{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:IJHYJWCC7YP6LJPF5AS6DOJA2O","short_pith_number":"pith:IJHYJWCC","canonical_record":{"source":{"id":"2605.19461","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-19T07:13:00Z","cross_cats_sorted":[],"title_canon_sha256":"89fd0952555b7ba2d5f22df70deffaba80a12f66653fb1ca728e59c387683eb5","abstract_canon_sha256":"f1c2984de532e1821df695509ac3a9632fdf144fa7df790d1bf87639459cda76"},"schema_version":"1.0"},"canonical_sha256":"424f84d842fe1fe5a5e5e825e1b920d39bf13dae59ca10da968f53356848d33e","source":{"kind":"arxiv","id":"2605.19461","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:IJHYJWCC7YP6LJPF5AS6DOJA2O","target":"record","payload":{"canonical_record":{"source":{"id":"2605.19461","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-19T07:13:00Z","cross_cats_sorted":[],"title_canon_sha256":"89fd0952555b7ba2d5f22df70deffaba80a12f66653fb1ca728e59c387683eb5","abstract_canon_sha256":"f1c2984de532e1821df695509ac3a9632fdf144fa7df790d1bf87639459cda76"},"schema_version":"1.0"},"canonical_sha256":"424f84d842fe1fe5a5e5e825e1b920d39bf13dae59ca10da968f53356848d33e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:05:47.032402Z","signature_b64":"ge8VR5XRcOuUUC9Ru/We0f8Dtr5its2HmyNkAJBlHahIHm5M+J/zVbwWp+v3SOSfq5hnWSzj2ZdIO9VfaBsMCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"424f84d842fe1fe5a5e5e825e1b920d39bf13dae59ca10da968f53356848d33e","last_reissued_at":"2026-05-20T01:05:47.031649Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:05:47.031649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.19461","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":"2026-05-20T01:05:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"argtVstuiq9ZQFvJLsd5NLC4CEvJaBg1WrrsNNU9nLxLXP1NGrx4WGoFqkP1FEjmoX4jYFXINsH4MiyVPO41Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T22:26:55.764299Z"},"content_sha256":"11c95592eeff5092fd4a9c40fa2b6a008eee0c8c70f238a008760e61baa6f03b","schema_version":"1.0","event_id":"sha256:11c95592eeff5092fd4a9c40fa2b6a008eee0c8c70f238a008760e61baa6f03b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:IJHYJWCC7YP6LJPF5AS6DOJA2O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Mode Collapse: Distribution Matching for Diverse Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","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","submitted_at":"2026-05-19T07:13:00Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19461","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/2605.19461/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":"2026-05-20T01:05:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FhJAttTYZ0o5lq/7Ur2wjC4wLB0anB7FfmpFWDWzZxZOeIwIoQdWLR57NSNP1nH02fbcF3HquAWOjcArrlKgBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T22:26:55.764703Z"},"content_sha256":"2e55d927292c2c96087162cbeeed415dba5062cd17fedad20f1a057c901d74bd","schema_version":"1.0","event_id":"sha256:2e55d927292c2c96087162cbeeed415dba5062cd17fedad20f1a057c901d74bd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IJHYJWCC7YP6LJPF5AS6DOJA2O/bundle.json","state_url":"https://pith.science/pith/IJHYJWCC7YP6LJPF5AS6DOJA2O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IJHYJWCC7YP6LJPF5AS6DOJA2O/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":"2026-05-21T22:26:55Z","links":{"resolver":"https://pith.science/pith/IJHYJWCC7YP6LJPF5AS6DOJA2O","bundle":"https://pith.science/pith/IJHYJWCC7YP6LJPF5AS6DOJA2O/bundle.json","state":"https://pith.science/pith/IJHYJWCC7YP6LJPF5AS6DOJA2O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IJHYJWCC7YP6LJPF5AS6DOJA2O/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"825jgBKIU++s4qORLH56Ky8blQcboiqKeCAxmmbY1IXgGThggmkj1LFlaEJ2TItDrjsorAfqpcpO7ntyCiQ1DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T22:26:55.767079Z","bundle_sha256":"b8c8140410d9114ed980e410c55e44d0d2006e66eafb4fcec011a6505a0bf265"}}