{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:PPCZJQ2AF3RGKUQPFFSDBPWUTQ","short_pith_number":"pith:PPCZJQ2A","canonical_record":{"source":{"id":"2606.31608","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-30T12:56:42Z","cross_cats_sorted":[],"title_canon_sha256":"1375ef3bbd355403ae2a92978dd8b9543a6ad5a82f89c88acbbd0b4cae90af90","abstract_canon_sha256":"8ab4b1f5e447f14f639de8a573798cdf3025404d3f4650d34b8249edb3b922ba"},"schema_version":"1.0"},"canonical_sha256":"7bc594c3402ee265520f296430bed49c1445bd9adf8a3e874b691f7318194de8","source":{"kind":"arxiv","id":"2606.31608","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.31608","created_at":"2026-07-01T01:18:09Z"},{"alias_kind":"arxiv_version","alias_value":"2606.31608v1","created_at":"2026-07-01T01:18:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31608","created_at":"2026-07-01T01:18:09Z"},{"alias_kind":"pith_short_12","alias_value":"PPCZJQ2AF3RG","created_at":"2026-07-01T01:18:09Z"},{"alias_kind":"pith_short_16","alias_value":"PPCZJQ2AF3RGKUQP","created_at":"2026-07-01T01:18:09Z"},{"alias_kind":"pith_short_8","alias_value":"PPCZJQ2A","created_at":"2026-07-01T01:18:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:PPCZJQ2AF3RGKUQPFFSDBPWUTQ","target":"record","payload":{"canonical_record":{"source":{"id":"2606.31608","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-30T12:56:42Z","cross_cats_sorted":[],"title_canon_sha256":"1375ef3bbd355403ae2a92978dd8b9543a6ad5a82f89c88acbbd0b4cae90af90","abstract_canon_sha256":"8ab4b1f5e447f14f639de8a573798cdf3025404d3f4650d34b8249edb3b922ba"},"schema_version":"1.0"},"canonical_sha256":"7bc594c3402ee265520f296430bed49c1445bd9adf8a3e874b691f7318194de8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:18:09.070107Z","signature_b64":"a0ithBHA7QogV3vco2C6PNj1iqMnvfQAOFAMvDKy42jdk0ZoEeykD+YFvdKORduFzgUQTVvnUSVovyyJhX6TCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7bc594c3402ee265520f296430bed49c1445bd9adf8a3e874b691f7318194de8","last_reissued_at":"2026-07-01T01:18:09.069609Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:18:09.069609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.31608","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":"2026-07-01T01:18:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YFW1XjSXMSrZzpHS/Hit0Z8/acAQytrez6wJotE4zVUILvK9FszNzFmPHxfGCdB1Usslp2/kk+eBdWEMWU/JAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T07:49:30.323683Z"},"content_sha256":"2aa2972c2c2ce90d63324b8e482aca5bba14549f1774738c2db9464acee3b18a","schema_version":"1.0","event_id":"sha256:2aa2972c2c2ce90d63324b8e482aca5bba14549f1774738c2db9464acee3b18a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:PPCZJQ2AF3RGKUQPFFSDBPWUTQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CLExEval: A Human-in-the-Loop Framework for Qualitative Evaluation of LLM Clinical Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abin Roy, Afthab Salam Kanniyan, Ajmal M., Jawadh Abdul Kabeer, Jerin James, Preslav Nakov, Zhuohan Xie","submitted_at":"2026-06-30T12:56:42Z","abstract_excerpt":"Large Language Models (LLMs) achieve strong results on many medical benchmarks, but their clinical reasoning remains difficult to evaluate reliably. A central risk is an evaluation illusion: fluent and well-structured explanations can appear clinically convincing even when the final diagnosis is incorrect. We introduce CLExEval, a human-in-the-loop framework for evaluating LLM clinical reasoning under progressive information masking. CLExEval combines 5,600 expert-physician annotations with 200 clinical reasoning traces derived from 40 rare diagnostic cases. Our analysis identifies three recur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31608","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/2606.31608/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":"2026-07-01T01:18:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B1KxZqt9qbPF+jFnAsPy7Ondd+c1DNRCxT7eYAbe3W3SeIfJlCPIAfECxFxxKjMOgwp2y2YeH7CVdgL4YApxDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T07:49:30.324069Z"},"content_sha256":"33a91cbacdccd8eea5297616e53b578a83cba2466eb3feb6fcf5d4c31202cab7","schema_version":"1.0","event_id":"sha256:33a91cbacdccd8eea5297616e53b578a83cba2466eb3feb6fcf5d4c31202cab7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PPCZJQ2AF3RGKUQPFFSDBPWUTQ/bundle.json","state_url":"https://pith.science/pith/PPCZJQ2AF3RGKUQPFFSDBPWUTQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PPCZJQ2AF3RGKUQPFFSDBPWUTQ/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":"2026-07-02T07:49:30Z","links":{"resolver":"https://pith.science/pith/PPCZJQ2AF3RGKUQPFFSDBPWUTQ","bundle":"https://pith.science/pith/PPCZJQ2AF3RGKUQPFFSDBPWUTQ/bundle.json","state":"https://pith.science/pith/PPCZJQ2AF3RGKUQPFFSDBPWUTQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PPCZJQ2AF3RGKUQPFFSDBPWUTQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PPCZJQ2AF3RGKUQPFFSDBPWUTQ","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":"8ab4b1f5e447f14f639de8a573798cdf3025404d3f4650d34b8249edb3b922ba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-30T12:56:42Z","title_canon_sha256":"1375ef3bbd355403ae2a92978dd8b9543a6ad5a82f89c88acbbd0b4cae90af90"},"schema_version":"1.0","source":{"id":"2606.31608","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.31608","created_at":"2026-07-01T01:18:09Z"},{"alias_kind":"arxiv_version","alias_value":"2606.31608v1","created_at":"2026-07-01T01:18:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31608","created_at":"2026-07-01T01:18:09Z"},{"alias_kind":"pith_short_12","alias_value":"PPCZJQ2AF3RG","created_at":"2026-07-01T01:18:09Z"},{"alias_kind":"pith_short_16","alias_value":"PPCZJQ2AF3RGKUQP","created_at":"2026-07-01T01:18:09Z"},{"alias_kind":"pith_short_8","alias_value":"PPCZJQ2A","created_at":"2026-07-01T01:18:09Z"}],"graph_snapshots":[{"event_id":"sha256:33a91cbacdccd8eea5297616e53b578a83cba2466eb3feb6fcf5d4c31202cab7","target":"graph","created_at":"2026-07-01T01:18:09Z","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/2606.31608/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) achieve strong results on many medical benchmarks, but their clinical reasoning remains difficult to evaluate reliably. A central risk is an evaluation illusion: fluent and well-structured explanations can appear clinically convincing even when the final diagnosis is incorrect. We introduce CLExEval, a human-in-the-loop framework for evaluating LLM clinical reasoning under progressive information masking. CLExEval combines 5,600 expert-physician annotations with 200 clinical reasoning traces derived from 40 rare diagnostic cases. Our analysis identifies three recur","authors_text":"Abin Roy, Afthab Salam Kanniyan, Ajmal M., Jawadh Abdul Kabeer, Jerin James, Preslav Nakov, Zhuohan Xie","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-30T12:56:42Z","title":"CLExEval: A Human-in-the-Loop Framework for Qualitative Evaluation of LLM Clinical Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31608","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":"sha256:2aa2972c2c2ce90d63324b8e482aca5bba14549f1774738c2db9464acee3b18a","target":"record","created_at":"2026-07-01T01:18:09Z","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":"8ab4b1f5e447f14f639de8a573798cdf3025404d3f4650d34b8249edb3b922ba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-30T12:56:42Z","title_canon_sha256":"1375ef3bbd355403ae2a92978dd8b9543a6ad5a82f89c88acbbd0b4cae90af90"},"schema_version":"1.0","source":{"id":"2606.31608","kind":"arxiv","version":1}},"canonical_sha256":"7bc594c3402ee265520f296430bed49c1445bd9adf8a3e874b691f7318194de8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7bc594c3402ee265520f296430bed49c1445bd9adf8a3e874b691f7318194de8","first_computed_at":"2026-07-01T01:18:09.069609Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T01:18:09.069609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a0ithBHA7QogV3vco2C6PNj1iqMnvfQAOFAMvDKy42jdk0ZoEeykD+YFvdKORduFzgUQTVvnUSVovyyJhX6TCg==","signature_status":"signed_v1","signed_at":"2026-07-01T01:18:09.070107Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.31608","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2aa2972c2c2ce90d63324b8e482aca5bba14549f1774738c2db9464acee3b18a","sha256:33a91cbacdccd8eea5297616e53b578a83cba2466eb3feb6fcf5d4c31202cab7"],"state_sha256":"0d4a6dc98057739fc38d1a673927b703033b8d73ed00cb545c041f6f74741111"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lb9xxnxM3J9E+E7poIa7iy+2VzBFRT72E5PRBuKVd5dBBdwlzfkcZDCznAqNGR5A2Gp1Yh9U5GHdc4aDET0oBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T07:49:30.326117Z","bundle_sha256":"3d099dfd774224504437e329ed5daf7da7e8227a2b26cdfff5b83db3e2bfc206"}}