{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:IW76GTUGTOH2KXMTR7YNKH6FN4","short_pith_number":"pith:IW76GTUG","canonical_record":{"source":{"id":"2607.13389","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-15T02:34:35Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b86d69d9f18e7dc045fb545693df8fa220b789cb7f75bb2b763bb6c5c21fff38","abstract_canon_sha256":"662e7adf8402702a34e6dad498ae8e1c56463b02a7022d31ec58ad7a740c1644"},"schema_version":"1.0"},"canonical_sha256":"45bfe34e869b8fa55d938ff0d51fc56f0fda1ed5d1270455466d5b370d67ee5f","source":{"kind":"arxiv","id":"2607.13389","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.13389","created_at":"2026-07-16T00:22:15Z"},{"alias_kind":"arxiv_version","alias_value":"2607.13389v1","created_at":"2026-07-16T00:22:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.13389","created_at":"2026-07-16T00:22:15Z"},{"alias_kind":"pith_short_12","alias_value":"IW76GTUGTOH2","created_at":"2026-07-16T00:22:15Z"},{"alias_kind":"pith_short_16","alias_value":"IW76GTUGTOH2KXMT","created_at":"2026-07-16T00:22:15Z"},{"alias_kind":"pith_short_8","alias_value":"IW76GTUG","created_at":"2026-07-16T00:22:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:IW76GTUGTOH2KXMTR7YNKH6FN4","target":"record","payload":{"canonical_record":{"source":{"id":"2607.13389","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-15T02:34:35Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b86d69d9f18e7dc045fb545693df8fa220b789cb7f75bb2b763bb6c5c21fff38","abstract_canon_sha256":"662e7adf8402702a34e6dad498ae8e1c56463b02a7022d31ec58ad7a740c1644"},"schema_version":"1.0"},"canonical_sha256":"45bfe34e869b8fa55d938ff0d51fc56f0fda1ed5d1270455466d5b370d67ee5f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-16T00:22:15.306252Z","signature_b64":"HxlO1Qd5ZmM2imHJF3Xbw0n3zaeWrlt4kyJi5ORyuTErEjpJQzx/rNrY2hfatr/w/wy6FSeluuseb4rVR0ZFDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45bfe34e869b8fa55d938ff0d51fc56f0fda1ed5d1270455466d5b370d67ee5f","last_reissued_at":"2026-07-16T00:22:15.305388Z","signature_status":"signed_v1","first_computed_at":"2026-07-16T00:22:15.305388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.13389","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":"2026-07-16T00:22:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eDkI0gfUPzPVP6WpB1wbxJS7rKY4mmgqnHp7xuGAIjWZD6BSAcF/kVxRR1DYQb+zrAL2k2zjEN9QLacXH6ptDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:22:46.157103Z"},"content_sha256":"b81f1dc7a62c2a3eeb7a1f781deb84cc7e6aff86bf46c44dc2ed46debbefe4e6","schema_version":"1.0","event_id":"sha256:b81f1dc7a62c2a3eeb7a1f781deb84cc7e6aff86bf46c44dc2ed46debbefe4e6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:IW76GTUGTOH2KXMTR7YNKH6FN4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Where Should RL Post-Training Compute Go? Model Size, Search, Learning, and Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Odej Kao, Patrick Wilhelm","submitted_at":"2026-07-15T02:34:35Z","abstract_excerpt":"Reinforcement Learning (RL) post-training is increasingly used to adapt foundation models for reasoning, planning, and feedback-driven robot-learning pipelines, but constrained post-training resources are often summarized by a single total FLOP budget. We study the fixed-budget decision problem behind this practice: under the same post-training budget, should one use a larger policy, train a smaller policy longer, generate more rollout search, or spend compute on stronger reward feedback? We introduce a FLOP-accounting framework for GRPO post-training that decomposes compute into rollout/searc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.13389","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/2607.13389/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":"2026-07-16T00:22:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mZs6R5kBhCq39WKKL1ZBlz/7HfXnNJVCm4qXr5vnBr6mCKp6GpGmCcb7XkUClSFiAj+qKYqzkKxJ53d4vyg8Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:22:46.158005Z"},"content_sha256":"e9e6456537b9f1a1d81d877c185c6f198a7a7a2eaa40f0f2b43d178ee94279cd","schema_version":"1.0","event_id":"sha256:e9e6456537b9f1a1d81d877c185c6f198a7a7a2eaa40f0f2b43d178ee94279cd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IW76GTUGTOH2KXMTR7YNKH6FN4/bundle.json","state_url":"https://pith.science/pith/IW76GTUGTOH2KXMTR7YNKH6FN4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IW76GTUGTOH2KXMTR7YNKH6FN4/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":"2026-08-04T21:22:46Z","links":{"resolver":"https://pith.science/pith/IW76GTUGTOH2KXMTR7YNKH6FN4","bundle":"https://pith.science/pith/IW76GTUGTOH2KXMTR7YNKH6FN4/bundle.json","state":"https://pith.science/pith/IW76GTUGTOH2KXMTR7YNKH6FN4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IW76GTUGTOH2KXMTR7YNKH6FN4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IW76GTUGTOH2KXMTR7YNKH6FN4","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":"662e7adf8402702a34e6dad498ae8e1c56463b02a7022d31ec58ad7a740c1644","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-15T02:34:35Z","title_canon_sha256":"b86d69d9f18e7dc045fb545693df8fa220b789cb7f75bb2b763bb6c5c21fff38"},"schema_version":"1.0","source":{"id":"2607.13389","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.13389","created_at":"2026-07-16T00:22:15Z"},{"alias_kind":"arxiv_version","alias_value":"2607.13389v1","created_at":"2026-07-16T00:22:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.13389","created_at":"2026-07-16T00:22:15Z"},{"alias_kind":"pith_short_12","alias_value":"IW76GTUGTOH2","created_at":"2026-07-16T00:22:15Z"},{"alias_kind":"pith_short_16","alias_value":"IW76GTUGTOH2KXMT","created_at":"2026-07-16T00:22:15Z"},{"alias_kind":"pith_short_8","alias_value":"IW76GTUG","created_at":"2026-07-16T00:22:15Z"}],"graph_snapshots":[{"event_id":"sha256:e9e6456537b9f1a1d81d877c185c6f198a7a7a2eaa40f0f2b43d178ee94279cd","target":"graph","created_at":"2026-07-16T00:22:15Z","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/2607.13389/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) post-training is increasingly used to adapt foundation models for reasoning, planning, and feedback-driven robot-learning pipelines, but constrained post-training resources are often summarized by a single total FLOP budget. We study the fixed-budget decision problem behind this practice: under the same post-training budget, should one use a larger policy, train a smaller policy longer, generate more rollout search, or spend compute on stronger reward feedback? We introduce a FLOP-accounting framework for GRPO post-training that decomposes compute into rollout/searc","authors_text":"Odej Kao, Patrick Wilhelm","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-15T02:34:35Z","title":"Where Should RL Post-Training Compute Go? Model Size, Search, Learning, and Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.13389","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:b81f1dc7a62c2a3eeb7a1f781deb84cc7e6aff86bf46c44dc2ed46debbefe4e6","target":"record","created_at":"2026-07-16T00:22:15Z","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":"662e7adf8402702a34e6dad498ae8e1c56463b02a7022d31ec58ad7a740c1644","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-15T02:34:35Z","title_canon_sha256":"b86d69d9f18e7dc045fb545693df8fa220b789cb7f75bb2b763bb6c5c21fff38"},"schema_version":"1.0","source":{"id":"2607.13389","kind":"arxiv","version":1}},"canonical_sha256":"45bfe34e869b8fa55d938ff0d51fc56f0fda1ed5d1270455466d5b370d67ee5f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45bfe34e869b8fa55d938ff0d51fc56f0fda1ed5d1270455466d5b370d67ee5f","first_computed_at":"2026-07-16T00:22:15.305388Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-16T00:22:15.305388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HxlO1Qd5ZmM2imHJF3Xbw0n3zaeWrlt4kyJi5ORyuTErEjpJQzx/rNrY2hfatr/w/wy6FSeluuseb4rVR0ZFDg==","signature_status":"signed_v1","signed_at":"2026-07-16T00:22:15.306252Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.13389","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b81f1dc7a62c2a3eeb7a1f781deb84cc7e6aff86bf46c44dc2ed46debbefe4e6","sha256:e9e6456537b9f1a1d81d877c185c6f198a7a7a2eaa40f0f2b43d178ee94279cd"],"state_sha256":"87e5359f8e8509a3b3a7bd621664bf3e2f7bc929325da50ee53e0a0e7ebc8997"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4MfnBkr2BC/R0H6srhk6qDdBmmkGZiVa2/c32jBDIgVfGyoAx/ZcTuAd+qe5FawWLbldcJqmIfcssSeX1C8wCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T21:22:46.164481Z","bundle_sha256":"096acd6b1589aec461c302a0f58e0004431ea66371afcbf6babe363de6acdbf6"}}