{"_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_8b2464ccaebb20af0be1a7c45a314f695b8dd26e8b5dd923fdaf95a44cb8129e","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_8b2464ccaebb20af0be1a7c45a314f695b8dd26e8b5dd923fdaf95a44cb8129e","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"19e41a7cce88c5ee74914352196076a85f50f1c2ea8231fa2836d2592fce63ad","published":"Mon, 01 Jun 2026 00:00:00 -0400","receipt_hash":"19e41a7cce88c5ee74914352196076a85f50f1c2ea8231fa2836d2592fce63ad","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":"19e41a7cce88c5ee74914352196076a85f50f1c2ea8231fa2836d2592fce63ad","observed_at":"2026-06-01T04:43:13.859018Z","parent_run_hash":"8993bbc535dae8c9669e099af3624cb39166b8d9bbfd66f26ae5c338cbb21be2","published":"Mon, 01 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:2502.15224v2 Announce Type: replace-cross \nAbstract: Interactive discovery requires agents to maintain and update structured beliefs over many rounds of feedback. Before evaluating agents in noisy, open-ended scientific environments, it is useful to isolate this prerequisite capability under controlled conditions. We introduce Auto-Discovery-Bench, a deterministic oracle-guided diagnostic benchmark in which agents recover hidden structures through repeated hypothesis--intervention--feedback cycles. The benchmark instantiates three controlled discovery abstractions: directed graph discovery, undirected relational discovery, and symbolic equation discovery. Across models, performance degrades as the number of variables, trajectory length, and distractors increase. A separate trajectory-tracking diagnostic shows that many failures persist even when intervention selection and hypothesis generation are removed, suggesting that limitations in maintaining and integrating long-range stru","title":"Auto-Discovery-Bench: Diagnosing Structured State Tracking in Oracle-Guided Discovery","url":"https://arxiv.org/abs/2502.15224","vendor":"arxiv_cs_ai"},"summary":"arXiv:2502.15224v2 Announce Type: replace-cross \nAbstract: Interactive discovery requires agents to maintain and update structured beliefs over many rounds of feedback. Before evaluating agents in noisy, open-ended scientific environments, it is useful to isolate this prerequisite capability under controlled conditions. We introduce Auto-Discovery-Bench, a deterministic oracle-guided diagnostic benchmark in which agents recover hidden structures through repeated hypothesis--intervention--feedback cycles. The benchmark instantiates three controlled discovery abstractions: directed graph discovery, undirected relational discovery, and symbolic equation discovery. Across models, performance degrades as the number of variables, trajectory length, and distractors increase. A separate trajectory-tracking diagnostic shows that many failures persist even when intervention selection and hypothesis generation are removed, suggesting that limitations in maintaining and integrating long-range stru","title":"Auto-Discovery-Bench: Diagnosing Structured State Tracking in Oracle-Guided Discovery","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-01T04:43:13Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2502.15224"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:804f75c1a1330dec37d0e218b0f3010edb1a5c65eb12c95e1fe4a9b309a5766bd2c5f321e5e04959677e1001cb07fffe83af84e8adc44e37970823641c360406","signer":"crovia.substrate","subject":{"observed_at":"2026-06-01T04:43:13Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2502.15224"},"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":"7e59cd8bb33e7076a3dcbd1685e8441cb73ab970d6c226908a08a5a91163aa8a","leaf_index":164045,"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":"b9a7b6606acd4caf55d2f37ff784928e573bb397ee15e7e79d318fe0bf367e52","side":"left"},{"sibling":"07dba946538d915538fa64f31ab46c377150bb368e09de44827146fc53e7a369","side":"right"},{"sibling":"b3f675360bd9cbed158c7c15b6da7b84e0b73bd8ea5aedb00bf4cf6419fe7d97","side":"left"},{"sibling":"6a686f821ed8e44125372bdebb388a54d0db52f3eb9f4d4d74a7bc7b397293bf","side":"left"},{"sibling":"94e27038cbcfab62212438c512efb916079288caa763193af7bcc75caf7124a1","side":"right"},{"sibling":"64adb5bce7321511a79350afc07efd61fa36fccbb0acace802969f448bc3148b","side":"right"},{"sibling":"6b9f5e8f735af934c2b99502e36dfe0c82b536ef2c88dafbb196d5ab8771a38f","side":"left"},{"sibling":"c2ed258674acbec09c8c9dbf15c89e6fc50854c6eb5f8d42b378de7db248641a","side":"left"},{"sibling":"86fede29e507d01bfe35484a1579149e8e99b3527ff48559423f6056d11af46a","side":"right"},{"sibling":"fc601f0745c37fc5f7c249300e654db05d61bb9059885eeb0b0a5047b5d28408","side":"right"},{"sibling":"6ed9290cdae063f13bfeb71c4c5440595cabb61fd4b39225b9cc913ffb336dd7","side":"right"},{"sibling":"a0446b923d1ce90021e78edff07f6bfc7cc2a1326a565c5f0786b82a24dd0a2a","side":"right"},{"sibling":"e598fd53912c30e58ca8e58d7d8a338fe0f2ecb63fdd99225bc703c499c948ec","side":"right"},{"sibling":"fc4873333221ec8167697f75b6f6a8a08491a8cf18952defb65fb6d4958fa5e7","side":"right"},{"sibling":"05c8a827da2a05549ee3250310777009120c687885816bf6c7c74801bfaa346d","side":"right"},{"sibling":"5ea2f2dc9f046df723b6bd9932d61a9a3d80a76e79ce1b939b3d93ff79b5a91c","side":"left"},{"sibling":"ce41d9b82f34b16efd653dfb3552acc4e2512939e47903e5fc979fbed00c5764","side":"right"},{"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":164217,"merkle_root":"a1098816aea1b60b8fe37b62410469bc5024a2c335bbec4f6ef2add7875dbdf2","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260601T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-01T05:37:41Z","sig_algorithm":"ed25519","signature":"d7f91db1d54b9495c499440c2828f4bd53360555391ce6e25adea5183bc1fa0f697d80708a099d0b0429e6f8cb6c71e7fccf82acb3c84481149974fb26074708","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_8b2464ccaebb20af0be1a7c45a314f695b8dd26e8b5dd923fdaf95a44cb8129e"}}