{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:XRUI6OAW7LFJP4QLIS5FVOHNOP","short_pith_number":"pith:XRUI6OAW","canonical_record":{"source":{"id":"2606.21090","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-17T18:03:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"95b8fc03068143c614557cc86ff7884ad4d403f518f9eecde045bbd4a8bcf08b","abstract_canon_sha256":"79b8df4eaac28179cd550e64db1a683a2d9a9b5c132fe5df349149b15f81a202"},"schema_version":"1.0"},"canonical_sha256":"bc688f3816faca97f20b44ba5ab8ed73c41313872d030185bab88a266d9d8061","source":{"kind":"arxiv","id":"2606.21090","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.21090","created_at":"2026-06-23T01:12:29Z"},{"alias_kind":"arxiv_version","alias_value":"2606.21090v1","created_at":"2026-06-23T01:12:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21090","created_at":"2026-06-23T01:12:29Z"},{"alias_kind":"pith_short_12","alias_value":"XRUI6OAW7LFJ","created_at":"2026-06-23T01:12:29Z"},{"alias_kind":"pith_short_16","alias_value":"XRUI6OAW7LFJP4QL","created_at":"2026-06-23T01:12:29Z"},{"alias_kind":"pith_short_8","alias_value":"XRUI6OAW","created_at":"2026-06-23T01:12:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:XRUI6OAW7LFJP4QLIS5FVOHNOP","target":"record","payload":{"canonical_record":{"source":{"id":"2606.21090","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-17T18:03:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"95b8fc03068143c614557cc86ff7884ad4d403f518f9eecde045bbd4a8bcf08b","abstract_canon_sha256":"79b8df4eaac28179cd550e64db1a683a2d9a9b5c132fe5df349149b15f81a202"},"schema_version":"1.0"},"canonical_sha256":"bc688f3816faca97f20b44ba5ab8ed73c41313872d030185bab88a266d9d8061","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:12:29.544507Z","signature_b64":"SKq4aqQoWR68fPVNUc/42Y/t8wBtvYpKxhUzV8v3xrtpU/mnO5hCb6MOqWIZfyC+Q/p/54rT0lZ52aPso/VOAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc688f3816faca97f20b44ba5ab8ed73c41313872d030185bab88a266d9d8061","last_reissued_at":"2026-06-23T01:12:29.544030Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:12:29.544030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.21090","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":"2026-06-23T01:12:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XgXunBH0zk+Gp3GyU4585N6p+xPUk0hVZ+xzMBkk+37b2L3Fxn1sXykf5cjkFAjHPrJpGSd+3yUrPqchyFgfAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T08:16:06.560417Z"},"content_sha256":"a30f5b488cbcf35193c6877535182c6dd84dbd2236cfd6d9da9e1b7022294e41","schema_version":"1.0","event_id":"sha256:a30f5b488cbcf35193c6877535182c6dd84dbd2236cfd6d9da9e1b7022294e41"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:XRUI6OAW7LFJP4QLIS5FVOHNOP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-Improvement Can Self-Regress: The Rise-and-Collapse Failure Mode of LLM Self-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Jianzhe Lin","submitted_at":"2026-06-17T18:03:06Z","abstract_excerpt":"Self-improvement can self-regress. In REINFORCE post-training for code, a model can quickly improve on its optimized metric and then collapse within the same training campaign. We study this in a controlled multi-seed testbed using Qwen-2.5-3B and Qwen-2.5-7B, trained on competitive-programming tasks with binary CodeGrader reward across 10 sequential 20-step campaigns. Across campaigns, pass@1 shows a robust rise-then-collapse pattern: it peaks within tens of gradient steps and then falls back, sometimes to near zero. This is not cross-task catastrophic forgetting, but within-task policy over-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21090","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/2606.21090/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":"2026-06-23T01:12:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hz36i6GunIqd3csXYXetK152MBQ3HyczZZHvMKvyRctX8eRKoHTSib+6iC+gYGaZf48OWy9VXiAoykteIl52DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T08:16:06.560793Z"},"content_sha256":"8b70b29064264c4eba8917c6dd44b7af418e8068d08e6fd49e94a4792cadce80","schema_version":"1.0","event_id":"sha256:8b70b29064264c4eba8917c6dd44b7af418e8068d08e6fd49e94a4792cadce80"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XRUI6OAW7LFJP4QLIS5FVOHNOP/bundle.json","state_url":"https://pith.science/pith/XRUI6OAW7LFJP4QLIS5FVOHNOP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XRUI6OAW7LFJP4QLIS5FVOHNOP/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":"2026-07-04T08:16:06Z","links":{"resolver":"https://pith.science/pith/XRUI6OAW7LFJP4QLIS5FVOHNOP","bundle":"https://pith.science/pith/XRUI6OAW7LFJP4QLIS5FVOHNOP/bundle.json","state":"https://pith.science/pith/XRUI6OAW7LFJP4QLIS5FVOHNOP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XRUI6OAW7LFJP4QLIS5FVOHNOP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XRUI6OAW7LFJP4QLIS5FVOHNOP","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":"79b8df4eaac28179cd550e64db1a683a2d9a9b5c132fe5df349149b15f81a202","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-17T18:03:06Z","title_canon_sha256":"95b8fc03068143c614557cc86ff7884ad4d403f518f9eecde045bbd4a8bcf08b"},"schema_version":"1.0","source":{"id":"2606.21090","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.21090","created_at":"2026-06-23T01:12:29Z"},{"alias_kind":"arxiv_version","alias_value":"2606.21090v1","created_at":"2026-06-23T01:12:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21090","created_at":"2026-06-23T01:12:29Z"},{"alias_kind":"pith_short_12","alias_value":"XRUI6OAW7LFJ","created_at":"2026-06-23T01:12:29Z"},{"alias_kind":"pith_short_16","alias_value":"XRUI6OAW7LFJP4QL","created_at":"2026-06-23T01:12:29Z"},{"alias_kind":"pith_short_8","alias_value":"XRUI6OAW","created_at":"2026-06-23T01:12:29Z"}],"graph_snapshots":[{"event_id":"sha256:8b70b29064264c4eba8917c6dd44b7af418e8068d08e6fd49e94a4792cadce80","target":"graph","created_at":"2026-06-23T01:12:29Z","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/2606.21090/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-improvement can self-regress. In REINFORCE post-training for code, a model can quickly improve on its optimized metric and then collapse within the same training campaign. We study this in a controlled multi-seed testbed using Qwen-2.5-3B and Qwen-2.5-7B, trained on competitive-programming tasks with binary CodeGrader reward across 10 sequential 20-step campaigns. Across campaigns, pass@1 shows a robust rise-then-collapse pattern: it peaks within tens of gradient steps and then falls back, sometimes to near zero. This is not cross-task catastrophic forgetting, but within-task policy over-","authors_text":"Jianzhe Lin","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-17T18:03:06Z","title":"Self-Improvement Can Self-Regress: The Rise-and-Collapse Failure Mode of LLM Self-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21090","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:a30f5b488cbcf35193c6877535182c6dd84dbd2236cfd6d9da9e1b7022294e41","target":"record","created_at":"2026-06-23T01:12:29Z","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":"79b8df4eaac28179cd550e64db1a683a2d9a9b5c132fe5df349149b15f81a202","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-17T18:03:06Z","title_canon_sha256":"95b8fc03068143c614557cc86ff7884ad4d403f518f9eecde045bbd4a8bcf08b"},"schema_version":"1.0","source":{"id":"2606.21090","kind":"arxiv","version":1}},"canonical_sha256":"bc688f3816faca97f20b44ba5ab8ed73c41313872d030185bab88a266d9d8061","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc688f3816faca97f20b44ba5ab8ed73c41313872d030185bab88a266d9d8061","first_computed_at":"2026-06-23T01:12:29.544030Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T01:12:29.544030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SKq4aqQoWR68fPVNUc/42Y/t8wBtvYpKxhUzV8v3xrtpU/mnO5hCb6MOqWIZfyC+Q/p/54rT0lZ52aPso/VOAQ==","signature_status":"signed_v1","signed_at":"2026-06-23T01:12:29.544507Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.21090","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a30f5b488cbcf35193c6877535182c6dd84dbd2236cfd6d9da9e1b7022294e41","sha256:8b70b29064264c4eba8917c6dd44b7af418e8068d08e6fd49e94a4792cadce80"],"state_sha256":"17690297efdb42ac303f400a4505fb80ab24de2100bd8ed07fa87c4d02bc839a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1D0fNhZBsvJuFKZJ/+KQQeljhtKvd90PP6+H7vJohcUAzZoa5JCvF2m6xlV9PtifUglSgpsfxW1xqrQAmhvKAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T08:16:06.564401Z","bundle_sha256":"5944da689e7944c95d6234ce7de6a0d462316542ae16796caa3b6e586fb27931"}}