{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:65MM57DB3V6QJK2ZZTI6L6RHMS","short_pith_number":"pith:65MM57DB","schema_version":"1.0","canonical_sha256":"f758cefc61dd7d04ab59ccd1e5fa2764ac05de6a214c0589c551742d5c90574c","source":{"kind":"arxiv","id":"2605.23977","version":1},"attestation_state":"computed","paper":{"title":"A Multi-Probe Audit of Clinical-Interview Depression Detection Benchmarks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jon Duke, Takehiro Ishikawa","submitted_at":"2026-05-13T17:32:41Z","abstract_excerpt":"This paper audits benchmark evaluation in clinical-interview depression detection through four complementary probes across DAIC/E-DAIC, CMDC, ANDROIDS, MODMA, and PDCH. First, we re-evaluate E-DAIC under strict subject-disjoint leave-one-subject-out cross-validation. A lightweight hybrid text-plus-LLM-score model reaches macro-F1 = 0.723 - the highest reported under this protocol, to our knowledge - providing a conservative out-of-fold reference point that does not depend on the privileged official holdout. Second, we test whether the E-DAIC official split supports fine-grained leaderboard ran"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.23977","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T17:32:41Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"66f1db766962cf20a49c4f26c92e192d753c5f0cc4c94ce0e32129350e1780d0","abstract_canon_sha256":"bc90f0ed8efff486a6324cc02394756e29c4f657cf5a0c3ab7d799525ee31bb1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T00:02:24.827641Z","signature_b64":"/MNWM2Mrq+NW+8WakbVq21VcsYpDtCU5Qv/IGNGTWZVoreHaYipDH/VrzrbUzRfsSOwrwClg5KSo7TahJE1LCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f758cefc61dd7d04ab59ccd1e5fa2764ac05de6a214c0589c551742d5c90574c","last_reissued_at":"2026-05-26T00:02:24.826835Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T00:02:24.826835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Multi-Probe Audit of Clinical-Interview Depression Detection Benchmarks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jon Duke, Takehiro Ishikawa","submitted_at":"2026-05-13T17:32:41Z","abstract_excerpt":"This paper audits benchmark evaluation in clinical-interview depression detection through four complementary probes across DAIC/E-DAIC, CMDC, ANDROIDS, MODMA, and PDCH. First, we re-evaluate E-DAIC under strict subject-disjoint leave-one-subject-out cross-validation. A lightweight hybrid text-plus-LLM-score model reaches macro-F1 = 0.723 - the highest reported under this protocol, to our knowledge - providing a conservative out-of-fold reference point that does not depend on the privileged official holdout. Second, we test whether the E-DAIC official split supports fine-grained leaderboard ran"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23977","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/2605.23977/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.23977","created_at":"2026-05-26T00:02:24.826958+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.23977v1","created_at":"2026-05-26T00:02:24.826958+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23977","created_at":"2026-05-26T00:02:24.826958+00:00"},{"alias_kind":"pith_short_12","alias_value":"65MM57DB3V6Q","created_at":"2026-05-26T00:02:24.826958+00:00"},{"alias_kind":"pith_short_16","alias_value":"65MM57DB3V6QJK2Z","created_at":"2026-05-26T00:02:24.826958+00:00"},{"alias_kind":"pith_short_8","alias_value":"65MM57DB","created_at":"2026-05-26T00:02:24.826958+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/65MM57DB3V6QJK2ZZTI6L6RHMS","json":"https://pith.science/pith/65MM57DB3V6QJK2ZZTI6L6RHMS.json","graph_json":"https://pith.science/api/pith-number/65MM57DB3V6QJK2ZZTI6L6RHMS/graph.json","events_json":"https://pith.science/api/pith-number/65MM57DB3V6QJK2ZZTI6L6RHMS/events.json","paper":"https://pith.science/paper/65MM57DB"},"agent_actions":{"view_html":"https://pith.science/pith/65MM57DB3V6QJK2ZZTI6L6RHMS","download_json":"https://pith.science/pith/65MM57DB3V6QJK2ZZTI6L6RHMS.json","view_paper":"https://pith.science/paper/65MM57DB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.23977&json=true","fetch_graph":"https://pith.science/api/pith-number/65MM57DB3V6QJK2ZZTI6L6RHMS/graph.json","fetch_events":"https://pith.science/api/pith-number/65MM57DB3V6QJK2ZZTI6L6RHMS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/65MM57DB3V6QJK2ZZTI6L6RHMS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/65MM57DB3V6QJK2ZZTI6L6RHMS/action/storage_attestation","attest_author":"https://pith.science/pith/65MM57DB3V6QJK2ZZTI6L6RHMS/action/author_attestation","sign_citation":"https://pith.science/pith/65MM57DB3V6QJK2ZZTI6L6RHMS/action/citation_signature","submit_replication":"https://pith.science/pith/65MM57DB3V6QJK2ZZTI6L6RHMS/action/replication_record"}},"created_at":"2026-05-26T00:02:24.826958+00:00","updated_at":"2026-05-26T00:02:24.826958+00:00"}