{"_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_26f79a8ab5925f9335994d2c9b56eda0dc32d3f67a5160b7b2ee13a4af7488ae","bitcoin_anchor":{"bitcoin_attestations":["bitcoin_block_949451"],"calendar_attestations":["https://finney.calendar.eternitywall.com","https://btc.calendar.catallaxy.com","https://alice.btc.calendar.opentimestamps.org","https://bob.btc.calendar.opentimestamps.org"],"ots_url":"/registry/data/substrate/anchors/77fc9c28fae777b81da5b495b3115474df6592dfac590333213d3bdf8b94a9b3.ots","stamped_at":"2026-05-15T03:00:03Z","status":"bitcoin"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_26f79a8ab5925f9335994d2c9b56eda0dc32d3f67a5160b7b2ee13a4af7488ae","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"9067046b81fbb61e5fd8946fa49e4fd8122490ccfea3d383b2dc1d706174a53a","published":"Thu, 07 May 2026 00:00:00 -0400","receipt_hash":"9067046b81fbb61e5fd8946fa49e4fd8122490ccfea3d383b2dc1d706174a53a","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":"9067046b81fbb61e5fd8946fa49e4fd8122490ccfea3d383b2dc1d706174a53a","observed_at":"2026-05-07T04:43:30.601849Z","parent_run_hash":"b20b3beeadde500bb99eda3b869d50b00c5259b2c78c650d83e786ac81b85801","published":"Thu, 07 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:2605.02944v1 Announce Type: cross \nAbstract: Reinforcement learning (RL) from unit-test feedback has become a standard post-training recipe for improving large language models (LLMs) on code generation. However, the pass-all-tests binary reward can be sparse, yielding no learning signal on challenging problems where none of the sampled solutions passes all tests. A common remedy is to use the test-case pass rate as a surrogate reward.\n  In this work, we study pass-rate rewards in critic-free RL for code generation (e.g., GRPO and RLOO) and report a consistent pattern across base models and algorithms: despite alleviating reward sparsity, pass-rate rewards do not reliably improve final performance over binary rewards in rigorous controlled experiments.\n  To understand this discrepancy, we analyze reward density and the resulting gradient directions. We find that pass-rate rewards are denser, but the induced gradient updates do not consistently move probability mass toward full-pas","title":"Exploring Pass-Rate Reward in Reinforcement Learning for Code Generation","url":"https://arxiv.org/abs/2605.02944","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.02944v1 Announce Type: cross \nAbstract: Reinforcement learning (RL) from unit-test feedback has become a standard post-training recipe for improving large language models (LLMs) on code generation. However, the pass-all-tests binary reward can be sparse, yielding no learning signal on challenging problems where none of the sampled solutions passes all tests. A common remedy is to use the test-case pass rate as a surrogate reward.\n  In this work, we study pass-rate rewards in critic-free RL for code generation (e.g., GRPO and RLOO) and report a consistent pattern across base models and algorithms: despite alleviating reward sparsity, pass-rate rewards do not reliably improve final performance over binary rewards in rigorous controlled experiments.\n  To understand this discrepancy, we analyze reward density and the resulting gradient directions. We find that pass-rate rewards are denser, but the induced gradient updates do not consistently move probability mass toward full-pas","title":"Exploring Pass-Rate Reward in Reinforcement Learning for Code Generation","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-07T04:43:30Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.02944"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:1031d3aa443fb27cfccea4c6920dfac92ad027c247228c5adc21ea4c98c29dcaee39633c6a35a0f576cdccaba5f92309904823723c369bab805e4a7ca9832803","signer":"crovia.substrate","subject":{"observed_at":"2026-05-07T04:43:30Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.02944"},"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":"ac1b1193beec999dee4d44a945a60017711da076947a4a864fb8445a62306792","leaf_index":118229,"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":"6f1d21823b6da87e7132092be2c7777093b72314f77a98c18eb961523599aff4","side":"left"},{"sibling":"7c84232466dc233ec6258c746e0623e1170c0494fde051c89bbce97954936f73","side":"right"},{"sibling":"1408fc7d50ed00aea058600f298cedcad64bc44062d04dee8f06ffd7fd25520a","side":"left"},{"sibling":"0ac7df9a8dbabd1792ee1b9768862132e3c3cf1d838a2ebea5a5228db04922ad","side":"right"},{"sibling":"cf3b73a5bcd53412dce42bee46d0ed4790d95c8e33fcfd7fde363064744dc114","side":"left"},{"sibling":"c063c39ae694b656fe885810193365d271b3b69afdf3da9ee1836f170f43c681","side":"right"},{"sibling":"1b5d9d099a141dbd9b65685d9424ef07b508b27c0e01ef2b925d1dd5d95de03a","side":"left"},{"sibling":"c25c853cb3dd8c7f1b99fc80fd602c044932de34c1b34bd69ab1d5b8c94e42b1","side":"left"},{"sibling":"3d3124224341dac361f0e93f24f70795342ba216dc1c0065e7fa7592d943b488","side":"left"},{"sibling":"438bef084db8613e8143527769e3c677e12a59f8a6e2dea114f88afab0446a43","side":"right"},{"sibling":"8e758a4477dfc0838d2e8ea2bdbd583bc3192683e75fd9cde217ee6a3b2f3ac8","side":"left"},{"sibling":"4219f746e463e594ccd6447debdf736a57e77319b12bcb74d8ece2b5860064c6","side":"left"},{"sibling":"05f89b32c00462e60adf95c1fe4579cdc2791b36e8b17573d8f3b5fd5da95a0b","side":"right"},{"sibling":"8ccd9937a2c0d5c04044d07d1557791b7d07bb31eac41a39a675608d44b38f23","side":"right"},{"sibling":"3a5e69cf0803f4c91f3895ed7c9a95748fef240bec4422e167c05300f79f06c0","side":"left"},{"sibling":"f2817ab288b5324fe49770372c7a10f33f7cd11005f8d4c0a730316f5229dc98","side":"left"},{"sibling":"725fac972e772ca0dc598810ea1abc70df472f72d2d6ab8a0baee2b80e5d2f4c","side":"left"},{"sibling":"98fc57dfef8873b512edc8340f7181df57302bb96777625e072235c62d7c5895","side":"right"}]},"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":134292,"merkle_root":"77fc9c28fae777b81da5b495b3115474df6592dfac590333213d3bdf8b94a9b3","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260515T023701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-15T02:37:25Z","sig_algorithm":"ed25519","signature":"68107a834b00b24f5d4501e5ec727445311f132a486567ecc4c72a4e6dff24c8c21f2de3105293353ba5fdbe370d032819af6aa70f694e2e39b6af6737507009","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_26f79a8ab5925f9335994d2c9b56eda0dc32d3f67a5160b7b2ee13a4af7488ae"}}