{"_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_338098ad837db8887132358ced125cf9652db85ff83328d26d75eb19c77a9e91","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_338098ad837db8887132358ced125cf9652db85ff83328d26d75eb19c77a9e91","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"592d04a1c432be363727464e22c802f6f920549983cb6a2a6f6b859b95d3d6a4","published":"Thu, 14 May 2026 00:00:00 -0400","receipt_hash":"592d04a1c432be363727464e22c802f6f920549983cb6a2a6f6b859b95d3d6a4","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":"592d04a1c432be363727464e22c802f6f920549983cb6a2a6f6b859b95d3d6a4","observed_at":"2026-05-14T04:43:36.462865Z","parent_run_hash":"eb105e641aec4518c665fb1a0f748c2a8c8189675990bd4092425661eb7af1d8","published":"Thu, 14 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:2605.05739v2 Announce Type: replace-cross \nAbstract: Forecast evaluation in finance has relied on aggregate accuracy metrics and predictive-accuracy tests built on point-forecast errors. These instruments evaluate forecast outputs but cannot evaluate the process of forecast generation, which is increasingly relevant as forecasting systems become agentic, issuing forecasts through sequences of interdependent autonomous decisions whose individual quality is hidden by output-level errors. We propose a behavioral forecast-evaluation methodology that complements accuracy tests by assessing the intermediate decision process itself. Behavioral traces logged at every autonomous decision point are grouped into five-day episodes and scored along six domain-specific dimensions (regime detection, routing, adaptation, risk calibration, strategy coherence, error recovery) by an ensemble of three large language model (LLM) judges. A perturbation procedure that corrupts one dimension while leavi","title":"Multi-Dimensional Behavioral Evaluation of Agentic Stock Prediction Systems Using Large Language Model Judges with Closed-Loop Reinforcement Learning Feedback","url":"https://arxiv.org/abs/2605.05739","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.05739v2 Announce Type: replace-cross \nAbstract: Forecast evaluation in finance has relied on aggregate accuracy metrics and predictive-accuracy tests built on point-forecast errors. These instruments evaluate forecast outputs but cannot evaluate the process of forecast generation, which is increasingly relevant as forecasting systems become agentic, issuing forecasts through sequences of interdependent autonomous decisions whose individual quality is hidden by output-level errors. We propose a behavioral forecast-evaluation methodology that complements accuracy tests by assessing the intermediate decision process itself. Behavioral traces logged at every autonomous decision point are grouped into five-day episodes and scored along six domain-specific dimensions (regime detection, routing, adaptation, risk calibration, strategy coherence, error recovery) by an ensemble of three large language model (LLM) judges. A perturbation procedure that corrupts one dimension while leavi","title":"Multi-Dimensional Behavioral Evaluation of Agentic Stock Prediction Systems Using Large Language Model Judges with Closed-Loop Reinforcement Learning Feedback","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-14T04:43:36Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.05739"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:18559e73431eaf320abe2557bd0f8ff722cca7223804da7b16eeac4a69bebff9d014e3751a3e14119df1b7e2adaad06f8714c47f81598370bab75c0f31ee5e09","signer":"crovia.substrate","subject":{"observed_at":"2026-05-14T04:43:36Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.05739"},"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":"c4b419976a868743b6a98a86b9981a393a899ee84cbbf709f2d44c4ffd40b121","leaf_index":132823,"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":"70cb1ecc61be67fdb152824d3466bb67131da918553140eb66bf84f53674643d","side":"left"},{"sibling":"36c9d8b3215d6beb6da29364be35bfc94ad63fcf602d58a4e6af3c19c2e6e504","side":"left"},{"sibling":"3d0d0fe99b7fb243329a4c961885054989833cbbaea275f2eaeb1efdbd95dd2b","side":"left"},{"sibling":"bfaf29e4db0640425f2848d462e31db128eaac40dc5b79dfa94dc9be9066503e","side":"right"},{"sibling":"5dc71a1e9ec8b11189b99c15b8efa1be0ad30c1630c49a66ce061e07852ea1bf","side":"left"},{"sibling":"5dd2eb51ff7523fd0041fd7f95a704681ed847c8ab70b74101bf64a8e5445b1a","side":"right"},{"sibling":"4b21c838ce912719c21c3cc68b21e467192490091afc471a8d6015d71ea1fe33","side":"left"},{"sibling":"d390ceb521d99fbee195843b8c087d5b6d6b3c13cc9f5d0b36a1c937a84cb77a","side":"left"},{"sibling":"2ae8cbb1d93652ee36f693c3d63e733765fbafcd7765d6d596692bf393ce0a1d","side":"right"},{"sibling":"a957418f640d5dc3181a7628c2646bb86c6da0ea6888670b451e534693a0c7cb","side":"left"},{"sibling":"c03f0a468f574a08ffe8b17e1a17bd88216e1359f0e33a54447e160cd8675da0","side":"left"},{"sibling":"038ff12da6f55509125ef0d96e1e57dda29a2fe63bf03fba2af4cf7cbcd88b36","side":"right"},{"sibling":"b0419206fe62ef216df3900ca93cffd44df267435a4643dda354c1310079cf91","side":"right"},{"sibling":"0d4a9c03674f9d0ce64df15c15e9f656a54b41f93c428aac8e615fda26291956","side":"right"},{"sibling":"7856d920f3f1f1d2194c1ed7351bf0d674440df3cb423a6911f89cb3e9578c0b","side":"right"},{"sibling":"6ac6396bdd2e9df315427a46155531476e7f9012b4bd962e0d2d6d1209b11723","side":"right"},{"sibling":"7c8dc85cbfe43e19ac759ad176cfa11dba2467ae17927c471d5c55663c4f490d","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":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_338098ad837db8887132358ced125cf9652db85ff83328d26d75eb19c77a9e91"}}