{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:OXIZ7PF3FWML7KNKG7EP6HTHMI","short_pith_number":"pith:OXIZ7PF3","canonical_record":{"source":{"id":"2605.10181","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-11T08:32:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"354af016f93a95670271a6186eee09f310676f21dae4129d8f8cd814b3ba609a","abstract_canon_sha256":"cf08ffc2b4c3a4516a812b309d0ccea42f55eef35cef7c2481247e75d7890d3e"},"schema_version":"1.0"},"canonical_sha256":"75d19fbcbb2d98bfa9aa37c8ff1e67620ada1cf3c8466d0ca53d54483133c472","source":{"kind":"arxiv","id":"2605.10181","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.10181","created_at":"2026-05-21T01:05:20Z"},{"alias_kind":"arxiv_version","alias_value":"2605.10181v2","created_at":"2026-05-21T01:05:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.10181","created_at":"2026-05-21T01:05:20Z"},{"alias_kind":"pith_short_12","alias_value":"OXIZ7PF3FWML","created_at":"2026-05-21T01:05:20Z"},{"alias_kind":"pith_short_16","alias_value":"OXIZ7PF3FWML7KNK","created_at":"2026-05-21T01:05:20Z"},{"alias_kind":"pith_short_8","alias_value":"OXIZ7PF3","created_at":"2026-05-21T01:05:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:OXIZ7PF3FWML7KNKG7EP6HTHMI","target":"record","payload":{"canonical_record":{"source":{"id":"2605.10181","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-11T08:32:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"354af016f93a95670271a6186eee09f310676f21dae4129d8f8cd814b3ba609a","abstract_canon_sha256":"cf08ffc2b4c3a4516a812b309d0ccea42f55eef35cef7c2481247e75d7890d3e"},"schema_version":"1.0"},"canonical_sha256":"75d19fbcbb2d98bfa9aa37c8ff1e67620ada1cf3c8466d0ca53d54483133c472","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:05:20.933493Z","signature_b64":"tTVSkXAl7sJMvc68i9+nq95Hed/MgyWa9J+iD6rww5WwdxdBkWWbnU/QK0QvIAoB/96sIqzZmx1Iu6xQZ52/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75d19fbcbb2d98bfa9aa37c8ff1e67620ada1cf3c8466d0ca53d54483133c472","last_reissued_at":"2026-05-21T01:05:20.932974Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:05:20.932974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.10181","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":"2026-05-21T01:05:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tYEbXOAAoOGmnKPV2K5dH5brJtYnCxg3GFxMmecsb058mBTxA8XzYhae3O/J2DODZbmVFkjMccv3Ld+8989jAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T19:59:07.329938Z"},"content_sha256":"5fad04ef4e86e5993bcc2e4f4d99f79b37833b3ced6825b312d1c4c5e00f788b","schema_version":"1.0","event_id":"sha256:5fad04ef4e86e5993bcc2e4f4d99f79b37833b3ced6825b312d1c4c5e00f788b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:OXIZ7PF3FWML7KNKG7EP6HTHMI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Comparative Study of Machine Learning and Deep Learning for Out-of-Distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Machine learning matches deep learning performance for out-of-distribution detection in medical images but with substantially lower latency.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Doohyun Park, Gitaek Kwon, Jihyeon Baek, Seunghoon Lee","submitted_at":"2026-05-11T08:32:50Z","abstract_excerpt":"Out-of-distribution (OOD) detection is essential for building reliable AI systems, as models that produce outputs for invalid inputs cannot be trusted. Although deep learning (DL) is often assumed to outperform traditional machine learning (ML), medical imaging data are typically acquired under standardized protocols, leading to relatively constrained image variability in OOD detection tasks. This motivates a direct comparison between ML and DL approaches in this setting. The two approaches are evaluated on open datasets comprising over 60,000 fundus and non-fundus images across multiple resol"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Both approaches achieved an AUROC of 1.000 and accuracies between 0.999 and 1.000 on internal and external validation sets, showing comparable detection performance. The ML approach, however, exhibited substantially lower end-to-end latency while maintaining equivalent accuracy.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"Medical imaging data acquired under standardized protocols exhibit limited image variability, allowing lightweight ML methods to achieve performance comparable to DL in OOD detection tasks.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ML matches DL in OOD detection accuracy for medical images but with substantially lower latency.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Machine learning matches deep learning performance for out-of-distribution detection in medical images but with substantially lower latency.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d765ace8fe849dcfd2fb2bd0abe2d1b335e534186f36294e45a4ebabf0bc7a60"},"source":{"id":"2605.10181","kind":"arxiv","version":2},"verdict":{"id":"0de84165-98e7-48dd-8184-494abbe9496e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T04:26:34.742454Z","strongest_claim":"Both approaches achieved an AUROC of 1.000 and accuracies between 0.999 and 1.000 on internal and external validation sets, showing comparable detection performance. The ML approach, however, exhibited substantially lower end-to-end latency while maintaining equivalent accuracy.","one_line_summary":"ML matches DL in OOD detection accuracy for medical images but with substantially lower latency.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"Medical imaging data acquired under standardized protocols exhibit limited image variability, allowing lightweight ML methods to achieve performance comparable to DL in OOD detection tasks.","pith_extraction_headline":"Machine learning matches deep learning performance for out-of-distribution detection in medical images but with substantially lower latency."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.10181/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T06:22:00.936084Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T15:39:01.205409Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T12:01:17.237875Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T09:37:44.380877Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"e5943bf41b26586a6133af53add919a02aeb6028971ccf098f5d2a2a89d42e73"},"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":"0de84165-98e7-48dd-8184-494abbe9496e"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T01:05:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aiH65/NX9wg97oc5alYIrVMGgq2WfRDfd5lNeax1OVgF5gkzbOrn8UAGy8DH9vUnPhs/lMwpAKV6a1dEU+ubDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T19:59:07.330895Z"},"content_sha256":"54529b1ce191444c6341eeae59a1e7d70466e5ded995c25444edb77a7bb99eb9","schema_version":"1.0","event_id":"sha256:54529b1ce191444c6341eeae59a1e7d70466e5ded995c25444edb77a7bb99eb9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OXIZ7PF3FWML7KNKG7EP6HTHMI/bundle.json","state_url":"https://pith.science/pith/OXIZ7PF3FWML7KNKG7EP6HTHMI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OXIZ7PF3FWML7KNKG7EP6HTHMI/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":"2026-05-21T19:59:07Z","links":{"resolver":"https://pith.science/pith/OXIZ7PF3FWML7KNKG7EP6HTHMI","bundle":"https://pith.science/pith/OXIZ7PF3FWML7KNKG7EP6HTHMI/bundle.json","state":"https://pith.science/pith/OXIZ7PF3FWML7KNKG7EP6HTHMI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OXIZ7PF3FWML7KNKG7EP6HTHMI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OXIZ7PF3FWML7KNKG7EP6HTHMI","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":"cf08ffc2b4c3a4516a812b309d0ccea42f55eef35cef7c2481247e75d7890d3e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-11T08:32:50Z","title_canon_sha256":"354af016f93a95670271a6186eee09f310676f21dae4129d8f8cd814b3ba609a"},"schema_version":"1.0","source":{"id":"2605.10181","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.10181","created_at":"2026-05-21T01:05:20Z"},{"alias_kind":"arxiv_version","alias_value":"2605.10181v2","created_at":"2026-05-21T01:05:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.10181","created_at":"2026-05-21T01:05:20Z"},{"alias_kind":"pith_short_12","alias_value":"OXIZ7PF3FWML","created_at":"2026-05-21T01:05:20Z"},{"alias_kind":"pith_short_16","alias_value":"OXIZ7PF3FWML7KNK","created_at":"2026-05-21T01:05:20Z"},{"alias_kind":"pith_short_8","alias_value":"OXIZ7PF3","created_at":"2026-05-21T01:05:20Z"}],"graph_snapshots":[{"event_id":"sha256:54529b1ce191444c6341eeae59a1e7d70466e5ded995c25444edb77a7bb99eb9","target":"graph","created_at":"2026-05-21T01:05:20Z","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":"Both approaches achieved an AUROC of 1.000 and accuracies between 0.999 and 1.000 on internal and external validation sets, showing comparable detection performance. The ML approach, however, exhibited substantially lower end-to-end latency while maintaining equivalent accuracy."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"Medical imaging data acquired under standardized protocols exhibit limited image variability, allowing lightweight ML methods to achieve performance comparable to DL in OOD detection tasks."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"ML matches DL in OOD detection accuracy for medical images but with substantially lower latency."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Machine learning matches deep learning performance for out-of-distribution detection in medical images but with substantially lower latency."}],"snapshot_sha256":"d765ace8fe849dcfd2fb2bd0abe2d1b335e534186f36294e45a4ebabf0bc7a60"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T06:22:00.936084Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T15:39:01.205409Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T12:01:17.237875Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T09:37:44.380877Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.10181/integrity.json","findings":[],"snapshot_sha256":"e5943bf41b26586a6133af53add919a02aeb6028971ccf098f5d2a2a89d42e73","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Out-of-distribution (OOD) detection is essential for building reliable AI systems, as models that produce outputs for invalid inputs cannot be trusted. Although deep learning (DL) is often assumed to outperform traditional machine learning (ML), medical imaging data are typically acquired under standardized protocols, leading to relatively constrained image variability in OOD detection tasks. This motivates a direct comparison between ML and DL approaches in this setting. The two approaches are evaluated on open datasets comprising over 60,000 fundus and non-fundus images across multiple resol","authors_text":"Doohyun Park, Gitaek Kwon, Jihyeon Baek, Seunghoon Lee","cross_cats":["cs.AI"],"headline":"Machine learning matches deep learning performance for out-of-distribution detection in medical images but with substantially lower latency.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-11T08:32:50Z","title":"A Comparative Study of Machine Learning and Deep Learning for Out-of-Distribution Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.10181","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-12T04:26:34.742454Z","id":"0de84165-98e7-48dd-8184-494abbe9496e","model_set":{"reader":"grok-4.3"},"one_line_summary":"ML matches DL in OOD detection accuracy for medical images but with substantially lower latency.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Machine learning matches deep learning performance for out-of-distribution detection in medical images but with substantially lower latency.","strongest_claim":"Both approaches achieved an AUROC of 1.000 and accuracies between 0.999 and 1.000 on internal and external validation sets, showing comparable detection performance. The ML approach, however, exhibited substantially lower end-to-end latency while maintaining equivalent accuracy.","weakest_assumption":"Medical imaging data acquired under standardized protocols exhibit limited image variability, allowing lightweight ML methods to achieve performance comparable to DL in OOD detection tasks."}},"verdict_id":"0de84165-98e7-48dd-8184-494abbe9496e"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5fad04ef4e86e5993bcc2e4f4d99f79b37833b3ced6825b312d1c4c5e00f788b","target":"record","created_at":"2026-05-21T01:05:20Z","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":"cf08ffc2b4c3a4516a812b309d0ccea42f55eef35cef7c2481247e75d7890d3e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-11T08:32:50Z","title_canon_sha256":"354af016f93a95670271a6186eee09f310676f21dae4129d8f8cd814b3ba609a"},"schema_version":"1.0","source":{"id":"2605.10181","kind":"arxiv","version":2}},"canonical_sha256":"75d19fbcbb2d98bfa9aa37c8ff1e67620ada1cf3c8466d0ca53d54483133c472","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"75d19fbcbb2d98bfa9aa37c8ff1e67620ada1cf3c8466d0ca53d54483133c472","first_computed_at":"2026-05-21T01:05:20.932974Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:05:20.932974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tTVSkXAl7sJMvc68i9+nq95Hed/MgyWa9J+iD6rww5WwdxdBkWWbnU/QK0QvIAoB/96sIqzZmx1Iu6xQZ52/Ag==","signature_status":"signed_v1","signed_at":"2026-05-21T01:05:20.933493Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.10181","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5fad04ef4e86e5993bcc2e4f4d99f79b37833b3ced6825b312d1c4c5e00f788b","sha256:54529b1ce191444c6341eeae59a1e7d70466e5ded995c25444edb77a7bb99eb9"],"state_sha256":"51ef957e1f0b3360de0e24d41e8f6d49688cf6128bc84b62356a90a9e39da03f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1Ms903FS5Qt4KP/6LrW9NB4UdIG/aexmr1PDsuWn2YFkeOepRw7l8nr3DITyfYbK9kZIiAiaJAZAsSTma8T3Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T19:59:07.333773Z","bundle_sha256":"e493db17820a886240133c0ba63df4e7b5816281f170f207c7a2e33202d3fe70"}}