{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:P4HS375LJX5JVRHKLJLWVSPZPR","short_pith_number":"pith:P4HS375L","canonical_record":{"source":{"id":"2507.21848","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-29T14:23:58Z","cross_cats_sorted":[],"title_canon_sha256":"e88601ae0756490950f4768c3636c29538e341f0d0ad4f8fc695cfed8c5ab174","abstract_canon_sha256":"b8d164e87e3ff4d13a0216498917c5db8110ddd61cdc23ca607cc60140f17fbb"},"schema_version":"1.0"},"canonical_sha256":"7f0f2dffab4dfa9ac4ea5a576ac9f97c4316c0a7ddd3c23f6dbf958134d48add","source":{"kind":"arxiv","id":"2507.21848","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.21848","created_at":"2026-07-05T11:45:08Z"},{"alias_kind":"arxiv_version","alias_value":"2507.21848v1","created_at":"2026-07-05T11:45:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.21848","created_at":"2026-07-05T11:45:08Z"},{"alias_kind":"pith_short_12","alias_value":"P4HS375LJX5J","created_at":"2026-07-05T11:45:08Z"},{"alias_kind":"pith_short_16","alias_value":"P4HS375LJX5JVRHK","created_at":"2026-07-05T11:45:08Z"},{"alias_kind":"pith_short_8","alias_value":"P4HS375L","created_at":"2026-07-05T11:45:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:P4HS375LJX5JVRHKLJLWVSPZPR","target":"record","payload":{"canonical_record":{"source":{"id":"2507.21848","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-29T14:23:58Z","cross_cats_sorted":[],"title_canon_sha256":"e88601ae0756490950f4768c3636c29538e341f0d0ad4f8fc695cfed8c5ab174","abstract_canon_sha256":"b8d164e87e3ff4d13a0216498917c5db8110ddd61cdc23ca607cc60140f17fbb"},"schema_version":"1.0"},"canonical_sha256":"7f0f2dffab4dfa9ac4ea5a576ac9f97c4316c0a7ddd3c23f6dbf958134d48add","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:08.658868Z","signature_b64":"5pqtFhSnoIxgsLxdy1lZNMymQ1BagUHgy71B6swHmQhSWVT7pSc+inUMX1vIrGbd5X61UDF3sMpZ5LU2LOxbCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f0f2dffab4dfa9ac4ea5a576ac9f97c4316c0a7ddd3c23f6dbf958134d48add","last_reissued_at":"2026-07-05T11:45:08.658433Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:08.658433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.21848","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":"2026-07-05T11:45:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6NYUmi6BG3Qy6ipo+RXcNF9ed7uPmjpPhx8UltlVXPk93hSDEhV3spk9aiVOdn2tGqYP9z3/zktKJmc6APOlDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T18:04:55.583505Z"},"content_sha256":"6c2770542ca11a8a6ae8494d2f5545e2158c924d2e37342daaa66416748d99e0","schema_version":"1.0","event_id":"sha256:6c2770542ca11a8a6ae8494d2f5545e2158c924d2e37342daaa66416748d99e0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:P4HS375LJX5JVRHKLJLWVSPZPR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Lei Huang, Siwei Wen, Wenjun Wu, Xingjian Zhang","submitted_at":"2025-07-29T14:23:58Z","abstract_excerpt":"Large Language Models (LLMs) have made remarkable progress in enhancing step-by-step reasoning through reinforcement learning. However, the Group Relative Policy Optimization (GRPO) algorithm, which relies on sparse reward rules, often encounters the issue of identical rewards within groups, leading to the advantage collapse problem. Existing works typically address this challenge from two perspectives: enforcing model reflection to enhance response diversity, and introducing internal feedback to augment the training signal (advantage). In this work, we begin by analyzing the limitations of mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.21848","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/2507.21848/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":"2026-07-05T11:45:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9UK66FOz5KP4seeonz/aycZPH1XTzrz3toIJaz6jiJ1HrLMjhcrY1skbEGD9L8yrScJBs6Zjg/R5YnYJikrvDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T18:04:55.584035Z"},"content_sha256":"1ce0b6ae85a2bfd525447b2f54b0e73f234b12d1ef21a56046e1ae7129f6e2a5","schema_version":"1.0","event_id":"sha256:1ce0b6ae85a2bfd525447b2f54b0e73f234b12d1ef21a56046e1ae7129f6e2a5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P4HS375LJX5JVRHKLJLWVSPZPR/bundle.json","state_url":"https://pith.science/pith/P4HS375LJX5JVRHKLJLWVSPZPR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P4HS375LJX5JVRHKLJLWVSPZPR/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":"2026-08-04T18:04:55Z","links":{"resolver":"https://pith.science/pith/P4HS375LJX5JVRHKLJLWVSPZPR","bundle":"https://pith.science/pith/P4HS375LJX5JVRHKLJLWVSPZPR/bundle.json","state":"https://pith.science/pith/P4HS375LJX5JVRHKLJLWVSPZPR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P4HS375LJX5JVRHKLJLWVSPZPR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:P4HS375LJX5JVRHKLJLWVSPZPR","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":"b8d164e87e3ff4d13a0216498917c5db8110ddd61cdc23ca607cc60140f17fbb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-29T14:23:58Z","title_canon_sha256":"e88601ae0756490950f4768c3636c29538e341f0d0ad4f8fc695cfed8c5ab174"},"schema_version":"1.0","source":{"id":"2507.21848","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.21848","created_at":"2026-07-05T11:45:08Z"},{"alias_kind":"arxiv_version","alias_value":"2507.21848v1","created_at":"2026-07-05T11:45:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.21848","created_at":"2026-07-05T11:45:08Z"},{"alias_kind":"pith_short_12","alias_value":"P4HS375LJX5J","created_at":"2026-07-05T11:45:08Z"},{"alias_kind":"pith_short_16","alias_value":"P4HS375LJX5JVRHK","created_at":"2026-07-05T11:45:08Z"},{"alias_kind":"pith_short_8","alias_value":"P4HS375L","created_at":"2026-07-05T11:45:08Z"}],"graph_snapshots":[{"event_id":"sha256:1ce0b6ae85a2bfd525447b2f54b0e73f234b12d1ef21a56046e1ae7129f6e2a5","target":"graph","created_at":"2026-07-05T11:45:08Z","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/2507.21848/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have made remarkable progress in enhancing step-by-step reasoning through reinforcement learning. However, the Group Relative Policy Optimization (GRPO) algorithm, which relies on sparse reward rules, often encounters the issue of identical rewards within groups, leading to the advantage collapse problem. Existing works typically address this challenge from two perspectives: enforcing model reflection to enhance response diversity, and introducing internal feedback to augment the training signal (advantage). In this work, we begin by analyzing the limitations of mo","authors_text":"Lei Huang, Siwei Wen, Wenjun Wu, Xingjian Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-29T14:23:58Z","title":"EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.21848","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":"sha256:6c2770542ca11a8a6ae8494d2f5545e2158c924d2e37342daaa66416748d99e0","target":"record","created_at":"2026-07-05T11:45:08Z","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":"b8d164e87e3ff4d13a0216498917c5db8110ddd61cdc23ca607cc60140f17fbb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-29T14:23:58Z","title_canon_sha256":"e88601ae0756490950f4768c3636c29538e341f0d0ad4f8fc695cfed8c5ab174"},"schema_version":"1.0","source":{"id":"2507.21848","kind":"arxiv","version":1}},"canonical_sha256":"7f0f2dffab4dfa9ac4ea5a576ac9f97c4316c0a7ddd3c23f6dbf958134d48add","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f0f2dffab4dfa9ac4ea5a576ac9f97c4316c0a7ddd3c23f6dbf958134d48add","first_computed_at":"2026-07-05T11:45:08.658433Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:45:08.658433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5pqtFhSnoIxgsLxdy1lZNMymQ1BagUHgy71B6swHmQhSWVT7pSc+inUMX1vIrGbd5X61UDF3sMpZ5LU2LOxbCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:45:08.658868Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.21848","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c2770542ca11a8a6ae8494d2f5545e2158c924d2e37342daaa66416748d99e0","sha256:1ce0b6ae85a2bfd525447b2f54b0e73f234b12d1ef21a56046e1ae7129f6e2a5"],"state_sha256":"c5d2cdec3967b5f979d90a8960699e43aee670071ec3ad548571b7a30700a8a7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pIk0bpVKSLifS6W1N0iJFAbRHW+hL9jbRbNtUrkkRJwUJw1o2o5dqumZDRVpvdSJReyGMiCubcpxN4vguBVqCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T18:04:55.588724Z","bundle_sha256":"8335dc8a11435829786a7b995b1a4eb834ddcb11e667ac4f61134702be356f62"}}