{"_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_9f27f91c36a6a129c553f1331dedc66981677dfe5f5b9904ea07a4f0858114dc","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_9f27f91c36a6a129c553f1331dedc66981677dfe5f5b9904ea07a4f0858114dc","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"b9fc0b41ec20bfd3294716da1ca9c6d0e4182aea64d267760f63dbda5c2c41f2","published":"Sat, 06 Jun 2026 00:00:00 -0400","receipt_hash":"b9fc0b41ec20bfd3294716da1ca9c6d0e4182aea64d267760f63dbda5c2c41f2","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":"b9fc0b41ec20bfd3294716da1ca9c6d0e4182aea64d267760f63dbda5c2c41f2","observed_at":"2026-06-06T04:43:19.193968Z","parent_run_hash":"550d5b02674822f43975c282be668ca76a4d9c7c957eb1601ba8b07dcb67715e","published":"Sat, 06 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:2606.05646v1 Announce Type: cross \nAbstract: Large language models (LLMs) have enabled powerful software engineering (SE) agents capable of navigating complex codebases and resolving real-world issues. However, these agents remain fundamentally episodic: they fail to retain, refine, and reuse experiences across tasks, repeatedly reconstructing context from scratch and reproducing similar mistakes. Even with memory support, they offer no remedy for the absence of a principled, task-agnostic \\textit{memory utility}, making them difficult to evaluate rigorously or generalize across agents and settings. To tackle these limitations, we introduce \\ours, a closed-loop framework for memory augmentation in SE agents. \\ours grounds memory utility in \\textit{validated downstream impact}, establishing utility as both a task-agnostic \\textbf{evaluation benchmark} and an annotation-free \\textbf{optimization signal}. Through complementary evaluation on \\textit{single-episode} and \\textit{cross-","title":"Enhancing Software Engineering Through Closed-Loop Memory Optimization","url":"https://arxiv.org/abs/2606.05646","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.05646v1 Announce Type: cross \nAbstract: Large language models (LLMs) have enabled powerful software engineering (SE) agents capable of navigating complex codebases and resolving real-world issues. However, these agents remain fundamentally episodic: they fail to retain, refine, and reuse experiences across tasks, repeatedly reconstructing context from scratch and reproducing similar mistakes. Even with memory support, they offer no remedy for the absence of a principled, task-agnostic \\textit{memory utility}, making them difficult to evaluate rigorously or generalize across agents and settings. To tackle these limitations, we introduce \\ours, a closed-loop framework for memory augmentation in SE agents. \\ours grounds memory utility in \\textit{validated downstream impact}, establishing utility as both a task-agnostic \\textbf{evaluation benchmark} and an annotation-free \\textbf{optimization signal}. Through complementary evaluation on \\textit{single-episode} and \\textit{cross-","title":"Enhancing Software Engineering Through Closed-Loop Memory Optimization","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-06T04:43:19Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.05646"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:98157b07a95547af7280bc91171f9402f0b98530c92f487448c169483ec3b73733d261aa3e9f6a354e3587ad3b2c8d983c891870b47e727d3145656c471dbf05","signer":"crovia.substrate","subject":{"observed_at":"2026-06-06T04:43:19Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.05646"},"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":"6b81645217c7db5ed6572145d3c1e67cbea1507ec46831376e6aadfa87742efc","leaf_index":219315,"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":"368a19030fec42676323dc13e9ff39e7f71002f8a73b46caf2f3deed49481f4b","side":"left"},{"sibling":"4cbe04edd546cc9fafbb1906eb0c1cb54f9988edea20f1cffc5b766623a645ad","side":"left"},{"sibling":"3b7d9e63d9b9ba98ad1601a001e712f128b6d65138c2ccab80d16c697570a66e","side":"right"},{"sibling":"edfca36c6b3fa250c2abc3c98d4dcb79b332fed68be62f702a89ebcb82c64e49","side":"right"},{"sibling":"303b9c9a50ca5fd47b4eb21f5f177494dc4b6f7a12056d87bb987ae218c782c3","side":"left"},{"sibling":"f69ada99b5a94148388de7652a5f01876fe5f7566a5bed0f5d64334a1f5a20fa","side":"left"},{"sibling":"10ee7485d3bc0c0562fa4cef6f34003c37b4601cd92eeec5d9ba5e84860493f3","side":"right"},{"sibling":"db337ff23246be63404145882725c137b40795d3b3a9316f0a9b49a930255017","side":"left"},{"sibling":"bd0dfa76bed61a2c5e95135a7304a2b8c4fd064958dbf768664232880d0abaa5","side":"right"},{"sibling":"84d2509eab51047589142ed6da8c496305d2fbcbe148e0e6755163db2c7a4bc4","side":"right"},{"sibling":"9e3ea17e834fab022f2eabcfedb8ea0ac95c1f9fb57edc5004dded68522d3c9e","side":"right"},{"sibling":"41d58fea95a95071715ee23ef8bcd15f5867a3639da28e62a0641bc95eb83094","side":"left"},{"sibling":"27ad9d6a9ab792d708709017242a61b9ca519da4e035f87a342811aae221d000","side":"left"},{"sibling":"5f303e2a7840c60038ff2d035b1cd911feefb0fba880de2d737c6671ace594d4","side":"right"},{"sibling":"b2590791b920ca2a4ed39de126d2c0b1a10d9e7e62f572f12425f214e767b6e1","side":"left"},{"sibling":"1a61eadbf0217d063ab78291ccafdc0c92907f7d6ccdc3357534ef89f07d78ae","side":"right"},{"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":219672,"merkle_root":"d3e32d3a61ca02ce6b1f0b2db86721107770b250e8a5bf762a2c225d2f03c870","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260606T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-06T05:38:35Z","sig_algorithm":"ed25519","signature":"dab214c2d4d857f01383c8e93a521a774b1aba60eaee5677d4e43e4074f0342b2c6a9b9bfcff0eba74f7ac81fcb490dd0e43727979c1a7e8979c7e11547fb101","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_9f27f91c36a6a129c553f1331dedc66981677dfe5f5b9904ea07a4f0858114dc"}}