alias_kind":"pith_short_8","alias_value":"QTS2I5ZE","created_at":"2026-07-05T03:22:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:QTS2I5ZE5TYLYKRJXR5OTM2VKP","target":"record","payload":{"canonical_record":{"source":{"id":"2110.07356","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-09T18:32:56Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e3ca4e7a9c715c969816ea98effe7d64507f3c5c40eef23c4e3c4d3e8c37a776","abstract_canon_sha256":"6f0d34196ef208a1d6936ea2260dd3f7c75515f71e98737feadcb4860d9130b8"},"schema_version":"1.0"},"canonical_sha256":"84e5a47724ecf0bc2a29bc7ae9b35553f5ce3b2abbb37b01de757cc3c01c1147","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:22:41.206013Z","signature_b64":"zsn9JrZ2+lnkslCyypG0s8ABT8hVO7Hy/FKZ3i7o3BXMpDOxUCdso4tZSJgfP/Zqg5VaoSKlWIoygHWGt8ecBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84e5a47724ecf0bc2a29bc7ae9b35553f5ce3b2abbb37b01de757cc3c01c1147","last_reissued_at":"2026-07-05T03:22:41.205638Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:22:41.205638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.07356","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":"2026-07-05T03:22:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TIHAjz6iu8D63CPz+9jh3jB5eYEbVGTu8N1BCY5a+V9mr3BijyfbjDmE6jX5EPjYu/L+wqKMkYPbosBWuDtjCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T03:31:37.084768Z"},"content_sha256":"33338ed9407552a989476d4fb83368bb2e157186fc3bb39d3821e711e79f612b","schema_version":"1.0","event_id":"sha256:33338ed9407552a989476d4fb83368bb2e157186fc3bb39d3821e711e79f612b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:QTS2I5ZE5TYLYKRJXR5OTM2VKP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Medically Aware GPT-3 as a Data Generator for Medical Dialogue Summarization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Anitha Kannan, Bharath Chintagunta, Namit Katariya, Xavier Amatriain","submitted_at":"2021-09-09T18:32:56Z","abstract_excerpt":"In medical dialogue summarization, summaries must be coherent and must capture all the medically relevant information in the dialogue. However, learning effective models for summarization require large amounts of labeled data which is especially hard to obtain. We present an algorithm to create synthetic training data with an explicit focus on capturing medically relevant information. We utilize GPT-3 as the backbone of our algorithm and scale 210 human labeled examples to yield results comparable to using 6400 human labeled examples (~30x) leveraging low-shot learning and an ensemble method. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.07356","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/2110.07356/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":"2026-07-05T03:22:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lECvKK4L+Jnp/1GmzU/dBcXXct0JwGp+dV5eFVGbdY+l5CGLKRdH0hAm4/nFMRmlklzKvalognYe6kI201a0CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T03:31:37.085392Z"},"content_sha256":"b847d1b5248cc422b7eaac45d6a5dcac0b19df40c811d159a702123887d75197","schema_version":"1.0","event_id":"sha256:b847d1b5248cc422b7eaac45d6a5dcac0b19df40c811d159a702123887d75197"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QTS2I5ZE5TYLYKRJXR5OTM2VKP/bundle.json","state_url":"https://pith.science/pith/QTS2I5ZE5TYLYKRJXR5OTM2VKP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QTS2I5ZE5TYLYKRJXR5OTM2VKP/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":"2026-08-17T03:31:37Z","links":{"resolver":"https://pith.science/pith/QTS2I5ZE5TYLYKRJXR5OTM2VKP","bundle":"https://pith.science/pith/QTS2I5ZE5TYLYKRJXR5OTM2VKP/bundle.json","state":"https://pith.science/pith/QTS2I5ZE5TYLYKRJXR5OTM2VKP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QTS2I5ZE5TYLYKRJXR5OTM2VKP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:QTS2I5ZE5TYLYKRJXR5OTM2VKP","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":"6f0d34196ef208a1d6936ea2260dd3f7c75515f71e98737feadcb4860d9130b8","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-09T18:32:56Z","title_canon_sha256":"e3ca4e7a9c715c969816ea98effe7d64507f3c5c40eef23c4e3c4d3e8c37a776"},"schema_version":"1.0","source":{"id":"2110.07356","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.07356","created_at":"2026-07-05T03:22:41Z"},{"alias_kind":"arxiv_version","alias_value":"2110.07356v1","created_at":"2026-07-05T03:22:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.07356","created_at":"2026-07-05T03:22:41Z"},{"alias_kind":"pith_short_12","alias_value":"QTS2I5ZE5TYL","created_at":"2026-07-05T03:22:41Z"},{"alias_kind":"pith_short_16","alias_value":"QTS2I5ZE5TYLYKRJ","created_at":"2026-07-05T03:22:41Z"},{"alias_kind":"pith_short_8","alias_value":"QTS2I5ZE","created_at":"2026-07-05T03:22:41Z"}],"graph_snapshots":[{"event_id":"sha256:b847d1b5248cc422b7eaac45d6a5dcac0b19df40c811d159a702123887d75197","target":"graph","created_at":"2026-07-05T03:22:41Z","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/2110.07356/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In medical dialogue summarization, summaries must be coherent and must capture all the medically relevant information in the dialogue. However, learning effective models for summarization require large amounts of labeled data which is especially hard to obtain. We present an algorithm to create synthetic training data with an explicit focus on capturing medically relevant information. We utilize GPT-3 as the backbone of our algorithm and scale 210 human labeled examples to yield results comparable to using 6400 human labeled examples (~30x) leveraging low-shot learning and an ensemble method. ","authors_text":"Anitha Kannan, Bharath Chintagunta, Namit Katariya, Xavier Amatriain","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-09T18:32:56Z","title":"Medically Aware GPT-3 as a Data Generator for Medical Dialogue Summarization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.07356","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":"sha256:33338ed9407552a989476d4fb83368bb2e157186fc3bb39d3821e711e79f612b","target":"record","created_at":"2026-07-05T03:22:41Z","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":"6f0d34196ef208a1d6936ea2260dd3f7c75515f71e98737feadcb4860d9130b8","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-09T18:32:56Z","title_canon_sha256":"e3ca4e7a9c715c969816ea98effe7d64507f3c5c40eef23c4e3c4d3e8c37a776"},"schema_version":"1.0","source":{"id":"2110.07356","kind":"arxiv","version":1}},"canonical_sha256":"84e5a47724ecf0bc2a29bc7ae9b35553f5ce3b2abbb37b01de757cc3c01c1147","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"84e5a47724ecf0bc2a29bc7ae9b35553f5ce3b2abbb37b01de757cc3c01c1147","first_computed_at":"2026-07-05T03:22:41.205638Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:22:41.205638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zsn9JrZ2+lnkslCyypG0s8ABT8hVO7Hy/FKZ3i7o3BXMpDOxUCdso4tZSJgfP/Zqg5VaoSKlWIoygHWGt8ecBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:22:41.206013Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.07356","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:33338ed9407552a989476d4fb83368bb2e157186fc3bb39d3821e711e79f612b","sha256:b847d1b5248cc422b7eaac45d6a5dcac0b19df40c811d159a702123887d75197"],"state_sha256":"d77261382ec12269286ce80de41ebe24de9f31ecffc3c9e841b5d80272434387"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZAMtUr3qXxeXoR/xpIrhmQDuSNxnk6nRN+KNpqBPfkizKXLHsipmdOs0nUm0yHywaY4cxrlzBKstFWL2gm+IDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T03:31:37.090330Z","bundle_sha256":"f001b70842cfddddb1c1e05f96877686ddb2c7ff382ba9b687f54fe320ee12b7"}}