{"_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_f2d1c564b0234f37e502a9dfce08578adf6142ea85f90381fdd8fc7c6571aafc","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_f2d1c564b0234f37e502a9dfce08578adf6142ea85f90381fdd8fc7c6571aafc","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"05d0486fdcf170e93c34f456e9fa98a7b9a337f9844a0b265b240bbeada548b5","published":"Tue, 19 May 2026 00:00:00 -0400","receipt_hash":"05d0486fdcf170e93c34f456e9fa98a7b9a337f9844a0b265b240bbeada548b5","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":"05d0486fdcf170e93c34f456e9fa98a7b9a337f9844a0b265b240bbeada548b5","observed_at":"2026-05-19T04:43:36.782648Z","parent_run_hash":"fefa4c726316a95c5dda9fc1ca07a38a811cf7ffa9825b2f09b365abacd9b32d","published":"Tue, 19 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:2605.12969v2 Announce Type: replace-cross \nAbstract: RLVR has become a widely adopted paradigm for improving LLMs' reasoning capabilities, and GRPO is one of its most representative algorithms. In this paper, we first show that GRPO admits an equivalent discriminative reformulation as a weighted positive-negative score difference. Under this view, GRPO increases sequence-level scores of verified positive rollouts and decreases those of negative rollouts, where the scores are averages of clipped token-level importance sampling ratios. This reformulation reveals two structural limitations of GRPO: likelihood-misaligned scoring, where clipped ratio-based surrogate scores are optimized instead of generation likelihoods, and score-insensitive credit assignment, where rollout-level credit is assigned without accounting for relative score gaps between positive and negative rollouts in the same group. To address these limitations, we propose ConSPO, a framework for Contrastive Sequence-l","title":"Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective","url":"https://arxiv.org/abs/2605.12969","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.12969v2 Announce Type: replace-cross \nAbstract: RLVR has become a widely adopted paradigm for improving LLMs' reasoning capabilities, and GRPO is one of its most representative algorithms. In this paper, we first show that GRPO admits an equivalent discriminative reformulation as a weighted positive-negative score difference. Under this view, GRPO increases sequence-level scores of verified positive rollouts and decreases those of negative rollouts, where the scores are averages of clipped token-level importance sampling ratios. This reformulation reveals two structural limitations of GRPO: likelihood-misaligned scoring, where clipped ratio-based surrogate scores are optimized instead of generation likelihoods, and score-insensitive credit assignment, where rollout-level credit is assigned without accounting for relative score gaps between positive and negative rollouts in the same group. To address these limitations, we propose ConSPO, a framework for Contrastive Sequence-l","title":"Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-19T04:43:36Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.12969"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:837abc0cd4cbfe750065925ee0fbe3699ed1c189e8ef3b5fc6dcd46a94078479a4704adae4b629f83586cf7be15c97b67df59ec9d88cf3a3cda17ffc42f7e30a","signer":"crovia.substrate","subject":{"observed_at":"2026-05-19T04:43:36Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.12969"},"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":"4ddbe3d836b009890c55998ec8a677e8ca75ed993104059cae8cfd9f881a034a","leaf_index":143237,"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":"4e1d03b3d9d47f5fb5fc8320239799a9aa5508fe9fc09ad3b755519ddc7aacc3","side":"left"},{"sibling":"32261259e24a6448c0e1742f2e5b8a0ee39e6adbdb6c6a158649269d01a2c3cc","side":"right"},{"sibling":"af19e7a3ca36322feded39f68d3d5ecfed77fca0a68310717caf55787b739cfa","side":"left"},{"sibling":"fb117aa6aedda7d014808bb032a48c80261c2863a08e3fe0770492dea268d821","side":"right"},{"sibling":"86579110f602643a4103181b38f987b91757b355da09dad7ce102acacae514a3","side":"right"},{"sibling":"e140fc56328315cf4260895eeeb50be071df16908f3fd8c26fc876c96ab11efd","side":"right"},{"sibling":"90929545ee8d8f55c8ea6dee6d4b9a4ca185dbac0746bd58350403aced73709e","side":"right"},{"sibling":"3462f9bd46b6db7df83e5ce51770dc15b529a075237329cfb3722200065e765e","side":"left"},{"sibling":"b986468aca0b7804b8a608705cafc663139e79ff550a69be0b9dd58ec70714f7","side":"left"},{"sibling":"db97141c585f6a1e6bebe92b3ea300ea0f38a2321ca286d85850b11b2dd162a6","side":"left"},{"sibling":"202f1bead178ef3785968d50d3d188264a95192a077654c331612e04a34cbfbe","side":"left"},{"sibling":"72249c8c8b068386e35d16f4bd0bbeb9ba820ca217ef0f0d28396c9fe493f5f0","side":"left"},{"sibling":"ea64599340f7ffdf17ad0cbc1d9401ef8870a347e3847bdc106d06b1673df09c","side":"right"},{"sibling":"8f4c0fbe56b6c010fbb8c782ebcd478079bb3f991d8704e2534209a075d9163c","side":"left"},{"sibling":"4db1f363729507e27a60851cf6ed334d7b9acdef194ed7d419aba4d2bd367a4a","side":"right"},{"sibling":"a86ee18c45e7fcc408b6007eaece05aa75b2d9ae30252e9e878462b4dffbef7b","side":"right"},{"sibling":"1d18e7663d43ccff0122ecc7ee12645bb16afb607b218e81b1ea2408f863cb78","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":143302,"merkle_root":"999156d40a7c61d9ddd52b7338f3cbda3e68f53bace070c7b616ea194e23b123","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260519T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-19T05:37:30Z","sig_algorithm":"ed25519","signature":"b1a252cc66ff32bed1d10dd88a6b2a200e3856d3dbcfcc4ee55e02e00f3d548e854ed9c544704b222bd5d315492c4a935ba2d90d727c585a67899b0ad602fc05","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_f2d1c564b0234f37e502a9dfce08578adf6142ea85f90381fdd8fc7c6571aafc"}}