{"_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_d5d91670c80f958db0ecfba505c46db1b9326dfb96ba05ea81f89ed7aff3108c","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_d5d91670c80f958db0ecfba505c46db1b9326dfb96ba05ea81f89ed7aff3108c","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"007a83550194e1e389892be7c91ebdc37c1d9178986797d8e2e0175bd0b9626b","published":"Thu, 28 May 2026 00:00:00 -0400","receipt_hash":"007a83550194e1e389892be7c91ebdc37c1d9178986797d8e2e0175bd0b9626b","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":"007a83550194e1e389892be7c91ebdc37c1d9178986797d8e2e0175bd0b9626b","observed_at":"2026-05-28T04:43:38.862500Z","parent_run_hash":"58f8b4a134069e0a15ea3949252489597eb86dd27c9ca3fb15c6fb838ce49ef3","published":"Thu, 28 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:2605.27846v1 Announce Type: new \nAbstract: Large Reasoning Models are typically trained via reinforcement learning from verifiable rewards (RLVR). However, existing approaches adopt fixed weights for positive and negative samples, and the conclusions hardly generalize to open-ended question answering (QA). In this paper, we systematically investigate the roles of positive and negative samples in reinforcement learning for open-ended QA. We propose a reward-mean-based strategy for distinguishing positive from negative samples, and observe that negative samples predominantly govern response diversity and the performance upper bound, whereas positive samples primarily determine response quality and convergence stability. Building on these observations, we propose EAPO, an Entropy-driven Adaptive Policy Optimization method that adaptively computes the weighting coefficients of positive samples based on the ratio of the current policy entropy to the initial entropy. During the entropy","title":"EAPO: Entropy-Driven Adaptive Positive-Negative Sample Weighting for Policy Optimization in Open-Ended QA","url":"https://arxiv.org/abs/2605.27846","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.27846v1 Announce Type: new \nAbstract: Large Reasoning Models are typically trained via reinforcement learning from verifiable rewards (RLVR). However, existing approaches adopt fixed weights for positive and negative samples, and the conclusions hardly generalize to open-ended question answering (QA). In this paper, we systematically investigate the roles of positive and negative samples in reinforcement learning for open-ended QA. We propose a reward-mean-based strategy for distinguishing positive from negative samples, and observe that negative samples predominantly govern response diversity and the performance upper bound, whereas positive samples primarily determine response quality and convergence stability. Building on these observations, we propose EAPO, an Entropy-driven Adaptive Policy Optimization method that adaptively computes the weighting coefficients of positive samples based on the ratio of the current policy entropy to the initial entropy. During the entropy","title":"EAPO: Entropy-Driven Adaptive Positive-Negative Sample Weighting for Policy Optimization in Open-Ended QA","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-28T04:43:38Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.27846"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:5a3627dca9390325b8db3d609b73d6bd5b83e9d6a9e07328b4ef6917230f251dd779314913a3fc9a2272fc24768eab67cffb9446d34658409f357bd441c9f001","signer":"crovia.substrate","subject":{"observed_at":"2026-05-28T04:43:38Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.27846"},"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":"dfc1c899e171d1880c13f00171d774063c4c0653542f490c5c9cbc03c3fd72ee","leaf_index":155602,"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":"5f9081be3ef5c6c2816fd3c794ecfdc441accb8c49b3587a898d1e3dbbb07967","side":"right"},{"sibling":"be0f6d09524e3c008f80cf68659db771a9cde11626109ad07a1f98413b718ce6","side":"left"},{"sibling":"806d32cd6c6db49c072b78af06d86ce230365ee79e30c57931abfccaac158b0a","side":"right"},{"sibling":"288f8780e1cb7edfdd8b00c8a2f79ec5cdcc93e8eb87105acdfb667b00fa8a41","side":"right"},{"sibling":"c8c21e6ef77478e42625acc377a4062ee6ad593745301a1f6d90936e6d94e475","side":"left"},{"sibling":"9271164ea0f2c427fba10eb695cb98be464e920bb5d4d839cf341ff315753f23","side":"right"},{"sibling":"7252c2f7874601f6b2d750e8a0aa6cc72c6924d6614fe237cd5c97d2026c5c17","side":"left"},{"sibling":"70e73f197ecea5d12ff2f9cf2ca33087110a782ea956c539b3058422ada4b2bd","side":"left"},{"sibling":"8c9c7b64ca041ef0029c35e402972d0bebed706fe997b9c587da6f5c811dcce1","side":"left"},{"sibling":"aa7a574eaea239ab8851da225206477d62a6ea5a15b65834f22d1c10288348e7","side":"left"},{"sibling":"7fcba2ee8232873e5d864902f28968d2be38867751c238f238f629eddb98b226","side":"left"},{"sibling":"816f233274bb10f5a122aac086a0c8c697b78fec67a4af55190bb596b7506fab","side":"left"},{"sibling":"d415e6939aee710631f5062799379b547d2c3e3d9a68f263bbb5a693285ab2ca","side":"left"},{"sibling":"d422d38e0ffe6e849b6ce3259d90c9d36497b4d7391a003e15591668c79028a7","side":"right"},{"sibling":"35ca36cee447f0ef7064a25d55f59357c66901e31427729c4c1d8b14aa8adb6c","side":"left"},{"sibling":"7b6f0bea4291a5e63574dfca9aa0f9756f450c9478c3d07474d39a7ababb51f9","side":"right"},{"sibling":"1d39fe14b21e2ebbfb87e882423b24ee9469eae1e4c77af5b799ac4db9537467","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":156177,"merkle_root":"c5705a0243d16afd8b1ebfd731b7aa304079c442c2a7906493c5bbed374c69ec","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260528T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-28T05:37:36Z","sig_algorithm":"ed25519","signature":"f087e13febc8bb6a2e0812610de64cebc65be92915518d9c4b230799c3b161839b04c4eb1b02741f938f35545a76ab76555b04c782bdc2f9a44852d171d65909","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_d5d91670c80f958db0ecfba505c46db1b9326dfb96ba05ea81f89ed7aff3108c"}}