{"_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_57fd7815f551a91e408d974277323efb8e3e0796a57afae8c9d491f0fe27a8af","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_57fd7815f551a91e408d974277323efb8e3e0796a57afae8c9d491f0fe27a8af","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"435a0e7158f57b0cea2ffa3b1dc28a634d91ec2368ea0b6d3013fcfbab41d53d","published":"Thu, 09 Jul 2026 00:00:00 -0400","receipt_hash":"435a0e7158f57b0cea2ffa3b1dc28a634d91ec2368ea0b6d3013fcfbab41d53d","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":"435a0e7158f57b0cea2ffa3b1dc28a634d91ec2368ea0b6d3013fcfbab41d53d","observed_at":"2026-07-09T04:43:38.345231Z","parent_run_hash":"3e22c7c40abc4d94232acf1766a43492b8b8d51d10a58f1109535988a16554e6","published":"Thu, 09 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:2607.06720v1 Announce Type: new \nAbstract: Training large language models (LLMs) with extended reasoning has enabled in-context search, in which models iteratively generate, critique, and revise solution attempts. We provide a theoretical analysis of in-context search by modeling it as approximate inference over reasoning traces, where the base model defines a prior and self-reflection provides feedback for posterior updates, and study the resulting inference-time sampling complexity - the number of sequential attempts needed to achieve high success probability. We show that when reflections reliably localize early mistakes, in-context search can yield exponential improvements over the base model, solving problems with exponentially small zero-shot pass rates using only a polynomial number of sequential attempts, whereas when this property fails, conditioning on past attempts offers no asymptotic benefit over parallel sampling. We further show that these gains are robust and lear","title":"When Does In-Context Search Help? A Sampling-Complexity Theory of Reflection-Driven Reasoning","url":"https://arxiv.org/abs/2607.06720","vendor":"arxiv_cs_ai"},"summary":"arXiv:2607.06720v1 Announce Type: new \nAbstract: Training large language models (LLMs) with extended reasoning has enabled in-context search, in which models iteratively generate, critique, and revise solution attempts. We provide a theoretical analysis of in-context search by modeling it as approximate inference over reasoning traces, where the base model defines a prior and self-reflection provides feedback for posterior updates, and study the resulting inference-time sampling complexity - the number of sequential attempts needed to achieve high success probability. We show that when reflections reliably localize early mistakes, in-context search can yield exponential improvements over the base model, solving problems with exponentially small zero-shot pass rates using only a polynomial number of sequential attempts, whereas when this property fails, conditioning on past attempts offers no asymptotic benefit over parallel sampling. We further show that these gains are robust and lear","title":"When Does In-Context Search Help? A Sampling-Complexity Theory of Reflection-Driven Reasoning","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-09T04:43:38Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2607.06720"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:c2a3a564a22abe08bf3f00d3a60a613b9dab089120841075397d5ed5010f4186a49479b7c57c79e105db37623e46a9ae1c6ba01c40d11da822ea026cc9e68109","signer":"crovia.substrate","subject":{"observed_at":"2026-07-09T04:43:38Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2607.06720"},"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":"ecccc7279cd693edaab3b64f6d7894064b7160b1f73a2dc4220250e30b7b415f","leaf_index":296012,"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":"c5d81b825e2ba14cb047ce240686aba011408b1b8640156cfe231b16b2e6d5b2","side":"right"},{"sibling":"bc85127f05c97675b7dc05c7b12f47a1dd3da7b696f776a0bd0b1b0b201a3206","side":"right"},{"sibling":"295fe35c505c454d283088f87796b07144f167674541c3d48dfd7bac9405cd65","side":"left"},{"sibling":"8ec412b835a6453186c3c3c80e3c17ace982af9f6b8677a976d0b77ccb321a5e","side":"left"},{"sibling":"52c54d782182ad50cc7308d5a225c019047a968f5493e3f45e1a483a721ba22b","side":"right"},{"sibling":"b9d0c6394d16780b95ccdb6ac125b78fc5bc45e9ada322cc3a64578790dd71dd","side":"right"},{"sibling":"8c908dbcf64951b63003ac0fe2b6ae1f91b0a5eed458422d8318f184561b931e","side":"left"},{"sibling":"8e0695b52b318123b078d052a3be7d9d1cd57f74d449e2fba7c1c870bdeda755","side":"right"},{"sibling":"47a94dfb6e50a020e68582e6af2e6a8cf5a4c7efe9fed3deaedbc51f53d75367","side":"right"},{"sibling":"92bb57de69c78fd32ac7108b10d81676c184265a5a53de3c4b22d8cf3b54b499","side":"right"},{"sibling":"85a226efd14acc17835b04bc26706fa44595edbd531f194faf59f60ab72d4bb8","side":"left"},{"sibling":"da38b05536b12aee196b6ac988739211c257d32da790faccf5ac4b0cbc1bb15c","side":"right"},{"sibling":"d438dc3eddb0b14dc8b97cd021a4f44545ce5a8e827f3ea4044fd32b1877475e","side":"right"},{"sibling":"f73ad10346837ae47f59f0647f79b9416e1d499bf2b90af44448e7f09372200a","side":"right"},{"sibling":"bdc09902fcd434c0f7d3e680bf550e560777228c0b085ce80c637ce97fc4104c","side":"right"},{"sibling":"d8b9143917b539c543cf4448cec00131f8b807bd8004979c54ebe09798748c66","side":"left"},{"sibling":"ba603dffe985ef518e3a72793a3eaca83a7f1a79e5491fd0f62f421339f2d137","side":"right"},{"sibling":"be20b90931f0a14e3558ea4387537200fcbd14e019b3c5ed07a2ae4c62fc7c42","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":296360,"merkle_root":"64af62f723a5bc02adfa98b77e2006fc634de4ebf68626694f052342a200bea2","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260709T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-09T05:38:18Z","sig_algorithm":"ed25519","signature":"92ece7411e0d82898aac164e7d6573a6d0f7a595aad0780d710d873e548a061d2a8678cef4d237d3bf0eabe0a5f766b41cbc0b4bada2801e7532026291b4a309","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_57fd7815f551a91e408d974277323efb8e3e0796a57afae8c9d491f0fe27a8af"}}