{"_canonicalization":{"envelope_id":"axm_ + sha256(envelope minus {signature, axiom_id, anchors})","envelope_signature":"ed25519(envelope minus {signature, axiom_id})","json":"sort_keys=True, separators=(',',':'), ensure_ascii=False, allow_nan=False, utf-8","leaf_hash":"sha256(0x00 || canonical_json(envelope_full))","seal_signature":"ed25519(seal minus {signature, sig_algorithm})"},"axiom_id":"axm_f783d90e24ff6f2d8ac345bf0396a983d6d17a7737cc70592b7b0889e716e7f3","bitcoin_anchor":{"bitcoin_attestations":[],"calendar_attestations":[],"ots_url":"","stamped_at":"","status":"pending_next_stamp"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_f783d90e24ff6f2d8ac345bf0396a983d6d17a7737cc70592b7b0889e716e7f3","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"672b1362f85cfc52ee2e056f375007741ccd92ef4b8083df38f1516c840f310a","published":"Thu, 18 Jun 2026 00:00:00 -0400","receipt_hash":"672b1362f85cfc52ee2e056f375007741ccd92ef4b8083df38f1516c840f310a","schema":"spider.news.vendor_press.v1","spider":"vendor_press","spider_record":{"axiom_subtype":"news.vendor_press.v1","category":"news","decision_hint":"POSITIVE","envelope_target":"AX.OBS","fingerprint":"672b1362f85cfc52ee2e056f375007741ccd92ef4b8083df38f1516c840f310a","observed_at":"2026-06-18T04:43:37.219665Z","parent_run_hash":"de79a40f7b3537d88842f7ac355e799c5df2adcb4fc32a4e28096d4bbdf01739","published":"Thu, 18 Jun 2026 00:00:00 -0400","runtime_version":"0.1.0","schema":"spider.news.vendor_press.v1","source_status":200,"source_url":"https://export.arxiv.org/rss/cs.AI","spider":"vendor_press","summary_excerpt":"arXiv:2606.18557v1 Announce Type: new \nAbstract: 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 hypothesis must pass polynomial-time checks for valid derivation, conservativity, and minimality, DeFAb makes logical rigor the instrument for measuring creativity and theoretical reasoning, scoring the disciplined construction of theory revisions rather than fluent but theory-destroying prose. The pipeline pairs taxonomic hierarchies (OpenCyc, YAGO, Wiki","title":"DeFAb: A Verifiable Benchmark for Defeasible Abduction in Foundation Models","url":"https://arxiv.org/abs/2606.18557","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.18557v1 Announce Type: new \nAbstract: 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 hypothesis must pass polynomial-time checks for valid derivation, conservativity, and minimality, DeFAb makes logical rigor the instrument for measuring creativity and theoretical reasoning, scoring the disciplined construction of theory revisions rather than fluent but theory-destroying prose. The pipeline pairs taxonomic hierarchies (OpenCyc, YAGO, Wiki","title":"DeFAb: A Verifiable Benchmark for Defeasible Abduction in Foundation Models","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-18T04:43:37Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.18557"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:f9ddec50bfb58563755555930412c641eabae6cc588d42540118b2bdd9a2964e0e72e4b4bc9e7942a872c1bcbd213359d6773ac47806f8c36820964257c01e07","signer":"crovia.substrate","subject":{"observed_at":"2026-06-18T04:43:37Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.18557"},"tsa":{"authority":"crovia.substrate.bootstrap","rfc3161_token":"{\"kind\":\"crovia.bootstrap.tsa\",\"source_jsonl\":\"/opt/crovia/spider/data/news/vendor_press_v1.jsonl\",\"source_seal_merkle_root\":\"spider_vendor_press_v1\",\"upgrade_path\":\"Sessione H \\u2014 OpenTimestamps weekly anchor\"}"},"zk_mode":"clear","zk_proof":null},"ledger":{"leaf_hash":"9422b833c2e7994b2cc182586ad41be55a581e4671c5556a4771659ace184ed9","leaf_index":233264,"ledger_path":"/opt/crovia/substrate/axiom_ledger.jsonl"},"merkle_proof":{"hash_alg":"sha256","leaf_prefix":"0x00","node_prefix":"0x01","odd_leaf_rule":"duplicate_last","path":[{"sibling":"dd757f51b0b471ae560617cdb533c0c6df56ce03368a1d69c0865496e779de79","side":"right"},{"sibling":"8cf1f1c472d4909ef25e7e1571a58acc36009bf6617da69a48af05454a50c127","side":"right"},{"sibling":"94575254d3207e4879e204b4b78cb540bd228a32f4d01addb689f578de725bfd","side":"right"},{"sibling":"166dac485e9293f93246f0c6e8971221b1686dfb7924afdca7557cd0fd952a99","side":"right"},{"sibling":"37441de7bd936568b2e409d1d405488ad1e857195c88998124b596541954b8ed","side":"left"},{"sibling":"ebe7b3b3edacf4b37e3be684062eca1613553f4843a7db7c86e46d04a7a9d844","side":"left"},{"sibling":"887bf20b113e6ae878a373487670e53c62c95f3eba2b85411e97f2048e7fb9ab","side":"right"},{"sibling":"0330fab6a2deb3386a57965a262bbfda239c89f35362e27a0c4e7f3a9108ec2e","side":"right"},{"sibling":"429c2a92a65e6eeaa2eda0a35fdb9e541472a1eace4c69a4d01a618a659a110f","side":"left"},{"sibling":"d97d1ebe04af6ea572f9d4334004d01026acffa3da5be2883c7566513c76e2c0","side":"left"},{"sibling":"571eb56e7ce00fe1f38d0ac4fc56828d01b2cfc1ab9089cde245c0656bee0514","side":"left"},{"sibling":"7ac50038a8ced3aeaf1194a2407a4a09346b0e4399da36ecde4390675a0c4bf1","side":"left"},{"sibling":"8c5e2b48dc31ef0edcd35c3db048235aa78cc48443aa2a8da3aa6e9b5524d2c4","side":"right"},{"sibling":"e616c34dbaf9456d5a6d3e2da82cde8621293c9f6d8a4cf9e441d7fd9cc81579","side":"right"},{"sibling":"94c0c932e61657f5e37fdba43f6ca9eddea8359425a7c1558dabe566911d5304","side":"right"},{"sibling":"a04392fb9f2a3a620840e3b3fecd93d12e6d224e481c162389d8ae64e7194599","side":"left"},{"sibling":"c300cf0154c136afc09b1702a0be98f4ba5b6dc5cf57e8cc714ec1eaf4196eff","side":"left"},{"sibling":"d841ad93efda0869e5eb97678f348f03f5caab4353e05ff4bf18f47fb945b822","side":"left"}]},"schema":"crovia.axiom_proof.v1","seal":{"first_collector_run_id":"","first_receipt_hash":"","jsonl_path":"/opt/crovia/substrate/axiom_ledger.jsonl","key_id":"430895f101d38164","last_collector_run_id":"","last_receipt_hash":"","leaf_count":234491,"merkle_root":"02576a6980e38bab47864ae2c57b5a5ff21e554e9bdf8f64bdf28155ff1aabec","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260618T143732Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-18T18:33:39Z","sig_algorithm":"ed25519","signature":"b6c708778fc38b7789a2b91156cfe87252a7cd3a1d29121cba11a0c78f8cf104ca3019fc50a962fa5a216bcc4922fc8f3f69c04d1f8332c6dc0d931e1012e502","signer_version":"1.1.0"},"trust_root":{"key_id":"430895f101d38164","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","signature_algorithm":"ed25519","url":"/registry/canon/TRUST_ROOT.md"},"verifier":{"spec":"/registry/canon/AXIOM_RECEIPT_v1.md","url":"/v/axm_f783d90e24ff6f2d8ac345bf0396a983d6d17a7737cc70592b7b0889e716e7f3"}}