{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LKDC5EVBTAIZWCBIBJTBDKSAQ2","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":"38a9c0a132d78f5fb18aadccf9d72277b6d5258a12ca48f61ef67b673767111e","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-24T18:58:51Z","title_canon_sha256":"3ab46ee6207538fac2627bd27c6b2c140dbd52298f6aa7ee00b7a3b0c47193ad"},"schema_version":"1.0","source":{"id":"2505.18830","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18830","created_at":"2026-07-05T11:09:20Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18830v1","created_at":"2026-07-05T11:09:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18830","created_at":"2026-07-05T11:09:20Z"},{"alias_kind":"pith_short_12","alias_value":"LKDC5EVBTAIZ","created_at":"2026-07-05T11:09:20Z"},{"alias_kind":"pith_short_16","alias_value":"LKDC5EVBTAIZWCBI","created_at":"2026-07-05T11:09:20Z"},{"alias_kind":"pith_short_8","alias_value":"LKDC5EVB","created_at":"2026-07-05T11:09:20Z"}],"graph_snapshots":[{"event_id":"sha256:b3464e3fd133f28b86042c86b0175d858d3cb9b7ee937780c03e6f3b2cab21a6","target":"graph","created_at":"2026-07-05T11:09:20Z","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/2505.18830/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has become popular in enhancing the reasoning capabilities of large language models (LLMs), with Group Relative Policy Optimization (GRPO) emerging as a widely used algorithm in recent systems. Despite GRPO's widespread adoption, we identify a previously unrecognized phenomenon we term Lazy Likelihood Displacement (LLD), wherein the likelihood of correct responses marginally increases or even decreases during training. This behavior mirrors a recently discovered misalignment issue in Direct Preference Optimization (DPO), attributed to the influence of negative gradi","authors_text":"Christos Thrampoulidis, Danica J. Sutherland, Muchen Li, Wenlong Deng, Xiaoxiao Li, Yi Ren","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-24T18:58:51Z","title":"On the Effect of Negative Gradient in Group Relative Deep Reinforcement Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18830","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:e1e0d2105c1348913858902414f47e4ae16d5875e85dc93ca81f2be0de0f3c33","target":"record","created_at":"2026-07-05T11:09:20Z","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":"38a9c0a132d78f5fb18aadccf9d72277b6d5258a12ca48f61ef67b673767111e","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-24T18:58:51Z","title_canon_sha256":"3ab46ee6207538fac2627bd27c6b2c140dbd52298f6aa7ee00b7a3b0c47193ad"},"schema_version":"1.0","source":{"id":"2505.18830","kind":"arxiv","version":1}},"canonical_sha256":"5a862e92a198119b08280a6611aa4086a55c451ca844be3fff317c1cfdec73e6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a862e92a198119b08280a6611aa4086a55c451ca844be3fff317c1cfdec73e6","first_computed_at":"2026-07-05T11:09:20.213467Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:20.213467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y04rI3OAWB6kMLwE2kdmyHqLGSSYHl7h3iDGqZURUIOUuGIwgt0u0JS1w8vwe6Y9HjIH4wYe44KeAAudVdDICg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:20.213942Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.18830","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e1e0d2105c1348913858902414f47e4ae16d5875e85dc93ca81f2be0de0f3c33","sha256:b3464e3fd133f28b86042c86b0175d858d3cb9b7ee937780c03e6f3b2cab21a6"],"state_sha256":"7da57c8dcb3da87668a63c30c44c63f6629a4d1dc24e56637b14d98389eb0d09"}