{"_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_278fbb83ece635b45ea1370c581f45bdbd704c0b4dc02fe74c6e79e5d2cc0dc4","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_278fbb83ece635b45ea1370c581f45bdbd704c0b4dc02fe74c6e79e5d2cc0dc4","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"4265ba70da36b00148ec33c9a97c0c8a2abcf7e6b5454d4d86872816c80d05c8","published":"Wed, 27 May 2026 00:00:00 -0400","receipt_hash":"4265ba70da36b00148ec33c9a97c0c8a2abcf7e6b5454d4d86872816c80d05c8","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":"4265ba70da36b00148ec33c9a97c0c8a2abcf7e6b5454d4d86872816c80d05c8","observed_at":"2026-05-27T04:43:18.926230Z","parent_run_hash":"6f581915edab4326e2b95fed7c82c2ee149e978d6d7c2443439442a927c31dfa","published":"Wed, 27 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:2604.11056v2 Announce Type: replace-cross \nAbstract: Reinforcement Learning with Verifiable Rewards (RLVR) improves the reasoning ability of Large Language Models (LLMs), but sparse outcome rewards make token-level credit assignment difficult.\n  We study token-level credit as a reward-conditioned shift from the behavior policy to a hindsight posterior.\n  In autoregressive RLVR, this shift can be expressed through Conditional Mutual Information (CMI), which shows that token entropy upper-bounds possible hindsight credit.\n  Entropy, however, indicates capacity rather than update direction, so we introduce the Four Quadrant Decomposition to separate updates by reward polarity and token entropy.\n  Controlled interventions show that these two factors jointly shape token updates.\n  Sustained reasoning gains concentrate in signed high-entropy quadrants, whereas low-entropy updates saturate quickly.\n  Based on this analysis, we propose Hindsight-Aware Policy Optimization (HAPO), a sign-p","title":"Where Hindsight Credit Can Reside: A Signed-Capacity View of Token Updates in RLVR","url":"https://arxiv.org/abs/2604.11056","vendor":"arxiv_cs_ai"},"summary":"arXiv:2604.11056v2 Announce Type: replace-cross \nAbstract: Reinforcement Learning with Verifiable Rewards (RLVR) improves the reasoning ability of Large Language Models (LLMs), but sparse outcome rewards make token-level credit assignment difficult.\n  We study token-level credit as a reward-conditioned shift from the behavior policy to a hindsight posterior.\n  In autoregressive RLVR, this shift can be expressed through Conditional Mutual Information (CMI), which shows that token entropy upper-bounds possible hindsight credit.\n  Entropy, however, indicates capacity rather than update direction, so we introduce the Four Quadrant Decomposition to separate updates by reward polarity and token entropy.\n  Controlled interventions show that these two factors jointly shape token updates.\n  Sustained reasoning gains concentrate in signed high-entropy quadrants, whereas low-entropy updates saturate quickly.\n  Based on this analysis, we propose Hindsight-Aware Policy Optimization (HAPO), a sign-p","title":"Where Hindsight Credit Can Reside: A Signed-Capacity View of Token Updates in RLVR","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-27T04:43:18Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2604.11056"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:e74f20f6b9864a818f55e1b47d656a70b0d0c0707beb775baef4257edcc1e715cfdcf7205a65445d333602de696dcf8e88dcfdf88ed43d7a80bdf41a934ef60b","signer":"crovia.substrate","subject":{"observed_at":"2026-05-27T04:43:18Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2604.11056"},"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":"3005d81d4a8dcc5a2f518e0f79f2baee602f32aefbb2f81e681acf6d486c549b","leaf_index":153968,"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":"a88b7d0caeebd69b120f276bbf03a21e149e2074f3a3351abe66d06be31ddf50","side":"right"},{"sibling":"d35795fcb66aeab7d5de2ea257c724c5eca57da1accdb2ea853d56c1ebf35ed3","side":"right"},{"sibling":"d926e335ae32b6ac178377843237bde287f6f4d312c8866aebd3cffe1bb1a3ba","side":"right"},{"sibling":"e1c19eb5f3a23192c901f295fd916f5612b15351c0ce6a4145c5492408e3b52e","side":"right"},{"sibling":"98ebd282a55489f632ab3e1fe41bbc3b1e6d3d645378583aa2c923a714d9fd16","side":"left"},{"sibling":"aa4dec90fd438277dd786812d9183b8c99388113e7334dd7376266c127e35403","side":"left"},{"sibling":"bc35d95b20384bcefab067b00429ecc07965f080c071ee591082cba7c0f219a2","side":"left"},{"sibling":"16c794666e8ffc4b9e71a0bacc0e4f9bbc68a8544c340b385c6d1abff1d748e5","side":"right"},{"sibling":"c14a4eb4b07d22a6a83f548cf6c304559dc63f0e53071e550ecc566dbba50b14","side":"left"},{"sibling":"3165125427a29042fc9d02858a59a68858dbdcb2e19d1afa5f6dd6a95cfbce6a","side":"right"},{"sibling":"04b9a68b8ec6fa37251564383c685c23ce69e5e031df4eae69f79a3a334b68bf","side":"right"},{"sibling":"816f233274bb10f5a122aac086a0c8c697b78fec67a4af55190bb596b7506fab","side":"left"},{"sibling":"d415e6939aee710631f5062799379b547d2c3e3d9a68f263bbb5a693285ab2ca","side":"left"},{"sibling":"374c02d15fb12bd356c179c94766043a982052c6132af8bfc15361b431ffa9f7","side":"right"},{"sibling":"35ca36cee447f0ef7064a25d55f59357c66901e31427729c4c1d8b14aa8adb6c","side":"left"},{"sibling":"990705096edf483cc877217308f731dc42d6f6d99f82880167bbdbbfef32560a","side":"right"},{"sibling":"dd265753d95fa2e2fb4f5768e37fab6f691ccff09ad60d0910ff7dc23bac9226","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":154065,"merkle_root":"4993cfdc172e7880b60667f16789dc2e831ff000f81bb1ecba248e73f1510eca","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260527T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-27T05:37:36Z","sig_algorithm":"ed25519","signature":"76ecf118011540405e96506e6219752df04a2850632f2903dc6f10e08b98bc5a42c8d9e1cb5b7c5bf714479806a403df5f34399afa40c23fbb71493a1f77bd0c","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_278fbb83ece635b45ea1370c581f45bdbd704c0b4dc02fe74c6e79e5d2cc0dc4"}}