{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IJHYJWCC7YP6LJPF5AS6DOJA2O","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":"f1c2984de532e1821df695509ac3a9632fdf144fa7df790d1bf87639459cda76","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-19T07:13:00Z","title_canon_sha256":"89fd0952555b7ba2d5f22df70deffaba80a12f66653fb1ca728e59c387683eb5"},"schema_version":"1.0","source":{"id":"2605.19461","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.19461","created_at":"2026-05-20T01:05:47Z"},{"alias_kind":"arxiv_version","alias_value":"2605.19461v1","created_at":"2026-05-20T01:05:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19461","created_at":"2026-05-20T01:05:47Z"},{"alias_kind":"pith_short_12","alias_value":"IJHYJWCC7YP6","created_at":"2026-05-20T01:05:47Z"},{"alias_kind":"pith_short_16","alias_value":"IJHYJWCC7YP6LJPF","created_at":"2026-05-20T01:05:47Z"},{"alias_kind":"pith_short_8","alias_value":"IJHYJWCC","created_at":"2026-05-20T01:05:47Z"}],"graph_snapshots":[{"event_id":"sha256:2e55d927292c2c96087162cbeeed415dba5062cd17fedad20f1a057c901d74bd","target":"graph","created_at":"2026-05-20T01:05:47Z","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/2605.19461/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-policy reinforcement learning methods like GRPO suffer from mode collapse: they exhibit reduced solution diversity, concentrating probability mass on a single solution once discovered and ceasing exploration of alternative strategies. We show this stems from reverse KL minimization's mode-seeking behavior, which reinforces the first high-reward trajectory found rather than maintaining a distribution over multiple diverse solutions. We propose DMPO (Distribution-Matching Policy Optimization), which prevents mode collapse through principled approximation of forward KL minimization. DMPO const","authors_text":"Dahua Lin, Kai Chen, Linyang Li, Peiji Li, Qingwen Liu, Qipeng Guo, Shengyuan Ding, Tianyi Lyu, Xiaozhe Li, Xinyu Fang, Yang Li, Yichuan Ma, Yongkang Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-19T07:13:00Z","title":"Beyond Mode Collapse: Distribution Matching for Diverse Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19461","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":"sha256:11c95592eeff5092fd4a9c40fa2b6a008eee0c8c70f238a008760e61baa6f03b","target":"record","created_at":"2026-05-20T01:05:47Z","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":"f1c2984de532e1821df695509ac3a9632fdf144fa7df790d1bf87639459cda76","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-19T07:13:00Z","title_canon_sha256":"89fd0952555b7ba2d5f22df70deffaba80a12f66653fb1ca728e59c387683eb5"},"schema_version":"1.0","source":{"id":"2605.19461","kind":"arxiv","version":1}},"canonical_sha256":"424f84d842fe1fe5a5e5e825e1b920d39bf13dae59ca10da968f53356848d33e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"424f84d842fe1fe5a5e5e825e1b920d39bf13dae59ca10da968f53356848d33e","first_computed_at":"2026-05-20T01:05:47.031649Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:05:47.031649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ge8VR5XRcOuUUC9Ru/We0f8Dtr5its2HmyNkAJBlHahIHm5M+J/zVbwWp+v3SOSfq5hnWSzj2ZdIO9VfaBsMCw==","signature_status":"signed_v1","signed_at":"2026-05-20T01:05:47.032402Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.19461","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:11c95592eeff5092fd4a9c40fa2b6a008eee0c8c70f238a008760e61baa6f03b","sha256:2e55d927292c2c96087162cbeeed415dba5062cd17fedad20f1a057c901d74bd"],"state_sha256":"9a19a62dab9de1383fd71dc4ed5d6e4a34da848f9509cae96b9c9bcb8621ccad"}