{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:6KKY5CM3FSL7BFVLHETLK3UVQ6","short_pith_number":"pith:6KKY5CM3","canonical_record":{"source":{"id":"2205.12689","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-25T11:49:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"be13c61ce8d8f94c6a4f3e7f5a849f34a11a58af1b1f02936e1b54c65f561b64","abstract_canon_sha256":"3f21df9d1a72a7ef224fff4e188db3880826144b3a9bdfa5dc8616d82c91e3a8"},"schema_version":"1.0"},"canonical_sha256":"f2958e899b2c97f096ab3926b56e95878104a7a558f8ddd5060a0264b00b83f3","source":{"kind":"arxiv","id":"2205.12689","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.12689","created_at":"2026-07-05T05:21:01Z"},{"alias_kind":"arxiv_version","alias_value":"2205.12689v2","created_at":"2026-07-05T05:21:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.12689","created_at":"2026-07-05T05:21:01Z"},{"alias_kind":"pith_short_12","alias_value":"6KKY5CM3FSL7","created_at":"2026-07-05T05:21:01Z"},{"alias_kind":"pith_short_16","alias_value":"6KKY5CM3FSL7BFVL","created_at":"2026-07-05T05:21:01Z"},{"alias_kind":"pith_short_8","alias_value":"6KKY5CM3","created_at":"2026-07-05T05:21:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:6KKY5CM3FSL7BFVLHETLK3UVQ6","target":"record","payload":{"canonical_record":{"source":{"id":"2205.12689","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-25T11:49:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"be13c61ce8d8f94c6a4f3e7f5a849f34a11a58af1b1f02936e1b54c65f561b64","abstract_canon_sha256":"3f21df9d1a72a7ef224fff4e188db3880826144b3a9bdfa5dc8616d82c91e3a8"},"schema_version":"1.0"},"canonical_sha256":"f2958e899b2c97f096ab3926b56e95878104a7a558f8ddd5060a0264b00b83f3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:21:01.361617Z","signature_b64":"JL9bEiVufcpyvPkUxSofcoLRcu0BCX75liJmmwayJuM88OmeiQ76J4h88QHq9MOC2HV3VaHo2tyeVXV8l9EQCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2958e899b2c97f096ab3926b56e95878104a7a558f8ddd5060a0264b00b83f3","last_reissued_at":"2026-07-05T05:21:01.361124Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:21:01.361124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.12689","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":"2026-07-05T05:21:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ezA5xbhcYRswLe9gyNWeDvQaW9VCaX2wqYQTqEVSFVXHEgoN+WtmZMFoh4U/AQw2VuyIow/WUFvMSRpMmcMUBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:57:14.002364Z"},"content_sha256":"433e36e3f6508908d21000c04962c88ed35ebd459c9a1357f2d06c6b5293fb6b","schema_version":"1.0","event_id":"sha256:433e36e3f6508908d21000c04962c88ed35ebd459c9a1357f2d06c6b5293fb6b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:6KKY5CM3FSL7BFVLHETLK3UVQ6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Language Models are Few-Shot Clinical Information Extractors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"David Sontag, Hunter Lang, Monica Agrawal, Stefan Hegselmann, Yoon Kim","submitted_at":"2022-05-25T11:49:58Z","abstract_excerpt":"A long-running goal of the clinical NLP community is the extraction of important variables trapped in clinical notes. However, roadblocks have included dataset shift from the general domain and a lack of public clinical corpora and annotations. In this work, we show that large language models, such as InstructGPT, perform well at zero- and few-shot information extraction from clinical text despite not being trained specifically for the clinical domain. Whereas text classification and generation performance have already been studied extensively in such models, here we additionally demonstrate h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.12689","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/2205.12689/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":"2026-07-05T05:21:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VtwMt9NRPR2LLBVorJkEzVzGSBGNV7cpSUeBvUSP1iT3hcFnlDHnJXgUEMU2Fa7wpFuAOg3cNHGsJBWO59CJBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:57:14.002871Z"},"content_sha256":"0718e10732e5455dcedc56e8254f5dce70cd2dada842242910d904c0b475d58c","schema_version":"1.0","event_id":"sha256:0718e10732e5455dcedc56e8254f5dce70cd2dada842242910d904c0b475d58c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6KKY5CM3FSL7BFVLHETLK3UVQ6/bundle.json","state_url":"https://pith.science/pith/6KKY5CM3FSL7BFVLHETLK3UVQ6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6KKY5CM3FSL7BFVLHETLK3UVQ6/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":"2026-08-03T15:57:14Z","links":{"resolver":"https://pith.science/pith/6KKY5CM3FSL7BFVLHETLK3UVQ6","bundle":"https://pith.science/pith/6KKY5CM3FSL7BFVLHETLK3UVQ6/bundle.json","state":"https://pith.science/pith/6KKY5CM3FSL7BFVLHETLK3UVQ6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6KKY5CM3FSL7BFVLHETLK3UVQ6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:6KKY5CM3FSL7BFVLHETLK3UVQ6","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":"3f21df9d1a72a7ef224fff4e188db3880826144b3a9bdfa5dc8616d82c91e3a8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-25T11:49:58Z","title_canon_sha256":"be13c61ce8d8f94c6a4f3e7f5a849f34a11a58af1b1f02936e1b54c65f561b64"},"schema_version":"1.0","source":{"id":"2205.12689","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.12689","created_at":"2026-07-05T05:21:01Z"},{"alias_kind":"arxiv_version","alias_value":"2205.12689v2","created_at":"2026-07-05T05:21:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.12689","created_at":"2026-07-05T05:21:01Z"},{"alias_kind":"pith_short_12","alias_value":"6KKY5CM3FSL7","created_at":"2026-07-05T05:21:01Z"},{"alias_kind":"pith_short_16","alias_value":"6KKY5CM3FSL7BFVL","created_at":"2026-07-05T05:21:01Z"},{"alias_kind":"pith_short_8","alias_value":"6KKY5CM3","created_at":"2026-07-05T05:21:01Z"}],"graph_snapshots":[{"event_id":"sha256:0718e10732e5455dcedc56e8254f5dce70cd2dada842242910d904c0b475d58c","target":"graph","created_at":"2026-07-05T05:21:01Z","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/2205.12689/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A long-running goal of the clinical NLP community is the extraction of important variables trapped in clinical notes. However, roadblocks have included dataset shift from the general domain and a lack of public clinical corpora and annotations. In this work, we show that large language models, such as InstructGPT, perform well at zero- and few-shot information extraction from clinical text despite not being trained specifically for the clinical domain. Whereas text classification and generation performance have already been studied extensively in such models, here we additionally demonstrate h","authors_text":"David Sontag, Hunter Lang, Monica Agrawal, Stefan Hegselmann, Yoon Kim","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-25T11:49:58Z","title":"Large Language Models are Few-Shot Clinical Information Extractors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.12689","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":"sha256:433e36e3f6508908d21000c04962c88ed35ebd459c9a1357f2d06c6b5293fb6b","target":"record","created_at":"2026-07-05T05:21:01Z","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":"3f21df9d1a72a7ef224fff4e188db3880826144b3a9bdfa5dc8616d82c91e3a8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-25T11:49:58Z","title_canon_sha256":"be13c61ce8d8f94c6a4f3e7f5a849f34a11a58af1b1f02936e1b54c65f561b64"},"schema_version":"1.0","source":{"id":"2205.12689","kind":"arxiv","version":2}},"canonical_sha256":"f2958e899b2c97f096ab3926b56e95878104a7a558f8ddd5060a0264b00b83f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f2958e899b2c97f096ab3926b56e95878104a7a558f8ddd5060a0264b00b83f3","first_computed_at":"2026-07-05T05:21:01.361124Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:21:01.361124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JL9bEiVufcpyvPkUxSofcoLRcu0BCX75liJmmwayJuM88OmeiQ76J4h88QHq9MOC2HV3VaHo2tyeVXV8l9EQCw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:21:01.361617Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.12689","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:433e36e3f6508908d21000c04962c88ed35ebd459c9a1357f2d06c6b5293fb6b","sha256:0718e10732e5455dcedc56e8254f5dce70cd2dada842242910d904c0b475d58c"],"state_sha256":"18cb2cdabf22f4e3117ec351d85327d62329460cb0c8a57c4dd336576d22578b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"odDsQ/+Mt6cf/KBPOIq5TyYHCWnkrHf4UVh66BaftWG0uzxKKPzj3vFQNHkDdBjnpszSnl1EvBmwpI5Zx93NAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T15:57:14.008126Z","bundle_sha256":"809aa42b82ce3f5f017877b3f17eddb6ca7da3d750a249e4366a245af360a432"}}