{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XTFYXDQ6RQYQ6QQVISAS2V4WFZ","short_pith_number":"pith:XTFYXDQ6","schema_version":"1.0","canonical_sha256":"bccb8b8e1e8c310f421544812d57962e47dff5685edf4b09db0c707c6efcf32c","source":{"kind":"arxiv","id":"2606.18557","version":1},"attestation_state":"computed","paper":{"title":"DeFAb: A Verifiable Benchmark for Defeasible Abduction in Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.LO"],"primary_cat":"cs.AI","authors_text":"Alvaro Velasquez, Patrick Cooper","submitted_at":"2026-06-17T00:13:40Z","abstract_excerpt":"A rule-based logic solver resolves every instance in our benchmark in under 50 microseconds with 100% accuracy; the best frontier language model reaches 65% at best and drops to 23.5% under rendering-robust evaluation (worst case over four surface renderings). We introduce DeFAb (Defeasible Abduction Benchmark), a dataset and generation pipeline that converts four decades of publicly funded knowledge bases into formally grounded instances for defeasible abduction: constructing hypotheses that explain anomalies by overriding defaults while preserving unrelated expectations. Because every hypoth"},"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":"2606.18557","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-17T00:13:40Z","cross_cats_sorted":["cs.LG","cs.LO"],"title_canon_sha256":"0c42088246af853c6af3eb356b11dfb05ef39484b2f123984454b5c091f89325","abstract_canon_sha256":"f78a39e5cc64fd3751a8a1fd68af05f76bd55557ea52a67ae1ec7a10f90ab335"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:40.865481Z","signature_b64":"SOwQSmC/Lx1aFTdu2JvYChi4S2H6vZj2cObZOrUW5XGXkAs3LniCbKJxnbbvAaXtaaeJzubi6WbQBGhB6ZOHCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bccb8b8e1e8c310f421544812d57962e47dff5685edf4b09db0c707c6efcf32c","last_reissued_at":"2026-06-19T16:11:40.865116Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:40.865116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeFAb: A Verifiable Benchmark for Defeasible Abduction in Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.LO"],"primary_cat":"cs.AI","authors_text":"Alvaro Velasquez, Patrick Cooper","submitted_at":"2026-06-17T00:13:40Z","abstract_excerpt":"A rule-based logic solver resolves every instance in our benchmark in under 50 microseconds with 100% accuracy; the best frontier language model reaches 65% at best and drops to 23.5% under rendering-robust evaluation (worst case over four surface renderings). We introduce DeFAb (Defeasible Abduction Benchmark), a dataset and generation pipeline that converts four decades of publicly funded knowledge bases into formally grounded instances for defeasible abduction: constructing hypotheses that explain anomalies by overriding defaults while preserving unrelated expectations. Because every hypoth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18557","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/2606.18557/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":"2606.18557","created_at":"2026-06-19T16:11:40.865171+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.18557v1","created_at":"2026-06-19T16:11:40.865171+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18557","created_at":"2026-06-19T16:11:40.865171+00:00"},{"alias_kind":"pith_short_12","alias_value":"XTFYXDQ6RQYQ","created_at":"2026-06-19T16:11:40.865171+00:00"},{"alias_kind":"pith_short_16","alias_value":"XTFYXDQ6RQYQ6QQV","created_at":"2026-06-19T16:11:40.865171+00:00"},{"alias_kind":"pith_short_8","alias_value":"XTFYXDQ6","created_at":"2026-06-19T16:11:40.865171+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/XTFYXDQ6RQYQ6QQVISAS2V4WFZ","json":"https://pith.science/pith/XTFYXDQ6RQYQ6QQVISAS2V4WFZ.json","graph_json":"https://pith.science/api/pith-number/XTFYXDQ6RQYQ6QQVISAS2V4WFZ/graph.json","events_json":"https://pith.science/api/pith-number/XTFYXDQ6RQYQ6QQVISAS2V4WFZ/events.json","paper":"https://pith.science/paper/XTFYXDQ6"},"agent_actions":{"view_html":"https://pith.science/pith/XTFYXDQ6RQYQ6QQVISAS2V4WFZ","download_json":"https://pith.science/pith/XTFYXDQ6RQYQ6QQVISAS2V4WFZ.json","view_paper":"https://pith.science/paper/XTFYXDQ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.18557&json=true","fetch_graph":"https://pith.science/api/pith-number/XTFYXDQ6RQYQ6QQVISAS2V4WFZ/graph.json","fetch_events":"https://pith.science/api/pith-number/XTFYXDQ6RQYQ6QQVISAS2V4WFZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XTFYXDQ6RQYQ6QQVISAS2V4WFZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XTFYXDQ6RQYQ6QQVISAS2V4WFZ/action/storage_attestation","attest_author":"https://pith.science/pith/XTFYXDQ6RQYQ6QQVISAS2V4WFZ/action/author_attestation","sign_citation":"https://pith.science/pith/XTFYXDQ6RQYQ6QQVISAS2V4WFZ/action/citation_signature","submit_replication":"https://pith.science/pith/XTFYXDQ6RQYQ6QQVISAS2V4WFZ/action/replication_record"}},"created_at":"2026-06-19T16:11:40.865171+00:00","updated_at":"2026-06-19T16:11:40.865171+00:00"}