{"_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_b74fb7eb97a4282cdc04859ce6869f5d6bf41fd51d876f79567d551331586ffc","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_b74fb7eb97a4282cdc04859ce6869f5d6bf41fd51d876f79567d551331586ffc","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"3feaa61eb56a46b8f1713a79ab21bb8f42e8866789d170a58694e0055eb76465","published":"Mon, 25 May 2026 00:00:00 -0400","receipt_hash":"3feaa61eb56a46b8f1713a79ab21bb8f42e8866789d170a58694e0055eb76465","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":"3feaa61eb56a46b8f1713a79ab21bb8f42e8866789d170a58694e0055eb76465","observed_at":"2026-05-25T04:43:48.841018Z","parent_run_hash":"56713422f06ad87427cd8cdcdb1ed341feb016b33c37198d9b168328d1df15fb","published":"Mon, 25 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:2603.19310v4 Announce Type: replace-cross \nAbstract: Reinforcement learning has emerged as a powerful paradigm for improving large language model (LLM) reasoning, where rollouts are sampled from the policy and reward signals computed on those rollouts are used to update the policy. However, in data-scarce scenarios, obtaining ground-truth labels to verify rollouts at scale often requires expensive human annotation or labor-intensive expert verification. For instance, evaluating mathematical proofs demands expert review, and open-ended question answering lacks definitive ground truth. When ground-truth labels are scarce, the effectiveness of reinforcement learning fine-tuning is constrained. Inspired by the success of semi-supervised learning in propagating labels from labeled to unlabeled samples, we propose MemReward, a graph-based experience memory framework that integrates reward propagation directly into online policy optimization. MemReward stores rollouts (thinking processe","title":"MemReward: Graph-Based Experience Memory for LLM Reward Prediction with Limited Labels","url":"https://arxiv.org/abs/2603.19310","vendor":"arxiv_cs_ai"},"summary":"arXiv:2603.19310v4 Announce Type: replace-cross \nAbstract: Reinforcement learning has emerged as a powerful paradigm for improving large language model (LLM) reasoning, where rollouts are sampled from the policy and reward signals computed on those rollouts are used to update the policy. However, in data-scarce scenarios, obtaining ground-truth labels to verify rollouts at scale often requires expensive human annotation or labor-intensive expert verification. For instance, evaluating mathematical proofs demands expert review, and open-ended question answering lacks definitive ground truth. When ground-truth labels are scarce, the effectiveness of reinforcement learning fine-tuning is constrained. Inspired by the success of semi-supervised learning in propagating labels from labeled to unlabeled samples, we propose MemReward, a graph-based experience memory framework that integrates reward propagation directly into online policy optimization. MemReward stores rollouts (thinking processe","title":"MemReward: Graph-Based Experience Memory for LLM Reward Prediction with Limited Labels","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-25T04:43:48Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2603.19310"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:4b335faf8302847a5704fbcc3916080d6c6c812601a614133c404a539c4a2789d7a26e4c4f6991235e935bdcfd4bf2753437ca6082251a3ad9c4c595de943509","signer":"crovia.substrate","subject":{"observed_at":"2026-05-25T04:43:48Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2603.19310"},"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":"c8b2cd2f48bc5ff2116c28cb0f728b8b00414d60ae14c63fbc91ae543e6cb747","leaf_index":149741,"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":"1e5737f1abc0a41ebefca9baf7d06e92ef319abcd885021d4e166ab2024bbe7c","side":"left"},{"sibling":"c22d10629a170c534fbe5fc6bd6bcb58bb6d4fb03d575f7aabace279c825c089","side":"right"},{"sibling":"5ee26e52a0589511ec1008d04882268d72a5f5fa0bdf9d5fb55b8d0e27965307","side":"left"},{"sibling":"dfe3e9a4429491da525d4342a1fb5b2cbc13e600b751e7cb582ff05909196555","side":"left"},{"sibling":"3f50524cca00805ea26f93ce2ea4e7666120458193f076e986ce627215aa29b8","side":"right"},{"sibling":"f4d732126f5433063a27ed518354e49a3c94e9c4c015a328c34b22b871d62002","side":"left"},{"sibling":"9a9dec70c246f07136fd93efad0647d42e469fcfca31c6741dcb1d715bd9ce45","side":"left"},{"sibling":"cb71a04113e54ec457f452a34b2778696e1747afe98ba9da255ce1f5fd8619d7","side":"left"},{"sibling":"e044acc52c31efe134c902c984299ea3452b42df993d096ed61ad8be9d530bbc","side":"right"},{"sibling":"6be461ecf12dedf98a31921aa7b5c32d4a32df6897e0f697b8bf1a4ba3e2d324","side":"right"},{"sibling":"c2861a8cef3eb66bf2726aa377c24a6bf6e8b7489dcd0e870b61d62a35ccadfb","side":"right"},{"sibling":"134949308b15cffd6792ee2cf678119af34d69a64764d7c89cd47573c94e1cda","side":"left"},{"sibling":"debbc1a6232ea7970009b91bdc2345041b2de5ac59551f955855d579001e512c","side":"right"},{"sibling":"216869846f40bd905626884f58cb67b9019e488b3656946a7808c436ab7339ac","side":"right"},{"sibling":"35ca36cee447f0ef7064a25d55f59357c66901e31427729c4c1d8b14aa8adb6c","side":"left"},{"sibling":"e734b0c6d6d13acb5f4cf00367b3913e5bbf1aa717377aa4e4820c6de24b7673","side":"right"},{"sibling":"4bbb7f78e96179bb9cdd06d7207b66b3503ab68e4880438263025b04ebe8f7ec","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":149835,"merkle_root":"51484a548bc0cf3d178eec868e98935c87f0aa83369143b7c96b048585e5ba01","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260525T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-25T05:37:33Z","sig_algorithm":"ed25519","signature":"99a657e53a015ace0bade5d7fbb3f60f950b6d1e1128251a63afcc454a492422cae5efdc0c18503b4f7e62f371bd48f2889be78d9048c4681d6c1e73f754d705","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_b74fb7eb97a4282cdc04859ce6869f5d6bf41fd51d876f79567d551331586ffc"}}