{"_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_3cd858556327fe384fe1aafacee58e8db96fd24c25f76a5d2a0926a22a8af567","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_3cd858556327fe384fe1aafacee58e8db96fd24c25f76a5d2a0926a22a8af567","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"f650f3fd4109b0655a2b12b2d4c921f8a3a8627fdca841b05f7f6a38e0783813","published":"Tue, 30 Jun 2026 00:00:00 -0400","receipt_hash":"f650f3fd4109b0655a2b12b2d4c921f8a3a8627fdca841b05f7f6a38e0783813","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":"f650f3fd4109b0655a2b12b2d4c921f8a3a8627fdca841b05f7f6a38e0783813","observed_at":"2026-06-30T04:43:04.087680Z","parent_run_hash":"74f7ab392cc702044101fe24a76a2fdad11164cd79ce725aad6c446a477e89c5","published":"Tue, 30 Jun 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:2606.29296v1 Announce Type: new \nAbstract: Group Relative Policy Optimization (GRPO) is a default recipe for process-supervised reinforcement learning of LLM reasoners, and dense process supervision -- via learned process reward models (PRMs) or on-policy-distillation KL signals -- is a common way to densify its otherwise weak outcome reward. Layering such a step-level signal on top of GRPO's group-standardized advantage, however, exposes three structural pathologies: \\emph{channel contamination} between the pooled process, outcome, and format streams at group standardization; \\emph{resolution mismatch} between the granularity of the process signal and the granularity of the logical decisions being credited; and a \\emph{cumulative trap} by which GRPO's return-to-go sum surfaces either length inflation or truncated exploration depending on the sign regime of the signal. We propose \\textbf{PASS} (\\emph{Process Advantage Signal Shaping}), a compact middleware that sits between any s","title":"Process Advantage Signal Shaping: A Paradigm-Agnostic Middleware for Process-Supervised RL in LLM Reasoners","url":"https://arxiv.org/abs/2606.29296","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.29296v1 Announce Type: new \nAbstract: Group Relative Policy Optimization (GRPO) is a default recipe for process-supervised reinforcement learning of LLM reasoners, and dense process supervision -- via learned process reward models (PRMs) or on-policy-distillation KL signals -- is a common way to densify its otherwise weak outcome reward. Layering such a step-level signal on top of GRPO's group-standardized advantage, however, exposes three structural pathologies: \\emph{channel contamination} between the pooled process, outcome, and format streams at group standardization; \\emph{resolution mismatch} between the granularity of the process signal and the granularity of the logical decisions being credited; and a \\emph{cumulative trap} by which GRPO's return-to-go sum surfaces either length inflation or truncated exploration depending on the sign regime of the signal. We propose \\textbf{PASS} (\\emph{Process Advantage Signal Shaping}), a compact middleware that sits between any s","title":"Process Advantage Signal Shaping: A Paradigm-Agnostic Middleware for Process-Supervised RL in LLM Reasoners","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-30T04:43:04Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.29296"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:030c062e8cf78b208e468aef9608d911657c287074fecc98624b2a64c84fdbf37bd257553b86cb43ef135f4c875871ac3e9860a2bdb38f46a2d3585ffe461806","signer":"crovia.substrate","subject":{"observed_at":"2026-06-30T04:43:04Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.29296"},"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":"f50adf1ead2aac4378083dea0bc33a7693940ada85ada4baaa076e2cf5ac2295","leaf_index":264640,"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":"612405d1ed641ca6c7d0056934898d101f9ec1c25f7e6ffef5ed128cf9e329e7","side":"right"},{"sibling":"ce99a6be372100ead82f95736845bd95252d18e6e0f03139589cb66b3dbed372","side":"right"},{"sibling":"a47806fe6589ba1fc4e467124429865252903cb34233e71e4c29ad8f4653e2fb","side":"right"},{"sibling":"11d81d6c043fc05ffdef211d36bdf283b7a05eb9a82d8b4a053f5d3db9672c2d","side":"right"},{"sibling":"b900ee396a5584fae1fdea34a878f46cb398e9728c0c6dddeb66939681f3351e","side":"right"},{"sibling":"0a27664369302f0956d74b2834cdf1f3aec65e09110e09edfc2d796fc639a390","side":"right"},{"sibling":"47460e4ad3c750350537b3d1cfaa7edcd6bdd9654e146d3d3828bac68075ac72","side":"left"},{"sibling":"0adb33f90b5325f1bcd6d9d08abc79306f0275cec357b6a5d5a9aeb8dae006eb","side":"left"},{"sibling":"a18aac5bf38684ad71f816483beee037e0b60af41587ea19ba92b263e2076d3e","side":"left"},{"sibling":"e814db3b1e34c91aa2d674ee041f8e093e00869024c9f6f8c4d72cab70c3a87e","side":"right"},{"sibling":"23994bf0974e5c9c7f63a61b4f0a48b0ca756a4adc34a8f85f878e774c37dfbe","side":"right"},{"sibling":"f9b4bed84fa6990c71ad2887c91bda183001f05f6b648f21d1273045a26b11fd","side":"left"},{"sibling":"173d2dc4b29ee04ea41d6d0ebc334c4bc2d46e7ee4230c94765413f24fb4bc42","side":"right"},{"sibling":"112461f7c0ec411116fb5c6c90fe95cea9d8f188b9fe08afe25a837ac02d0071","side":"right"},{"sibling":"ea9488204352c49db8f7daf05eefcd7628ecf9413830346674801a99d0654a94","side":"right"},{"sibling":"6261c13b9922cb657f10d1e5d36ec15d8771cf8766e36c61dcbffb7bed57e396","side":"right"},{"sibling":"fa19aa3faf287618b820bcfceebb366152ad521dd20ef9f51e977816663e448b","side":"right"},{"sibling":"c32f943406b62d1fc59b7f7e243492174c8e1caba8c8a2705f86c773315736e0","side":"right"},{"sibling":"1cecb7f447febd025aac272837c80de218aecc6485d2395a509b2a1f1b9c746e","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":265374,"merkle_root":"9636001ecab173cb6af10dc7c71eb14585daa62f9c0a6f027046f05633156891","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260630T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-30T05:38:03Z","sig_algorithm":"ed25519","signature":"6d4b8fd9b9da856cbb5fba7540877c6a63fa18a5ec3eaf28dc4d6d1c64921c9c0565f8c95f4b7aec0e7744fd7754844f051baf863db708cad768765b416a7b0c","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_3cd858556327fe384fe1aafacee58e8db96fd24c25f76a5d2a0926a22a8af567"}}