{"_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_3923d9957498b27e4584ec53ceda53727e7385f0b887fa6566e5840c989c7bb6","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_3923d9957498b27e4584ec53ceda53727e7385f0b887fa6566e5840c989c7bb6","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"5bbb399337ba2782d9c65556c351e6618ec53fb9f1fb23b238fd9ab6cf3d39b7","published":"Wed, 13 May 2026 00:00:00 -0400","receipt_hash":"5bbb399337ba2782d9c65556c351e6618ec53fb9f1fb23b238fd9ab6cf3d39b7","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":"5bbb399337ba2782d9c65556c351e6618ec53fb9f1fb23b238fd9ab6cf3d39b7","observed_at":"2026-05-13T04:43:23.245186Z","parent_run_hash":"2a6c2eea51fc0fdbbd1acb92c878f75767034fb102189f6a665cf0ad0e16536e","published":"Wed, 13 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:2605.09287v2 Announce Type: new \nAbstract: Large Language Model (LLM)-based search agents trained with reinforcement learning (RL) have significantly improved the performance of knowledge-intensive tasks. However, existing methods encounter critical challenges in long-horizon credit assignment: (i) Reward Sparsity, where models receive only outcome feedback without step-level guidance to differentiate action quality; (ii) Isolated Credit, where credit is assigned to steps independently, failing to capture sequential dependencies; and (iii) Distributional Shift, where rewards are estimated on templates that deviate from the model's natural generative distribution. To address these issues, we propose Pivot-Based Credit Assignment (PiCA), a novel step reward mechanism that reformulates the search trajectory as a sequential process of cumulative search progress. Unlike prior isolated step rewards, PiCA defines process rewards as success probabilities dependent on the historical conte","title":"PiCA: Pivot-Based Credit Assignment for Search Agentic Reinforcement Learning","url":"https://arxiv.org/abs/2605.09287","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.09287v2 Announce Type: new \nAbstract: Large Language Model (LLM)-based search agents trained with reinforcement learning (RL) have significantly improved the performance of knowledge-intensive tasks. However, existing methods encounter critical challenges in long-horizon credit assignment: (i) Reward Sparsity, where models receive only outcome feedback without step-level guidance to differentiate action quality; (ii) Isolated Credit, where credit is assigned to steps independently, failing to capture sequential dependencies; and (iii) Distributional Shift, where rewards are estimated on templates that deviate from the model's natural generative distribution. To address these issues, we propose Pivot-Based Credit Assignment (PiCA), a novel step reward mechanism that reformulates the search trajectory as a sequential process of cumulative search progress. Unlike prior isolated step rewards, PiCA defines process rewards as success probabilities dependent on the historical conte","title":"PiCA: Pivot-Based Credit Assignment for Search Agentic Reinforcement Learning","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-13T04:43:23Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.09287"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:9580d890e979fd755e842dca2050e39e39671d914f375685b7f339261d3a1706b624a2da2cc2cee945768173337362fd6c6c78a72766710f982b667a5388f10e","signer":"crovia.substrate","subject":{"observed_at":"2026-05-13T04:43:23Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.09287"},"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":"902d89a0ba49832fd742174fa920ee0ea1a426f4adc501ae31e6ea959e90b005","leaf_index":130816,"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":"9e3b396c5cafeeb95a1691972e9bc0f708bffc25692dff515c5d6bca088bd6f8","side":"right"},{"sibling":"74c51a0e4b84e450776bd47392e567c3c0111fe85c124b89174dc4b3966b1996","side":"right"},{"sibling":"3475b6db1e25791b65a8ddf1ebc8718e924931ed9dcd357c3ea6ce900a46cd8e","side":"right"},{"sibling":"a245fc9880d498ca0deab34e54d89ee1766f5bfca4b9a4cc6210954fc8cfc98d","side":"right"},{"sibling":"fd5112dbc47128530028d729e49510d3964d5b8a5136fb82784e22153672ffb5","side":"right"},{"sibling":"6fb621d7885f617d4c32e8192907383f1535fee31ff131144336ec2721a782b9","side":"right"},{"sibling":"8c3518f7d38b276e607f8cbcb7f75921989c30b7fe9b7b7e1b44124372142599","side":"right"},{"sibling":"85f99166b87e29998300b931a3a01c0d1d77304f8efad796211b0ec7150ce694","side":"right"},{"sibling":"15cb4b41b9655a3093d130158e8145d2864f09dffa42ed180b96bc1d7e0f2f1b","side":"left"},{"sibling":"2170332c55df32c3e98553424d3e6242cef02b9714e5a34c7878ee7365425826","side":"left"},{"sibling":"ae6b2233fdba10d8b237d055d6febc6665ca818dcd31382efc2ab8723586948f","side":"left"},{"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_3923d9957498b27e4584ec53ceda53727e7385f0b887fa6566e5840c989c7bb6"}}