{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:CXL3WGPMZH4AJMN2WGI4H2FPMN","short_pith_number":"pith:CXL3WGPM","canonical_record":{"source":{"id":"2606.05003","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2026-06-03T15:20:15Z","cross_cats_sorted":[],"title_canon_sha256":"33512a4e4194b8f3322d904c54370609f3f48e10578607c37b90dcc0f093d890","abstract_canon_sha256":"626422f3c360249c4819ce8280428f2b5a844e02f17ea761a405ccda0e911047"},"schema_version":"1.0"},"canonical_sha256":"15d7bb19ecc9f804b1bab191c3e8af6341cc974309880c6657154cf8f46f9a38","source":{"kind":"arxiv","id":"2606.05003","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05003","created_at":"2026-06-04T01:10:01Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05003v1","created_at":"2026-06-04T01:10:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05003","created_at":"2026-06-04T01:10:01Z"},{"alias_kind":"pith_short_12","alias_value":"CXL3WGPMZH4A","created_at":"2026-06-04T01:10:01Z"},{"alias_kind":"pith_short_16","alias_value":"CXL3WGPMZH4AJMN2","created_at":"2026-06-04T01:10:01Z"},{"alias_kind":"pith_short_8","alias_value":"CXL3WGPM","created_at":"2026-06-04T01:10:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:CXL3WGPMZH4AJMN2WGI4H2FPMN","target":"record","payload":{"canonical_record":{"source":{"id":"2606.05003","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2026-06-03T15:20:15Z","cross_cats_sorted":[],"title_canon_sha256":"33512a4e4194b8f3322d904c54370609f3f48e10578607c37b90dcc0f093d890","abstract_canon_sha256":"626422f3c360249c4819ce8280428f2b5a844e02f17ea761a405ccda0e911047"},"schema_version":"1.0"},"canonical_sha256":"15d7bb19ecc9f804b1bab191c3e8af6341cc974309880c6657154cf8f46f9a38","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:10:01.065270Z","signature_b64":"FRI4q1Cj1a4Y2BKeDdLnQeIgi7aPwJjBIK6WSPv3MQcJKRymw8syvRDwAzce+OS0/6hG/6A8IZQwc76l+T5SCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15d7bb19ecc9f804b1bab191c3e8af6341cc974309880c6657154cf8f46f9a38","last_reissued_at":"2026-06-04T01:10:01.064113Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:10:01.064113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.05003","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":"2026-06-04T01:10:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"THzB6VgnvJ1manwcyJuDG0Rdj5GFtAT182piDp8/te/ARy7XSYWtQpFy2aPQsClaNsoR3OeZV+GLqjwIGQp7BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T15:38:24.914250Z"},"content_sha256":"840717dad254ba53bd16ff9b0bf7de376556431d1722f4d2828659665f0f4157","schema_version":"1.0","event_id":"sha256:840717dad254ba53bd16ff9b0bf7de376556431d1722f4d2828659665f0f4157"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:CXL3WGPMZH4AJMN2WGI4H2FPMN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PhysDox: Benchmarking LLMs on Physical Feasibility Auditing of Physiological Sensing Protocols","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Boyuan Gu, Haiyang Sun, He Liu, Shuaiqi Cheng, Siyu You, Xuming Hu","submitted_at":"2026-06-03T15:20:15Z","abstract_excerpt":"Large language models (LLMs) increasingly assist in experimental design, yet fluent protocols often remain physically infeasible. We introduce PhysDox, a physical feasibility auditing benchmark for biomedical protocols comprising a 683-sample expert-curated Gold set and a 5,000-sample Silver set across six sensing domains. We formulate the task as a two-stage evaluation: severity detection classifying protocols as valid, minor, or fatal, followed by the constraint-level diagnosis of fatal violations. Evaluating 6 LLMs across 4 inference strategies yields a peak Stage-1 macro-F1 of only 53.0. M"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05003","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/2606.05003/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":"2026-06-04T01:10:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bMGRKkE3wNVDArnipgbQF9WOjMHZxpLLbr7KxsgcPM1u9MY2zkEvN9DtKmF0ABVBwP5/ZwNK+tIgr06QmgapDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T15:38:24.915008Z"},"content_sha256":"ba61bad7e8db08f0afd2d9b567ba8496d972e605d036a9a9e4af6963b802f66b","schema_version":"1.0","event_id":"sha256:ba61bad7e8db08f0afd2d9b567ba8496d972e605d036a9a9e4af6963b802f66b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CXL3WGPMZH4AJMN2WGI4H2FPMN/bundle.json","state_url":"https://pith.science/pith/CXL3WGPMZH4AJMN2WGI4H2FPMN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CXL3WGPMZH4AJMN2WGI4H2FPMN/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":"2026-06-08T15:38:24Z","links":{"resolver":"https://pith.science/pith/CXL3WGPMZH4AJMN2WGI4H2FPMN","bundle":"https://pith.science/pith/CXL3WGPMZH4AJMN2WGI4H2FPMN/bundle.json","state":"https://pith.science/pith/CXL3WGPMZH4AJMN2WGI4H2FPMN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CXL3WGPMZH4AJMN2WGI4H2FPMN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CXL3WGPMZH4AJMN2WGI4H2FPMN","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":"626422f3c360249c4819ce8280428f2b5a844e02f17ea761a405ccda0e911047","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2026-06-03T15:20:15Z","title_canon_sha256":"33512a4e4194b8f3322d904c54370609f3f48e10578607c37b90dcc0f093d890"},"schema_version":"1.0","source":{"id":"2606.05003","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05003","created_at":"2026-06-04T01:10:01Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05003v1","created_at":"2026-06-04T01:10:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05003","created_at":"2026-06-04T01:10:01Z"},{"alias_kind":"pith_short_12","alias_value":"CXL3WGPMZH4A","created_at":"2026-06-04T01:10:01Z"},{"alias_kind":"pith_short_16","alias_value":"CXL3WGPMZH4AJMN2","created_at":"2026-06-04T01:10:01Z"},{"alias_kind":"pith_short_8","alias_value":"CXL3WGPM","created_at":"2026-06-04T01:10:01Z"}],"graph_snapshots":[{"event_id":"sha256:ba61bad7e8db08f0afd2d9b567ba8496d972e605d036a9a9e4af6963b802f66b","target":"graph","created_at":"2026-06-04T01:10:01Z","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/2606.05003/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) increasingly assist in experimental design, yet fluent protocols often remain physically infeasible. We introduce PhysDox, a physical feasibility auditing benchmark for biomedical protocols comprising a 683-sample expert-curated Gold set and a 5,000-sample Silver set across six sensing domains. We formulate the task as a two-stage evaluation: severity detection classifying protocols as valid, minor, or fatal, followed by the constraint-level diagnosis of fatal violations. Evaluating 6 LLMs across 4 inference strategies yields a peak Stage-1 macro-F1 of only 53.0. M","authors_text":"Boyuan Gu, Haiyang Sun, He Liu, Shuaiqi Cheng, Siyu You, Xuming Hu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2026-06-03T15:20:15Z","title":"PhysDox: Benchmarking LLMs on Physical Feasibility Auditing of Physiological Sensing Protocols"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05003","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":"sha256:840717dad254ba53bd16ff9b0bf7de376556431d1722f4d2828659665f0f4157","target":"record","created_at":"2026-06-04T01:10:01Z","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":"626422f3c360249c4819ce8280428f2b5a844e02f17ea761a405ccda0e911047","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2026-06-03T15:20:15Z","title_canon_sha256":"33512a4e4194b8f3322d904c54370609f3f48e10578607c37b90dcc0f093d890"},"schema_version":"1.0","source":{"id":"2606.05003","kind":"arxiv","version":1}},"canonical_sha256":"15d7bb19ecc9f804b1bab191c3e8af6341cc974309880c6657154cf8f46f9a38","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15d7bb19ecc9f804b1bab191c3e8af6341cc974309880c6657154cf8f46f9a38","first_computed_at":"2026-06-04T01:10:01.064113Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:10:01.064113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FRI4q1Cj1a4Y2BKeDdLnQeIgi7aPwJjBIK6WSPv3MQcJKRymw8syvRDwAzce+OS0/6hG/6A8IZQwc76l+T5SCA==","signature_status":"signed_v1","signed_at":"2026-06-04T01:10:01.065270Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05003","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:840717dad254ba53bd16ff9b0bf7de376556431d1722f4d2828659665f0f4157","sha256:ba61bad7e8db08f0afd2d9b567ba8496d972e605d036a9a9e4af6963b802f66b"],"state_sha256":"661fdf77736e8df7dc71bc078529abe36d83e44ed60301997cba370a828fa648"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rHJSHnSMOGSnnu3kuy46zmCFLfi57Fb6IYYmkgG0akGmlPTJCuQ55NdHGdCSIdHS9W8cYLpN9D+ejN8v3F6YDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T15:38:24.918889Z","bundle_sha256":"c4914300dd337a61c59a84056ceb66df6cf980e82b719522ec7c2df1e28451e7"}}