{"_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_5263499e251d85811e9ce2c36f4bf7122ca38d12f56ef6592e35ccfb5d9dbe87","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_5263499e251d85811e9ce2c36f4bf7122ca38d12f56ef6592e35ccfb5d9dbe87","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"6a753f730d8f46cb44ba5e5015966852223e86b60abe174d3270c2f195d5a5aa","published":"Thu, 02 Jul 2026 00:00:00 -0400","receipt_hash":"6a753f730d8f46cb44ba5e5015966852223e86b60abe174d3270c2f195d5a5aa","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":"6a753f730d8f46cb44ba5e5015966852223e86b60abe174d3270c2f195d5a5aa","observed_at":"2026-07-02T04:43:28.872255Z","parent_run_hash":"9f528c2a80e5b201c2a66ae885c05dd596ad2c3532bb4c6809c7c9704d10e650","published":"Thu, 02 Jul 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:2607.00062v1 Announce Type: cross \nAbstract: High pass rates on established programming benchmarks such as HumanEval and LiveCodeBench do not always show whether a model can reason about algorithms. Many fixed benchmarks eventually become part of the public training ecosystem through released problem statements, editorials, and generated solutions, allowing later models to improve partly by exposure rather than by stronger algorithmic ability. We introduce ALGOBENCH, a framework that automatically builds novel algorithmic problems from known competitive-programming problems through structured constraint-shifting transformations. Each accepted ALGOBENCH variant is traceable to a source problem, but must make the original reference algorithm fail. Beyond pass@$k$, we introduce complexity-aware metrics -- including OPTT, OPTS, TRAPRATE, GAPT, and CONSENS -- to test whether a solution is not only functionally correct but also asymptotically suitable for the generated problem. Experim","title":"AlgoBench: Benchmarking Algorithmic Adaptation in Code Generation","url":"https://arxiv.org/abs/2607.00062","vendor":"arxiv_cs_ai"},"summary":"arXiv:2607.00062v1 Announce Type: cross \nAbstract: High pass rates on established programming benchmarks such as HumanEval and LiveCodeBench do not always show whether a model can reason about algorithms. Many fixed benchmarks eventually become part of the public training ecosystem through released problem statements, editorials, and generated solutions, allowing later models to improve partly by exposure rather than by stronger algorithmic ability. We introduce ALGOBENCH, a framework that automatically builds novel algorithmic problems from known competitive-programming problems through structured constraint-shifting transformations. Each accepted ALGOBENCH variant is traceable to a source problem, but must make the original reference algorithm fail. Beyond pass@$k$, we introduce complexity-aware metrics -- including OPTT, OPTS, TRAPRATE, GAPT, and CONSENS -- to test whether a solution is not only functionally correct but also asymptotically suitable for the generated problem. Experim","title":"AlgoBench: Benchmarking Algorithmic Adaptation in Code Generation","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-02T04:43:28Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2607.00062"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:8a6258d5afc5a2ce80966bfa5fa6bddac0114770bcda26b81facbc66e008d3f6059e5d935b88525456c1732de96e6356698d67e55f6e1d1753ee449b09f55a01","signer":"crovia.substrate","subject":{"observed_at":"2026-07-02T04:43:28Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2607.00062"},"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":"fa7cc66c161f3ca066d166651c8fad20ef9aa0e4a85cd7d72f419af93004f88a","leaf_index":271972,"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":"eb38b2b9581b0a88b0c6316678d139f8d2923c255c6700c6c647d41712e7694c","side":"right"},{"sibling":"ed28a3de6c62ff5fc4a829398b529c2bf8f1795ed8be977ec406ad59f9786284","side":"right"},{"sibling":"c57d791c5096a978985d99656719e21d0805eab89043958bad78c064767e1773","side":"left"},{"sibling":"fcef53ca75544ed190ce402dce415a70c9bb367ccae087e33bde1826e117e363","side":"right"},{"sibling":"f746b927d1f90ae3862bcf56b43ce81c1e825efaeba580cc981b9648dd555c28","side":"right"},{"sibling":"c25f18d33f4ad3f321fbcc471335c7d8875df72b3401ae191213309c57c4d3fb","side":"left"},{"sibling":"bba3920d4d73572ccae4aab47102490e036c6245a6d1cb8a6c5b92b702d7f20a","side":"left"},{"sibling":"245706846217c65709d33d0c2ef53806eee8ea674294e4e08c1d4f19cee09ac7","side":"right"},{"sibling":"155ae596a5c6a5260be50ff412642fbd25f4587b43e04c56950c1dc544719be1","side":"right"},{"sibling":"4cfdd7f7072619c015edc477162c2cf29c6f70370acb8dbddf1eb590876d82fe","side":"left"},{"sibling":"43990c9db8fcb3172d821965dfac69152981af4108b8dc87bd32f15c0e56f4cf","side":"left"},{"sibling":"15dbacc2e5845fe3bb835797bb7647ab6f091e79adadd39f40c636980716c622","side":"right"},{"sibling":"7ecc1d0d471643b88d886db58cb02a77af4d1495674760c3867834550b143757","side":"right"},{"sibling":"8a09562f6b247c1c3cd1fea36cb3b8f1cf5c575479dd514573856a380a964bf5","side":"left"},{"sibling":"7b681d50e7d0a7b8d2a749507aed58030072539a90fab18de4f698743685cc00","side":"right"},{"sibling":"9b262645232510ff15bb7325ab858256f2914f711d2726caeafd49f5ca0fb7a9","side":"right"},{"sibling":"5bd94446b5721b713c5e4dcf4624b9bc682657ab2784af927caae7b80c297d7d","side":"right"},{"sibling":"21ac0b7091fe1133859bcd17b4f8da2fe37a2489d472dad508305740b483221b","side":"right"},{"sibling":"1cecb7f447febd025aac272837c80de218aecc6485d2395a509b2a1f1b9c746e","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":272319,"merkle_root":"dd4fa4deb1f207e8a7756821b4f940f39e9f06a25e6fa8500a21dd403318a5a7","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260702T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-02T05:38:06Z","sig_algorithm":"ed25519","signature":"68eb2e3bbc0f593bea7b5c3c110c90b6f4fe4fd8277d8dee7c866ba0471c1a50684aa4539c8a493e6d9c9202d8c03f4d897a0df3477e9ecd5b0ff03eb1016f00","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_5263499e251d85811e9ce2c36f4bf7122ca38d12f56ef6592e35ccfb5d9dbe87"}}