{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:CGHDYSAHUYW2JMKCBYUP4DRPMX","short_pith_number":"pith:CGHDYSAH","canonical_record":{"source":{"id":"2605.15467","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T23:13:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"482151a2ab80529a188b5715f43911a7643f0dcbb7ebe8ebc6afe9b938365c42","abstract_canon_sha256":"e0e00ec6e4c07ba565efa608336d1d5aa239e52aa1869561a3e75d5920b7b8d4"},"schema_version":"1.0"},"canonical_sha256":"118e3c4807a62da4b1420e28fe0e2f65f06037753acbd26f17eff99864afbac8","source":{"kind":"arxiv","id":"2605.15467","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15467","created_at":"2026-05-20T00:01:00Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15467v1","created_at":"2026-05-20T00:01:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15467","created_at":"2026-05-20T00:01:00Z"},{"alias_kind":"pith_short_12","alias_value":"CGHDYSAHUYW2","created_at":"2026-05-20T00:01:00Z"},{"alias_kind":"pith_short_16","alias_value":"CGHDYSAHUYW2JMKC","created_at":"2026-05-20T00:01:00Z"},{"alias_kind":"pith_short_8","alias_value":"CGHDYSAH","created_at":"2026-05-20T00:01:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:CGHDYSAHUYW2JMKCBYUP4DRPMX","target":"record","payload":{"canonical_record":{"source":{"id":"2605.15467","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T23:13:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"482151a2ab80529a188b5715f43911a7643f0dcbb7ebe8ebc6afe9b938365c42","abstract_canon_sha256":"e0e00ec6e4c07ba565efa608336d1d5aa239e52aa1869561a3e75d5920b7b8d4"},"schema_version":"1.0"},"canonical_sha256":"118e3c4807a62da4b1420e28fe0e2f65f06037753acbd26f17eff99864afbac8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:00.096951Z","signature_b64":"IgdKEnLNwORwKSIMGPbB85fXSDjz8ZGYu8lHepj/EzIzW9LRP7YmfMAiVSJ0rtrnZcI+ChzOjiWvR9I16A8nCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"118e3c4807a62da4b1420e28fe0e2f65f06037753acbd26f17eff99864afbac8","last_reissued_at":"2026-05-20T00:01:00.096241Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:00.096241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.15467","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":"2026-05-20T00:01:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8OfDJ4QUOJdEW8OgygEWuk1+UxAFOnQXNxXTBChHqCPluqaB1vfLLQ1sjLF0txc+meTown9LjfBld8r8hXIEAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T04:20:28.814622Z"},"content_sha256":"4d32fbe92a5b7a55bb28766cd05ee807075379c7a3e36aabb93b56f79238adbf","schema_version":"1.0","event_id":"sha256:4d32fbe92a5b7a55bb28766cd05ee807075379c7a3e36aabb93b56f79238adbf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:CGHDYSAHUYW2JMKCBYUP4DRPMX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Retrieval-Augmented Large Language Models for Schema-Constrained Clinical Information Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A retrieval-augmented pipeline with schema-constrained prompts extracts structured clinical observations from transcripts at 80.36 percent F1.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"A H M Rezaul Karim, Ozlem Uzuner","submitted_at":"2026-05-14T23:13:05Z","abstract_excerpt":"Conversational nurse-patient transcripts contain actionable observations, but converting these transcripts into structured representations at scale remains challenging. Documentation burden is substantial, with prior studies showing clinicians spend large portions of their workday on documentation and related desk work rather than direct patient care. MEDIQA-SYNUR focuses on observation extraction from conversational nurse-patient transcripts, requiring systems to normalize these narratives into a predefined schema with value-type constraints. We propose a modular retrieval-augmented generatio"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our best configuration uses GPT-5.2 with full schema, RAG, and a second-pass auditing, achieving 80.36% F1 score. Overall, our results show that RAG consistently improves performance, while the optimal degree of schema constraint depends on the model, and second-pass auditing yields modest additional gains by correcting residual schema-adherence errors.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The training set can serve as an effective exemplar corpus for retrieval that meaningfully improves the model's ability to produce schema-adherent outputs when combined with prompting and post-processing.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A modular RAG pipeline with schema-constrained prompting, deterministic post-processing, and second-pass auditing reaches 80.36% F1 on observation extraction from nurse-patient transcripts using GPT-5.2.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A retrieval-augmented pipeline with schema-constrained prompts extracts structured clinical observations from transcripts at 80.36 percent F1.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"198542f5504c423eec9d74d0ff6d450a1f13996ca33e564ac9b47213deb0ac56"},"source":{"id":"2605.15467","kind":"arxiv","version":1},"verdict":{"id":"3caedaa6-c236-41c2-816b-17c280b2ffe2","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T14:33:37.610108Z","strongest_claim":"Our best configuration uses GPT-5.2 with full schema, RAG, and a second-pass auditing, achieving 80.36% F1 score. Overall, our results show that RAG consistently improves performance, while the optimal degree of schema constraint depends on the model, and second-pass auditing yields modest additional gains by correcting residual schema-adherence errors.","one_line_summary":"A modular RAG pipeline with schema-constrained prompting, deterministic post-processing, and second-pass auditing reaches 80.36% F1 on observation extraction from nurse-patient transcripts using GPT-5.2.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The training set can serve as an effective exemplar corpus for retrieval that meaningfully improves the model's ability to produce schema-adherent outputs when combined with prompting and post-processing.","pith_extraction_headline":"A retrieval-augmented pipeline with schema-constrained prompts extracts structured clinical observations from transcripts at 80.36 percent F1."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15467/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"cited_work_retraction","ran_at":"2026-05-19T15:22:27.215273Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T15:01:17.592726Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T14:49:59.373697Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T14:21:54.091978Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"citation_quote_validity","ran_at":"2026-05-19T13:49:41.413208Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.665807Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"3a4ec63fa048280ba2f1885346d995002f54130e6db809451a1a7f7bd17c217f"},"references":{"count":38,"sample":[{"doi":"","year":2011,"title":"Catalan Speecon database","work_id":"e825f578-5024-46c6-96cc-0be9929215b5","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2004,"title":"The EMILLE/CIIL Corpus","work_id":"e5746524-edbb-487b-910b-7618b5cb0508","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2004,"title":"The OrienTel Moroccan MCA (Modern Colloquial Arabic) database","work_id":"4980f97c-33c0-41e0-8f04-9907e5ee6077","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"ItalWordNet v.2","work_id":"eb1afe4c-a2b1-47a3-9112-5facc420b451","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Advances in neural information processing systems , volume=","work_id":"27180506-faab-44b1-9295-6bf5eb791eed","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":38,"snapshot_sha256":"6624ab5197220560db4bf82faa2c1999098bb6be8445bb96f6011a98aa9e7fe7","internal_anchors":0},"formal_canon":{"evidence_count":1,"snapshot_sha256":"580aa5f392bb2864df00564ed872432317d218a56f825617f15464f230c7597a"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"3caedaa6-c236-41c2-816b-17c280b2ffe2"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:01:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4CP5/lQgC8se3mNW3TDMJ0/o+gCEEsFozY3qzcEahapAbJdKcniv7aATdbSYgFu17ZOnkxEwZCCrlCZGtcUyBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T04:20:28.815251Z"},"content_sha256":"47d63217d824eb56b9b896ce9d0eb8c1b2e6fa4d628737688d23bfcdf9f3ce10","schema_version":"1.0","event_id":"sha256:47d63217d824eb56b9b896ce9d0eb8c1b2e6fa4d628737688d23bfcdf9f3ce10"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CGHDYSAHUYW2JMKCBYUP4DRPMX/bundle.json","state_url":"https://pith.science/pith/CGHDYSAHUYW2JMKCBYUP4DRPMX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CGHDYSAHUYW2JMKCBYUP4DRPMX/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":"2026-06-02T04:20:28Z","links":{"resolver":"https://pith.science/pith/CGHDYSAHUYW2JMKCBYUP4DRPMX","bundle":"https://pith.science/pith/CGHDYSAHUYW2JMKCBYUP4DRPMX/bundle.json","state":"https://pith.science/pith/CGHDYSAHUYW2JMKCBYUP4DRPMX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CGHDYSAHUYW2JMKCBYUP4DRPMX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CGHDYSAHUYW2JMKCBYUP4DRPMX","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":"e0e00ec6e4c07ba565efa608336d1d5aa239e52aa1869561a3e75d5920b7b8d4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T23:13:05Z","title_canon_sha256":"482151a2ab80529a188b5715f43911a7643f0dcbb7ebe8ebc6afe9b938365c42"},"schema_version":"1.0","source":{"id":"2605.15467","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15467","created_at":"2026-05-20T00:01:00Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15467v1","created_at":"2026-05-20T00:01:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15467","created_at":"2026-05-20T00:01:00Z"},{"alias_kind":"pith_short_12","alias_value":"CGHDYSAHUYW2","created_at":"2026-05-20T00:01:00Z"},{"alias_kind":"pith_short_16","alias_value":"CGHDYSAHUYW2JMKC","created_at":"2026-05-20T00:01:00Z"},{"alias_kind":"pith_short_8","alias_value":"CGHDYSAH","created_at":"2026-05-20T00:01:00Z"}],"graph_snapshots":[{"event_id":"sha256:47d63217d824eb56b9b896ce9d0eb8c1b2e6fa4d628737688d23bfcdf9f3ce10","target":"graph","created_at":"2026-05-20T00:01:00Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Our best configuration uses GPT-5.2 with full schema, RAG, and a second-pass auditing, achieving 80.36% F1 score. Overall, our results show that RAG consistently improves performance, while the optimal degree of schema constraint depends on the model, and second-pass auditing yields modest additional gains by correcting residual schema-adherence errors."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The training set can serve as an effective exemplar corpus for retrieval that meaningfully improves the model's ability to produce schema-adherent outputs when combined with prompting and post-processing."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A modular RAG pipeline with schema-constrained prompting, deterministic post-processing, and second-pass auditing reaches 80.36% F1 on observation extraction from nurse-patient transcripts using GPT-5.2."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A retrieval-augmented pipeline with schema-constrained prompts extracts structured clinical observations from transcripts at 80.36 percent F1."}],"snapshot_sha256":"198542f5504c423eec9d74d0ff6d450a1f13996ca33e564ac9b47213deb0ac56"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"580aa5f392bb2864df00564ed872432317d218a56f825617f15464f230c7597a"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"cited_work_retraction","ran_at":"2026-05-19T15:22:27.215273Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T15:01:17.592726Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T14:49:59.373697Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T14:21:54.091978Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"citation_quote_validity","ran_at":"2026-05-19T13:49:41.413208Z","status":"skipped","version":"0.1.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.665807Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.15467/integrity.json","findings":[],"snapshot_sha256":"3a4ec63fa048280ba2f1885346d995002f54130e6db809451a1a7f7bd17c217f","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Conversational nurse-patient transcripts contain actionable observations, but converting these transcripts into structured representations at scale remains challenging. Documentation burden is substantial, with prior studies showing clinicians spend large portions of their workday on documentation and related desk work rather than direct patient care. MEDIQA-SYNUR focuses on observation extraction from conversational nurse-patient transcripts, requiring systems to normalize these narratives into a predefined schema with value-type constraints. We propose a modular retrieval-augmented generatio","authors_text":"A H M Rezaul Karim, Ozlem Uzuner","cross_cats":["cs.AI"],"headline":"A retrieval-augmented pipeline with schema-constrained prompts extracts structured clinical observations from transcripts at 80.36 percent F1.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T23:13:05Z","title":"Retrieval-Augmented Large Language Models for Schema-Constrained Clinical Information Extraction"},"references":{"count":38,"internal_anchors":0,"resolved_work":38,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Catalan Speecon database","work_id":"e825f578-5024-46c6-96cc-0be9929215b5","year":2011},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"The EMILLE/CIIL Corpus","work_id":"e5746524-edbb-487b-910b-7618b5cb0508","year":2004},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"The OrienTel Moroccan MCA (Modern Colloquial Arabic) database","work_id":"4980f97c-33c0-41e0-8f04-9907e5ee6077","year":2004},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"ItalWordNet v.2","work_id":"eb1afe4c-a2b1-47a3-9112-5facc420b451","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Advances in neural information processing systems , volume=","work_id":"27180506-faab-44b1-9295-6bf5eb791eed","year":null}],"snapshot_sha256":"6624ab5197220560db4bf82faa2c1999098bb6be8445bb96f6011a98aa9e7fe7"},"source":{"id":"2605.15467","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T14:33:37.610108Z","id":"3caedaa6-c236-41c2-816b-17c280b2ffe2","model_set":{"reader":"grok-4.3"},"one_line_summary":"A modular RAG pipeline with schema-constrained prompting, deterministic post-processing, and second-pass auditing reaches 80.36% F1 on observation extraction from nurse-patient transcripts using GPT-5.2.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A retrieval-augmented pipeline with schema-constrained prompts extracts structured clinical observations from transcripts at 80.36 percent F1.","strongest_claim":"Our best configuration uses GPT-5.2 with full schema, RAG, and a second-pass auditing, achieving 80.36% F1 score. Overall, our results show that RAG consistently improves performance, while the optimal degree of schema constraint depends on the model, and second-pass auditing yields modest additional gains by correcting residual schema-adherence errors.","weakest_assumption":"The training set can serve as an effective exemplar corpus for retrieval that meaningfully improves the model's ability to produce schema-adherent outputs when combined with prompting and post-processing."}},"verdict_id":"3caedaa6-c236-41c2-816b-17c280b2ffe2"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4d32fbe92a5b7a55bb28766cd05ee807075379c7a3e36aabb93b56f79238adbf","target":"record","created_at":"2026-05-20T00:01:00Z","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":"e0e00ec6e4c07ba565efa608336d1d5aa239e52aa1869561a3e75d5920b7b8d4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T23:13:05Z","title_canon_sha256":"482151a2ab80529a188b5715f43911a7643f0dcbb7ebe8ebc6afe9b938365c42"},"schema_version":"1.0","source":{"id":"2605.15467","kind":"arxiv","version":1}},"canonical_sha256":"118e3c4807a62da4b1420e28fe0e2f65f06037753acbd26f17eff99864afbac8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"118e3c4807a62da4b1420e28fe0e2f65f06037753acbd26f17eff99864afbac8","first_computed_at":"2026-05-20T00:01:00.096241Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:01:00.096241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IgdKEnLNwORwKSIMGPbB85fXSDjz8ZGYu8lHepj/EzIzW9LRP7YmfMAiVSJ0rtrnZcI+ChzOjiWvR9I16A8nCw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:01:00.096951Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15467","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4d32fbe92a5b7a55bb28766cd05ee807075379c7a3e36aabb93b56f79238adbf","sha256:47d63217d824eb56b9b896ce9d0eb8c1b2e6fa4d628737688d23bfcdf9f3ce10"],"state_sha256":"559562872e48b504e3f48404305fd28b71fdf5c99f349b84c5695dd8d9af4e8f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s5kBJLynIccyZPBWm/F8mPMuXBehDNk/1o6zA7f/fpY0xCQ7A+GflcIg5yp/GrxMs2wluRPpFX7TZAQFdIq8Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T04:20:28.818268Z","bundle_sha256":"de0a50a6a463202ca2dfc9d3fcf8be2d1a01e8a7aaaffd874953f8aab275cd9f"}}