{"_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_5066642795ad33d05c7b174406b9d4fa908897e4dded731e0f2575c4c90cd515","bitcoin_anchor":{"bitcoin_attestations":["bitcoin_block_949451"],"calendar_attestations":["https://finney.calendar.eternitywall.com","https://btc.calendar.catallaxy.com","https://alice.btc.calendar.opentimestamps.org","https://bob.btc.calendar.opentimestamps.org"],"ots_url":"/registry/data/substrate/anchors/77fc9c28fae777b81da5b495b3115474df6592dfac590333213d3bdf8b94a9b3.ots","stamped_at":"2026-05-15T03:00:03Z","status":"bitcoin"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_5066642795ad33d05c7b174406b9d4fa908897e4dded731e0f2575c4c90cd515","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"a0502a9576d6a9a084b9c457503f23a00435a26fcdc36d68f644e8f05ee89f65","published":"Tue, 12 May 2026 00:00:00 -0400","receipt_hash":"a0502a9576d6a9a084b9c457503f23a00435a26fcdc36d68f644e8f05ee89f65","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":"a0502a9576d6a9a084b9c457503f23a00435a26fcdc36d68f644e8f05ee89f65","observed_at":"2026-05-12T04:43:42.564879Z","parent_run_hash":"4cc5aca0c1b8116c9ab92405e0260204f01cf7ce2e49dea9d7e123236f5dc13b","published":"Tue, 12 May 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:2602.04811v2 Announce Type: replace-cross \nAbstract: True self-evolution requires agents to act as lifelong learners that internalize novel experiences to solve future problems. However, rigorously measuring this foundational capability is hindered by two obstacles: the entanglement of prior knowledge, where ``new'' knowledge may appear in pre-training data, and the entanglement of reasoning complexity, where failures may stem from problem difficulty rather than an inability to recall learned knowledge. We introduce SE-Bench, a diagnostic environment that obfuscates the NumPy library and its API doc into a pseudo-novel package with randomized identifiers. Agents are trained to internalize this package and evaluated on simple coding tasks without access to documentation, yielding a clean setting where tasks are trivial with the new API doc but impossible for base models without it. Our investigation reveals three insights: (1) the Open-Book Paradox, where training with reference d","title":"SE-Bench: Benchmarking Self-Evolution with Knowledge Internalization","url":"https://arxiv.org/abs/2602.04811","vendor":"arxiv_cs_ai"},"summary":"arXiv:2602.04811v2 Announce Type: replace-cross \nAbstract: True self-evolution requires agents to act as lifelong learners that internalize novel experiences to solve future problems. However, rigorously measuring this foundational capability is hindered by two obstacles: the entanglement of prior knowledge, where ``new'' knowledge may appear in pre-training data, and the entanglement of reasoning complexity, where failures may stem from problem difficulty rather than an inability to recall learned knowledge. We introduce SE-Bench, a diagnostic environment that obfuscates the NumPy library and its API doc into a pseudo-novel package with randomized identifiers. Agents are trained to internalize this package and evaluated on simple coding tasks without access to documentation, yielding a clean setting where tasks are trivial with the new API doc but impossible for base models without it. Our investigation reveals three insights: (1) the Open-Book Paradox, where training with reference d","title":"SE-Bench: Benchmarking Self-Evolution with Knowledge Internalization","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-12T04:43:42Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2602.04811"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:1f5dfcde3d70ecfd4bb7be8d3e20c025ee7fb0e02cf09a710b2db63053566979234e0923b14e354ff49468bdbe147c262a687d52a53149811bbda2e2d2ec9303","signer":"crovia.substrate","subject":{"observed_at":"2026-05-12T04:43:42Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2602.04811"},"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":"e929be3653d0320898ae2167eb807aa4ab0e2620db0da21154f41ba0710f69ed","leaf_index":129136,"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":"b86f6a71d9b556cbe90e7a61869e47bcc2b1b0c2728e33d9dd00785248e20217","side":"right"},{"sibling":"09b2d4f4c1e6f1065ffe039bffe7e0a4539a2b6d99f8a243a3f32bbf2c971fb6","side":"right"},{"sibling":"8cfd541264397d94ffe83a19be9ce82406c6664b3717ea239e21cfdcc9bfdd94","side":"right"},{"sibling":"5950e97940bc935b7991807cad283b53b62aa1be0859b3c94122e7e08ecf9b5e","side":"right"},{"sibling":"a340d227db664a83319caa60cf7c4cdb77a56ddbeb988cfe0222dda1c9f10a32","side":"left"},{"sibling":"cd05b2bf5b67ed7de8483e412656f334a998abc972fa62da600db82736c1982f","side":"left"},{"sibling":"de3746873a17cbee8458cf7f279f03cf066292b79b849b56e0cdcff253bd1ee4","side":"left"},{"sibling":"684a7e41697dc4a5ae5bd51e0b1fa452ba8e0ce5866bec279d63e12ce9b1e6cf","side":"right"},{"sibling":"bb93634b6ea81ccfb7b9c5b023ffaff85acd8b3f1ec609973d847fd93873d3ec","side":"right"},{"sibling":"9922155d12ac3db561299f0abaec57fc59dd8e711d91cd590823abd8f3e4647f","side":"right"},{"sibling":"9c71dae5b380aff58527385ccecc23b4cd8ff36395d4fc35ad5236b00fcb6db8","side":"right"},{"sibling":"d32d0a951c1d7e98a8e1951a587d83c97962daeeaa455643bc1d5d53744dc21e","side":"left"},{"sibling":"ffc4d51379293bc3e1910c7d612f409dc610fd9acf8241793fb89f82e1bad4ef","side":"left"},{"sibling":"62ac6554017807bd83187f5a3e5f4f72d6c482616429c2780e9fff1f4845fa04","side":"left"},{"sibling":"3a5e69cf0803f4c91f3895ed7c9a95748fef240bec4422e167c05300f79f06c0","side":"left"},{"sibling":"f2817ab288b5324fe49770372c7a10f33f7cd11005f8d4c0a730316f5229dc98","side":"left"},{"sibling":"725fac972e772ca0dc598810ea1abc70df472f72d2d6ab8a0baee2b80e5d2f4c","side":"left"},{"sibling":"98fc57dfef8873b512edc8340f7181df57302bb96777625e072235c62d7c5895","side":"right"}]},"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":134292,"merkle_root":"77fc9c28fae777b81da5b495b3115474df6592dfac590333213d3bdf8b94a9b3","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260515T023701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-15T02:37:25Z","sig_algorithm":"ed25519","signature":"68107a834b00b24f5d4501e5ec727445311f132a486567ecc4c72a4e6dff24c8c21f2de3105293353ba5fdbe370d032819af6aa70f694e2e39b6af6737507009","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_5066642795ad33d05c7b174406b9d4fa908897e4dded731e0f2575c4c90cd515"}}