{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:X6RSJVKXP6ZVX43KI4YKOWRHT2","short_pith_number":"pith:X6RSJVKX","schema_version":"1.0","canonical_sha256":"bfa324d5577fb35bf36a4730a75a279ea1b6e1ad508569d509cafa35c3ecac7a","source":{"kind":"arxiv","id":"2606.18487","version":1},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.18487","created_at":"2026-06-19T16:11:02.294289+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.18487v1","created_at":"2026-06-19T16:11:02.294289+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18487","created_at":"2026-06-19T16:11:02.294289+00:00"},{"alias_kind":"pith_short_12","alias_value":"X6RSJVKXP6ZV","created_at":"2026-06-19T16:11:02.294289+00:00"},{"alias_kind":"pith_short_16","alias_value":"X6RSJVKXP6ZVX43K","created_at":"2026-06-19T16:11:02.294289+00:00"},{"alias_kind":"pith_short_8","alias_value":"X6RSJVKX","created_at":"2026-06-19T16:11:02.294289+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X6RSJVKXP6ZVX43KI4YKOWRHT2","json":"https://pith.science/pith/X6RSJVKXP6ZVX43KI4YKOWRHT2.json","graph_json":"https://pith.science/api/pith-number/X6RSJVKXP6ZVX43KI4YKOWRHT2/graph.json","events_json":"https://pith.science/api/pith-number/X6RSJVKXP6ZVX43KI4YKOWRHT2/events.json","paper":"https://pith.science/paper/X6RSJVKX"},"agent_actions":{"view_html":"https://pith.science/pith/X6RSJVKXP6ZVX43KI4YKOWRHT2","download_json":"https://pith.science/pith/X6RSJVKXP6ZVX43KI4YKOWRHT2.json","view_paper":"https://pith.science/paper/X6RSJVKX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.18487&json=true","fetch_graph":"https://pith.science/api/pith-number/X6RSJVKXP6ZVX43KI4YKOWRHT2/graph.json","fetch_events":"https://pith.science/api/pith-number/X6RSJVKXP6ZVX43KI4YKOWRHT2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X6RSJVKXP6ZVX43KI4YKOWRHT2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X6RSJVKXP6ZVX43KI4YKOWRHT2/action/storage_attestation","attest_author":"https://pith.science/pith/X6RSJVKXP6ZVX43KI4YKOWRHT2/action/author_attestation","sign_citation":"https://pith.science/pith/X6RSJVKXP6ZVX43KI4YKOWRHT2/action/citation_signature","submit_replication":"https://pith.science/pith/X6RSJVKXP6ZVX43KI4YKOWRHT2/action/replication_record"}},"created_at":"2026-06-19T16:11:02.294289+00:00","updated_at":"2026-06-19T16:11:02.294289+00:00"}