{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:X6RSJVKXP6ZVX43KI4YKOWRHT2","short_pith_number":"pith:X6RSJVKX","canonical_record":{"source":{"id":"2606.18487","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-16T20:59:55Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"b420e20faad16ced76e087c9cc1e5442acbada7ac42360b4c54ec53c021c19e1","abstract_canon_sha256":"6024f6751e2736691aa00c7a38435853513dfbe55bb2ba18323aeda818dead53"},"schema_version":"1.0"},"canonical_sha256":"bfa324d5577fb35bf36a4730a75a279ea1b6e1ad508569d509cafa35c3ecac7a","source":{"kind":"arxiv","id":"2606.18487","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.18487","created_at":"2026-06-19T16:11:02Z"},{"alias_kind":"arxiv_version","alias_value":"2606.18487v1","created_at":"2026-06-19T16:11:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18487","created_at":"2026-06-19T16:11:02Z"},{"alias_kind":"pith_short_12","alias_value":"X6RSJVKXP6ZV","created_at":"2026-06-19T16:11:02Z"},{"alias_kind":"pith_short_16","alias_value":"X6RSJVKXP6ZVX43K","created_at":"2026-06-19T16:11:02Z"},{"alias_kind":"pith_short_8","alias_value":"X6RSJVKX","created_at":"2026-06-19T16:11:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:X6RSJVKXP6ZVX43KI4YKOWRHT2","target":"record","payload":{"canonical_record":{"source":{"id":"2606.18487","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-16T20:59:55Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"b420e20faad16ced76e087c9cc1e5442acbada7ac42360b4c54ec53c021c19e1","abstract_canon_sha256":"6024f6751e2736691aa00c7a38435853513dfbe55bb2ba18323aeda818dead53"},"schema_version":"1.0"},"canonical_sha256":"bfa324d5577fb35bf36a4730a75a279ea1b6e1ad508569d509cafa35c3ecac7a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:02.294588Z","signature_b64":"SmNMhImMRfPBgTUayIGpOUqfOZP06vlBBUGoZG9t9nhqd+iZkcdszkWNPpF5ks3CmrNepdFG8NkpimZri5NFBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfa324d5577fb35bf36a4730a75a279ea1b6e1ad508569d509cafa35c3ecac7a","last_reissued_at":"2026-06-19T16:11:02.294224Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:02.294224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.18487","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":"2026-06-19T16:11:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MJ0OenIhFPwXZW+pTg14+y+esZRIfgknCUn9lEz4bzPD7+W7w9SbwqtNONRAAbD2JfVZeg3HIJYeFhhdf5NzCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T13:48:38.866892Z"},"content_sha256":"3f34c6d6bdf664f47ea57fe50131b86841bfcda6b7888f052624130a0aa4f371","schema_version":"1.0","event_id":"sha256:3f34c6d6bdf664f47ea57fe50131b86841bfcda6b7888f052624130a0aa4f371"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:X6RSJVKXP6ZVX43KI4YKOWRHT2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SFT Overtraining Predicts Rank Inversion via Entropy Collapse Under RLVR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Kelly Liu, Siddharth Aphale","submitted_at":"2026-06-16T20:59:55Z","abstract_excerpt":"The standard heuristic of selecting the SFT checkpoint with the highest pass@1 for GRPO can fail when SFT compresses the rollout distribution. For binary rewards, the expected within group advantage variance is $p(1{-}p)(g{-}1)/g$; when early GRPO drives $p$ below $p^*(g)$, most groups have identical rewards and provide no group relative signal. We study SFT depth ladders for Qwen2.5-Coder-3B and DeepSeek-Coder-6.7B. We test Qwen2.5-Coder-3B across five depths and three seeds, and DeepSeek-Coder-6.7B across four matched depths and three seeds. On Qwen, pre RL pass@1 rises with SFT depth, but p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18487","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/2606.18487/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":"2026-06-19T16:11:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gnjfMzMDmGHI+JnEly893hcrNyXxsSmu+ixPWRG9fP/WsE8hzvnjWPKsbqXImLAKXdVzH1FpWPtnP3RNk+qrBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T13:48:38.867255Z"},"content_sha256":"1095e09ca6f9ef8025903c70af1ed8e5eb4d952b3867e1f26ec49e7116446bad","schema_version":"1.0","event_id":"sha256:1095e09ca6f9ef8025903c70af1ed8e5eb4d952b3867e1f26ec49e7116446bad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X6RSJVKXP6ZVX43KI4YKOWRHT2/bundle.json","state_url":"https://pith.science/pith/X6RSJVKXP6ZVX43KI4YKOWRHT2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X6RSJVKXP6ZVX43KI4YKOWRHT2/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":"2026-06-28T13:48:38Z","links":{"resolver":"https://pith.science/pith/X6RSJVKXP6ZVX43KI4YKOWRHT2","bundle":"https://pith.science/pith/X6RSJVKXP6ZVX43KI4YKOWRHT2/bundle.json","state":"https://pith.science/pith/X6RSJVKXP6ZVX43KI4YKOWRHT2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X6RSJVKXP6ZVX43KI4YKOWRHT2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:X6RSJVKXP6ZVX43KI4YKOWRHT2","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":"6024f6751e2736691aa00c7a38435853513dfbe55bb2ba18323aeda818dead53","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-16T20:59:55Z","title_canon_sha256":"b420e20faad16ced76e087c9cc1e5442acbada7ac42360b4c54ec53c021c19e1"},"schema_version":"1.0","source":{"id":"2606.18487","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.18487","created_at":"2026-06-19T16:11:02Z"},{"alias_kind":"arxiv_version","alias_value":"2606.18487v1","created_at":"2026-06-19T16:11:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18487","created_at":"2026-06-19T16:11:02Z"},{"alias_kind":"pith_short_12","alias_value":"X6RSJVKXP6ZV","created_at":"2026-06-19T16:11:02Z"},{"alias_kind":"pith_short_16","alias_value":"X6RSJVKXP6ZVX43K","created_at":"2026-06-19T16:11:02Z"},{"alias_kind":"pith_short_8","alias_value":"X6RSJVKX","created_at":"2026-06-19T16:11:02Z"}],"graph_snapshots":[{"event_id":"sha256:1095e09ca6f9ef8025903c70af1ed8e5eb4d952b3867e1f26ec49e7116446bad","target":"graph","created_at":"2026-06-19T16:11:02Z","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/2606.18487/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The standard heuristic of selecting the SFT checkpoint with the highest pass@1 for GRPO can fail when SFT compresses the rollout distribution. For binary rewards, the expected within group advantage variance is $p(1{-}p)(g{-}1)/g$; when early GRPO drives $p$ below $p^*(g)$, most groups have identical rewards and provide no group relative signal. We study SFT depth ladders for Qwen2.5-Coder-3B and DeepSeek-Coder-6.7B. We test Qwen2.5-Coder-3B across five depths and three seeds, and DeepSeek-Coder-6.7B across four matched depths and three seeds. On Qwen, pre RL pass@1 rises with SFT depth, but p","authors_text":"Kelly Liu, Siddharth Aphale","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-16T20:59:55Z","title":"SFT Overtraining Predicts Rank Inversion via Entropy Collapse Under RLVR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18487","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":"sha256:3f34c6d6bdf664f47ea57fe50131b86841bfcda6b7888f052624130a0aa4f371","target":"record","created_at":"2026-06-19T16:11:02Z","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":"6024f6751e2736691aa00c7a38435853513dfbe55bb2ba18323aeda818dead53","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-16T20:59:55Z","title_canon_sha256":"b420e20faad16ced76e087c9cc1e5442acbada7ac42360b4c54ec53c021c19e1"},"schema_version":"1.0","source":{"id":"2606.18487","kind":"arxiv","version":1}},"canonical_sha256":"bfa324d5577fb35bf36a4730a75a279ea1b6e1ad508569d509cafa35c3ecac7a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bfa324d5577fb35bf36a4730a75a279ea1b6e1ad508569d509cafa35c3ecac7a","first_computed_at":"2026-06-19T16:11:02.294224Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:11:02.294224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SmNMhImMRfPBgTUayIGpOUqfOZP06vlBBUGoZG9t9nhqd+iZkcdszkWNPpF5ks3CmrNepdFG8NkpimZri5NFBA==","signature_status":"signed_v1","signed_at":"2026-06-19T16:11:02.294588Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.18487","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f34c6d6bdf664f47ea57fe50131b86841bfcda6b7888f052624130a0aa4f371","sha256:1095e09ca6f9ef8025903c70af1ed8e5eb4d952b3867e1f26ec49e7116446bad"],"state_sha256":"88b7cb0abdc4c444f3a5ef48095d311e4c805749000802951f1390ac273ae24c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BeUsM4wdAG6c9DWrwoQfAEGfAaFkNN1fHXoTGVkEXhRlPas6a6LE3JRtSg3nx08G3GiJTxgEIPcKamaDKBnmAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T13:48:38.869424Z","bundle_sha256":"6e08624c1e9af61871c434e0101e265d2551ed4f5df5e47e1b0049e6ee634cac"}}