{"_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_168d4988f2ecd7c60b770ad8ec8f86e24d05eb51e2b7ecfb9506e48742215b3e","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_168d4988f2ecd7c60b770ad8ec8f86e24d05eb51e2b7ecfb9506e48742215b3e","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"70231cfd323ad393e1df0dd3defc78ddaeeb224e66a865686fb40e84b6f8401b","published":"Mon, 01 Jun 2026 00:00:00 -0400","receipt_hash":"70231cfd323ad393e1df0dd3defc78ddaeeb224e66a865686fb40e84b6f8401b","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":"70231cfd323ad393e1df0dd3defc78ddaeeb224e66a865686fb40e84b6f8401b","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:2605.31584v1 Announce Type: cross \nAbstract: Long-context reasoning remains a central challenge for large language models, which often fail to locate and integrate key information in extensive distracting content. Reinforcement learning with verifiable rewards (RLVR) has shown promise for this task, yet existing methods are limited by low-confusability distractors and sparse, outcome-only reward signals that cannot supervise intermediate reasoning steps. To address these issues, we introduce \\textsc{LongTraceRL}. For data construction, we generate multi-hop questions via knowledge graph random walks and leverage search agent trajectories to build \\emph{tiered distractors}: documents the agent read but did not cite (high confusability) and documents that appeared in search results but were never opened (low confusability), producing training contexts that are far more challenging than those built by random sampling or one-shot search. For reward design, we propose a \\emph{rubric r","title":"LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards","url":"https://arxiv.org/abs/2605.31584","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.31584v1 Announce Type: cross \nAbstract: Long-context reasoning remains a central challenge for large language models, which often fail to locate and integrate key information in extensive distracting content. Reinforcement learning with verifiable rewards (RLVR) has shown promise for this task, yet existing methods are limited by low-confusability distractors and sparse, outcome-only reward signals that cannot supervise intermediate reasoning steps. To address these issues, we introduce \\textsc{LongTraceRL}. For data construction, we generate multi-hop questions via knowledge graph random walks and leverage search agent trajectories to build \\emph{tiered distractors}: documents the agent read but did not cite (high confusability) and documents that appeared in search results but were never opened (low confusability), producing training contexts that are far more challenging than those built by random sampling or one-shot search. For reward design, we propose a \\emph{rubric r","title":"LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards","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/2605.31584"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:574c0a635b3801d102a959713ae0ae8c3aca70335e441549408e9c33dea6e2436ed7545bb3df7605b54e069299497b623bd38cf84daa19648f49c50d83af280f","signer":"crovia.substrate","subject":{"observed_at":"2026-06-01T04:43:13Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.31584"},"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":"90ef4f0a6093deace1eb970bae586957b17c155876986dd4d423ee1cfba8e44f","leaf_index":163986,"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":"ba70fae0683ea6fe7d3cb4218eebf989c5d22162a3c5732ffe8e1c19993ba4b2","side":"right"},{"sibling":"f8f6e8c2c719d8e32d292f635060a799b6c7c0482d8683cbafaad2c94191531a","side":"left"},{"sibling":"cf8b720fcee5037461af14f840838ce0673651c75a410f2431b16e3816085f08","side":"right"},{"sibling":"9a817f237c716d13dff6a44783d581dd9561d838c21dea79da7f70e54f48279c","side":"right"},{"sibling":"f3ff6e4a9545a4ccd17e5ab2f30347dc620f5ed889d8420c0816c05b9bb5de5b","side":"left"},{"sibling":"3a4b99b5e30e175fae490ceb9436824dfa4dacb6bb8fcc8b02cec6847385e329","side":"right"},{"sibling":"1d23b94e7765a5d6bcc243f4f7ecca5895f450b29cd855b417c9c7111e6b5a45","side":"right"},{"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_168d4988f2ecd7c60b770ad8ec8f86e24d05eb51e2b7ecfb9506e48742215b3e"}}