{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CTG6T5OASHEXACNMX2OOZ4OSCP","short_pith_number":"pith:CTG6T5OA","canonical_record":{"source":{"id":"2508.05428","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-07T14:17:28Z","cross_cats_sorted":[],"title_canon_sha256":"8898f84c615346bc46708d74dad63ee492f25150d92e544c4502d63d613ce1e7","abstract_canon_sha256":"236f4be7bb83e0d1cabe547ec3f0538772459878232bc36a0d0a039621aac234"},"schema_version":"1.0"},"canonical_sha256":"14cde9f5c091c97009acbe9cecf1d213e88864f030b38ddfb3266f56f6d65e22","source":{"kind":"arxiv","id":"2508.05428","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.05428","created_at":"2026-07-05T11:50:13Z"},{"alias_kind":"arxiv_version","alias_value":"2508.05428v1","created_at":"2026-07-05T11:50:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.05428","created_at":"2026-07-05T11:50:13Z"},{"alias_kind":"pith_short_12","alias_value":"CTG6T5OASHEX","created_at":"2026-07-05T11:50:13Z"},{"alias_kind":"pith_short_16","alias_value":"CTG6T5OASHEXACNM","created_at":"2026-07-05T11:50:13Z"},{"alias_kind":"pith_short_8","alias_value":"CTG6T5OA","created_at":"2026-07-05T11:50:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CTG6T5OASHEXACNMX2OOZ4OSCP","target":"record","payload":{"canonical_record":{"source":{"id":"2508.05428","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-07T14:17:28Z","cross_cats_sorted":[],"title_canon_sha256":"8898f84c615346bc46708d74dad63ee492f25150d92e544c4502d63d613ce1e7","abstract_canon_sha256":"236f4be7bb83e0d1cabe547ec3f0538772459878232bc36a0d0a039621aac234"},"schema_version":"1.0"},"canonical_sha256":"14cde9f5c091c97009acbe9cecf1d213e88864f030b38ddfb3266f56f6d65e22","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:13.073128Z","signature_b64":"hs2HZ5OnsdCPF3IMpcEGDFBheC54h/rnCct3XmIcHq3D2eHyORJ6v6yDkcrYqzoTnBsDUfiWDmq3frbSiODHCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14cde9f5c091c97009acbe9cecf1d213e88864f030b38ddfb3266f56f6d65e22","last_reissued_at":"2026-07-05T11:50:13.072621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:50:13.072621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.05428","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":"2026-07-05T11:50:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BXIsD9A88m6kIwWtKiEZJ8SILha5jMZ/A4KyUPZiFhkHBEW+WHuwfjgy1InEORDDfz6AuKqj6qO8vrR17BjQBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:45:54.127449Z"},"content_sha256":"42324e4b5c4c1795b499894b206eac33eb44a090db6f1efb5f3c256c5e8caa9b","schema_version":"1.0","event_id":"sha256:42324e4b5c4c1795b499894b206eac33eb44a090db6f1efb5f3c256c5e8caa9b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CTG6T5OASHEXACNMX2OOZ4OSCP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Group Causal Policy Optimization for Post-Training Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Changwen Zheng, Chuxiong Sun, Jingyao Wang, Ran Zuo, Wenwen Qiang, Zeen Song, Ziyin Gu","submitted_at":"2025-08-07T14:17:28Z","abstract_excerpt":"Recent advances in large language models (LLMs) have broadened their applicability across diverse tasks, yet specialized domains still require targeted post training. Among existing methods, Group Relative Policy Optimization (GRPO) stands out for its efficiency, leveraging groupwise relative rewards while avoiding costly value function learning. However, GRPO treats candidate responses as independent, overlooking semantic interactions such as complementarity and contradiction. To address this challenge, we first introduce a Structural Causal Model (SCM) that reveals hidden dependencies among "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.05428","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/2508.05428/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":"2026-07-05T11:50:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3jaevsTL+4oETxNg+LrFwnhcGikRkLXJS/NIOulE3lGAJOchiEnG3kVf3sEYBTh24tX7QJEHPZsfw+KAdAzOAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:45:54.128019Z"},"content_sha256":"6c88e7fc3bc6f11781707c1089f2a9fc3fcd1536593e09ca44a9eece010ef793","schema_version":"1.0","event_id":"sha256:6c88e7fc3bc6f11781707c1089f2a9fc3fcd1536593e09ca44a9eece010ef793"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CTG6T5OASHEXACNMX2OOZ4OSCP/bundle.json","state_url":"https://pith.science/pith/CTG6T5OASHEXACNMX2OOZ4OSCP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CTG6T5OASHEXACNMX2OOZ4OSCP/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":"2026-08-07T00:45:54Z","links":{"resolver":"https://pith.science/pith/CTG6T5OASHEXACNMX2OOZ4OSCP","bundle":"https://pith.science/pith/CTG6T5OASHEXACNMX2OOZ4OSCP/bundle.json","state":"https://pith.science/pith/CTG6T5OASHEXACNMX2OOZ4OSCP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CTG6T5OASHEXACNMX2OOZ4OSCP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CTG6T5OASHEXACNMX2OOZ4OSCP","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":"236f4be7bb83e0d1cabe547ec3f0538772459878232bc36a0d0a039621aac234","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-07T14:17:28Z","title_canon_sha256":"8898f84c615346bc46708d74dad63ee492f25150d92e544c4502d63d613ce1e7"},"schema_version":"1.0","source":{"id":"2508.05428","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.05428","created_at":"2026-07-05T11:50:13Z"},{"alias_kind":"arxiv_version","alias_value":"2508.05428v1","created_at":"2026-07-05T11:50:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.05428","created_at":"2026-07-05T11:50:13Z"},{"alias_kind":"pith_short_12","alias_value":"CTG6T5OASHEX","created_at":"2026-07-05T11:50:13Z"},{"alias_kind":"pith_short_16","alias_value":"CTG6T5OASHEXACNM","created_at":"2026-07-05T11:50:13Z"},{"alias_kind":"pith_short_8","alias_value":"CTG6T5OA","created_at":"2026-07-05T11:50:13Z"}],"graph_snapshots":[{"event_id":"sha256:6c88e7fc3bc6f11781707c1089f2a9fc3fcd1536593e09ca44a9eece010ef793","target":"graph","created_at":"2026-07-05T11:50:13Z","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/2508.05428/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in large language models (LLMs) have broadened their applicability across diverse tasks, yet specialized domains still require targeted post training. Among existing methods, Group Relative Policy Optimization (GRPO) stands out for its efficiency, leveraging groupwise relative rewards while avoiding costly value function learning. However, GRPO treats candidate responses as independent, overlooking semantic interactions such as complementarity and contradiction. To address this challenge, we first introduce a Structural Causal Model (SCM) that reveals hidden dependencies among ","authors_text":"Changwen Zheng, Chuxiong Sun, Jingyao Wang, Ran Zuo, Wenwen Qiang, Zeen Song, Ziyin Gu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-07T14:17:28Z","title":"Group Causal Policy Optimization for Post-Training Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.05428","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":"sha256:42324e4b5c4c1795b499894b206eac33eb44a090db6f1efb5f3c256c5e8caa9b","target":"record","created_at":"2026-07-05T11:50:13Z","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":"236f4be7bb83e0d1cabe547ec3f0538772459878232bc36a0d0a039621aac234","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-07T14:17:28Z","title_canon_sha256":"8898f84c615346bc46708d74dad63ee492f25150d92e544c4502d63d613ce1e7"},"schema_version":"1.0","source":{"id":"2508.05428","kind":"arxiv","version":1}},"canonical_sha256":"14cde9f5c091c97009acbe9cecf1d213e88864f030b38ddfb3266f56f6d65e22","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"14cde9f5c091c97009acbe9cecf1d213e88864f030b38ddfb3266f56f6d65e22","first_computed_at":"2026-07-05T11:50:13.072621Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:50:13.072621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hs2HZ5OnsdCPF3IMpcEGDFBheC54h/rnCct3XmIcHq3D2eHyORJ6v6yDkcrYqzoTnBsDUfiWDmq3frbSiODHCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:50:13.073128Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.05428","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42324e4b5c4c1795b499894b206eac33eb44a090db6f1efb5f3c256c5e8caa9b","sha256:6c88e7fc3bc6f11781707c1089f2a9fc3fcd1536593e09ca44a9eece010ef793"],"state_sha256":"1078d83c4d4caa2a39485da934a18ba88c1fe6338ff82ed99617d891b3ad0f32"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bg2KQ758tfhdFNZbGhUB482BBGP3XpkMJbGFOilNoE/Ycut8pNnrp+xdT7ejMnu5e4aO47KxZZLfIjq7saJQCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T00:45:54.133466Z","bundle_sha256":"c6981f0747324623fce8635684b8697d96150bacf32abc6fbfa7fd1bd3e8afee"}}