{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KORTA25IQMY64FPLUQSSGRKB3O","short_pith_number":"pith:KORTA25I","canonical_record":{"source":{"id":"2606.29296","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-28T09:36:43Z","cross_cats_sorted":[],"title_canon_sha256":"0ae0bda9661b5f8e08a0faa3cc4630bc7e4f808e485ad302094fd6d5d92f2b36","abstract_canon_sha256":"9f1261590861dcaada965ebcc332b59d0f8f6787a99a3fe444ef5742b0602f42"},"schema_version":"1.0"},"canonical_sha256":"53a3306ba88331ee15eba425234541dba04c881984753f9e45c98730f9b54728","source":{"kind":"arxiv","id":"2606.29296","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.29296","created_at":"2026-06-30T01:18:00Z"},{"alias_kind":"arxiv_version","alias_value":"2606.29296v1","created_at":"2026-06-30T01:18:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29296","created_at":"2026-06-30T01:18:00Z"},{"alias_kind":"pith_short_12","alias_value":"KORTA25IQMY6","created_at":"2026-06-30T01:18:00Z"},{"alias_kind":"pith_short_16","alias_value":"KORTA25IQMY64FPL","created_at":"2026-06-30T01:18:00Z"},{"alias_kind":"pith_short_8","alias_value":"KORTA25I","created_at":"2026-06-30T01:18:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KORTA25IQMY64FPLUQSSGRKB3O","target":"record","payload":{"canonical_record":{"source":{"id":"2606.29296","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-28T09:36:43Z","cross_cats_sorted":[],"title_canon_sha256":"0ae0bda9661b5f8e08a0faa3cc4630bc7e4f808e485ad302094fd6d5d92f2b36","abstract_canon_sha256":"9f1261590861dcaada965ebcc332b59d0f8f6787a99a3fe444ef5742b0602f42"},"schema_version":"1.0"},"canonical_sha256":"53a3306ba88331ee15eba425234541dba04c881984753f9e45c98730f9b54728","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:18:00.617358Z","signature_b64":"jXpu9i832zsSTItmqr/SkuIXRoCRkMFvXdVcEtEw/9sqCRiuAvGCNd0133j87AZDqWbAtbDBkzeGecM5cgLWCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53a3306ba88331ee15eba425234541dba04c881984753f9e45c98730f9b54728","last_reissued_at":"2026-06-30T01:18:00.616833Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:18:00.616833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.29296","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-30T01:18:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uh2AiubDv3D6CyZqpBtP084n7uh5HCuN9EQ+sHfgo05l1WW3uvsyqSZqNWzOpbJVKp4Rn/btX2A+DWCfWpZGCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T19:49:56.937364Z"},"content_sha256":"792fd7999022790ed35afd0eff611d72a06c5de83e97ee8fb29656ba90037327","schema_version":"1.0","event_id":"sha256:792fd7999022790ed35afd0eff611d72a06c5de83e97ee8fb29656ba90037327"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KORTA25IQMY64FPLUQSSGRKB3O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Process Advantage Signal Shaping: A Paradigm-Agnostic Middleware for Process-Supervised RL in LLM Reasoners","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chao Wang, Hongtao Tian, Tao Yang, Ting Yao, Wenbo Ding, Yunsheng Shi","submitted_at":"2026-06-28T09:36:43Z","abstract_excerpt":"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 p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29296","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.29296/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-30T01:18:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VmQI6cq7ZIEkiLT9WZ35cSpyv5kn944EzLYfKxjQ1Is2PHjtZA9L3BSYpGlRr7haRMruCjrfzloRsSehMcKfAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T19:49:56.937752Z"},"content_sha256":"2e2a8ac7e5c4f953071e15b1e321827e2c0c2e1167dad7ba855303f1f748a750","schema_version":"1.0","event_id":"sha256:2e2a8ac7e5c4f953071e15b1e321827e2c0c2e1167dad7ba855303f1f748a750"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KORTA25IQMY64FPLUQSSGRKB3O/bundle.json","state_url":"https://pith.science/pith/KORTA25IQMY64FPLUQSSGRKB3O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KORTA25IQMY64FPLUQSSGRKB3O/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-02T19:49:56Z","links":{"resolver":"https://pith.science/pith/KORTA25IQMY64FPLUQSSGRKB3O","bundle":"https://pith.science/pith/KORTA25IQMY64FPLUQSSGRKB3O/bundle.json","state":"https://pith.science/pith/KORTA25IQMY64FPLUQSSGRKB3O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KORTA25IQMY64FPLUQSSGRKB3O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KORTA25IQMY64FPLUQSSGRKB3O","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9f1261590861dcaada965ebcc332b59d0f8f6787a99a3fe444ef5742b0602f42","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-28T09:36:43Z","title_canon_sha256":"0ae0bda9661b5f8e08a0faa3cc4630bc7e4f808e485ad302094fd6d5d92f2b36"},"schema_version":"1.0","source":{"id":"2606.29296","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.29296","created_at":"2026-06-30T01:18:00Z"},{"alias_kind":"arxiv_version","alias_value":"2606.29296v1","created_at":"2026-06-30T01:18:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29296","created_at":"2026-06-30T01:18:00Z"},{"alias_kind":"pith_short_12","alias_value":"KORTA25IQMY6","created_at":"2026-06-30T01:18:00Z"},{"alias_kind":"pith_short_16","alias_value":"KORTA25IQMY64FPL","created_at":"2026-06-30T01:18:00Z"},{"alias_kind":"pith_short_8","alias_value":"KORTA25I","created_at":"2026-06-30T01:18:00Z"}],"graph_snapshots":[{"event_id":"sha256:2e2a8ac7e5c4f953071e15b1e321827e2c0c2e1167dad7ba855303f1f748a750","target":"graph","created_at":"2026-06-30T01:18:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.29296/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"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 p","authors_text":"Chao Wang, Hongtao Tian, Tao Yang, Ting Yao, Wenbo Ding, Yunsheng Shi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-28T09:36:43Z","title":"Process Advantage Signal Shaping: A Paradigm-Agnostic Middleware for Process-Supervised RL in LLM Reasoners"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29296","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:792fd7999022790ed35afd0eff611d72a06c5de83e97ee8fb29656ba90037327","target":"record","created_at":"2026-06-30T01:18:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9f1261590861dcaada965ebcc332b59d0f8f6787a99a3fe444ef5742b0602f42","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-28T09:36:43Z","title_canon_sha256":"0ae0bda9661b5f8e08a0faa3cc4630bc7e4f808e485ad302094fd6d5d92f2b36"},"schema_version":"1.0","source":{"id":"2606.29296","kind":"arxiv","version":1}},"canonical_sha256":"53a3306ba88331ee15eba425234541dba04c881984753f9e45c98730f9b54728","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53a3306ba88331ee15eba425234541dba04c881984753f9e45c98730f9b54728","first_computed_at":"2026-06-30T01:18:00.616833Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T01:18:00.616833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jXpu9i832zsSTItmqr/SkuIXRoCRkMFvXdVcEtEw/9sqCRiuAvGCNd0133j87AZDqWbAtbDBkzeGecM5cgLWCQ==","signature_status":"signed_v1","signed_at":"2026-06-30T01:18:00.617358Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.29296","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:792fd7999022790ed35afd0eff611d72a06c5de83e97ee8fb29656ba90037327","sha256:2e2a8ac7e5c4f953071e15b1e321827e2c0c2e1167dad7ba855303f1f748a750"],"state_sha256":"8a2ee7fde8b1d97aa9c3e39d859358d63516e2eb6d08b466a756e4703be89582"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0UZZqbKWObj5ABxukStSUozgz4jCjiaQVtMj0MTHCXzVhgOxTJAw3CL+Yco02WVADEi/RYbx8kJfMgU9rW/LCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T19:49:56.939724Z","bundle_sha256":"5385efb3aaca7a4d62c7e3d0757452cddcba139178ad59785b3998f1e5196d75"}}