{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HAANFKKTZIMFHXHQ7X3AMEWT7W","short_pith_number":"pith:HAANFKKT","schema_version":"1.0","canonical_sha256":"3800d2a953ca1853dcf0fdf60612d3fda3874705620e23b4cf6427ccdeb88114","source":{"kind":"arxiv","id":"2606.23175","version":1},"attestation_state":"computed","paper":{"title":"Position: Correct Answer, Wrong Mechanism -- When AI Scientists Defend General Claims Their Own Data Contradicts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Steven Young Eulig","submitted_at":"2026-06-22T11:14:07Z","abstract_excerpt":"AI scientist systems are described as tools, coauthors, or founders, but we evaluate them as if only the final answer matters. This position paper argues that outcome-only evaluation is insufficient, and that task outcome, mechanism fidelity, and epistemic honesty must be measured separately. Our evidence comes from 28 episodes of a coding agent attempting to rediscover a known particle identification observable in a Geant4 simulation, including an 8-episode probe across two additional frontier models. In 4/20 primary-model and 3/8 cross-model episodes, agents reach right-looking results throu"},"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":"2606.23175","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T11:14:07Z","cross_cats_sorted":[],"title_canon_sha256":"d8c2ba58ec1aefb46860d988a116dfa24e9d9c8d01dc80bb6f0b0fe6793cf33f","abstract_canon_sha256":"87336145a3c05d5776b0822188e6894d67720f01ea4309eea5e1a1acbf606cc5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:12.183385Z","signature_b64":"ORU87Jk/gVky0U0Cnqj53kZJfCXQXsx7YgssxV9IS9/ZISR8wh2yYIAbh6OPXxPQ9g0EzpCqIGjYe933baNuCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3800d2a953ca1853dcf0fdf60612d3fda3874705620e23b4cf6427ccdeb88114","last_reissued_at":"2026-06-23T03:14:12.182966Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:12.182966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Position: Correct Answer, Wrong Mechanism -- When AI Scientists Defend General Claims Their Own Data Contradicts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Steven Young Eulig","submitted_at":"2026-06-22T11:14:07Z","abstract_excerpt":"AI scientist systems are described as tools, coauthors, or founders, but we evaluate them as if only the final answer matters. This position paper argues that outcome-only evaluation is insufficient, and that task outcome, mechanism fidelity, and epistemic honesty must be measured separately. Our evidence comes from 28 episodes of a coding agent attempting to rediscover a known particle identification observable in a Geant4 simulation, including an 8-episode probe across two additional frontier models. In 4/20 primary-model and 3/8 cross-model episodes, agents reach right-looking results throu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23175","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/2606.23175/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":"2606.23175","created_at":"2026-06-23T03:14:12.183021+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.23175v1","created_at":"2026-06-23T03:14:12.183021+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23175","created_at":"2026-06-23T03:14:12.183021+00:00"},{"alias_kind":"pith_short_12","alias_value":"HAANFKKTZIMF","created_at":"2026-06-23T03:14:12.183021+00:00"},{"alias_kind":"pith_short_16","alias_value":"HAANFKKTZIMFHXHQ","created_at":"2026-06-23T03:14:12.183021+00:00"},{"alias_kind":"pith_short_8","alias_value":"HAANFKKT","created_at":"2026-06-23T03:14:12.183021+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/HAANFKKTZIMFHXHQ7X3AMEWT7W","json":"https://pith.science/pith/HAANFKKTZIMFHXHQ7X3AMEWT7W.json","graph_json":"https://pith.science/api/pith-number/HAANFKKTZIMFHXHQ7X3AMEWT7W/graph.json","events_json":"https://pith.science/api/pith-number/HAANFKKTZIMFHXHQ7X3AMEWT7W/events.json","paper":"https://pith.science/paper/HAANFKKT"},"agent_actions":{"view_html":"https://pith.science/pith/HAANFKKTZIMFHXHQ7X3AMEWT7W","download_json":"https://pith.science/pith/HAANFKKTZIMFHXHQ7X3AMEWT7W.json","view_paper":"https://pith.science/paper/HAANFKKT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.23175&json=true","fetch_graph":"https://pith.science/api/pith-number/HAANFKKTZIMFHXHQ7X3AMEWT7W/graph.json","fetch_events":"https://pith.science/api/pith-number/HAANFKKTZIMFHXHQ7X3AMEWT7W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HAANFKKTZIMFHXHQ7X3AMEWT7W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HAANFKKTZIMFHXHQ7X3AMEWT7W/action/storage_attestation","attest_author":"https://pith.science/pith/HAANFKKTZIMFHXHQ7X3AMEWT7W/action/author_attestation","sign_citation":"https://pith.science/pith/HAANFKKTZIMFHXHQ7X3AMEWT7W/action/citation_signature","submit_replication":"https://pith.science/pith/HAANFKKTZIMFHXHQ7X3AMEWT7W/action/replication_record"}},"created_at":"2026-06-23T03:14:12.183021+00:00","updated_at":"2026-06-23T03:14:12.183021+00:00"}