{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:CGIBGO635F67SMMO7ZUYSHIKO5","short_pith_number":"pith:CGIBGO63","canonical_record":{"source":{"id":"2312.06585","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-11T18:17:43Z","cross_cats_sorted":[],"title_canon_sha256":"e6f01419f3183ccef4ae6812e0bc345f062a4d13758792b5f93678a3dc639db4","abstract_canon_sha256":"b4ddb1d9e9a1501c3bbbf08491415a4f11b004e8a7be172142b48cca1fdcc66f"},"schema_version":"1.0"},"canonical_sha256":"1190133bdbe97df9318efe69891d0a7765158f2f07c750ba8010d727bcafe5c8","source":{"kind":"arxiv","id":"2312.06585","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.06585","created_at":"2026-07-05T08:09:27Z"},{"alias_kind":"arxiv_version","alias_value":"2312.06585v4","created_at":"2026-07-05T08:09:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06585","created_at":"2026-07-05T08:09:27Z"},{"alias_kind":"pith_short_12","alias_value":"CGIBGO635F67","created_at":"2026-07-05T08:09:27Z"},{"alias_kind":"pith_short_16","alias_value":"CGIBGO635F67SMMO","created_at":"2026-07-05T08:09:27Z"},{"alias_kind":"pith_short_8","alias_value":"CGIBGO63","created_at":"2026-07-05T08:09:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:CGIBGO635F67SMMO7ZUYSHIKO5","target":"record","payload":{"canonical_record":{"source":{"id":"2312.06585","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-11T18:17:43Z","cross_cats_sorted":[],"title_canon_sha256":"e6f01419f3183ccef4ae6812e0bc345f062a4d13758792b5f93678a3dc639db4","abstract_canon_sha256":"b4ddb1d9e9a1501c3bbbf08491415a4f11b004e8a7be172142b48cca1fdcc66f"},"schema_version":"1.0"},"canonical_sha256":"1190133bdbe97df9318efe69891d0a7765158f2f07c750ba8010d727bcafe5c8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:09:27.040334Z","signature_b64":"Iujldx8qKy2m5y1OB1wIRPf5/Zi04/bPm1DrFao03FofmWmioQsHcR3iuJwn+TuT3rQlBtVBk6G37n1vFQGPAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1190133bdbe97df9318efe69891d0a7765158f2f07c750ba8010d727bcafe5c8","last_reissued_at":"2026-07-05T08:09:27.039855Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:09:27.039855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.06585","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:09:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5N7jZ/loTIR56ZH24qagd+agfMmS3YtT8lpr2dM4OojnV7BsfqmCnSx91v5kLIxipQtO53eZRT5J1XbLZLbUAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T05:13:01.959109Z"},"content_sha256":"5f46170b59e42eded4448cd456c4e3381f2ac46d774e4672060af12e058ed70b","schema_version":"1.0","event_id":"sha256:5f46170b59e42eded4448cd456c4e3381f2ac46d774e4672060af12e058ed70b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:CGIBGO635F67SMMO7ZUYSHIKO5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aaron Parisi, Abhishek Kumar, Alex Alemi, Alex Rizkowsky, Ankesh Anand, Avi Singh, Azade Nova, Behnam Neyshabur, Ben Adlam, Bernd Bohnet, Ethan Dyer, Gamaleldin Elsayed, Hanie Sedghi, Igor Mordatch, Isabelle Simpson, Izzeddin Gur, Jaehoon Lee, James Harrison, Jascha Sohl-Dickstein, Jasper Snoek, Jeffrey Pennington, Jiri Hron, John D. Co-Reyes, Kathleen Kenealy, Kelvin Xu, Kevin Swersky, Kshiteej Mahajan, Laura Culp, Lechao Xiao, Maxwell L. Bileschi, Noah Constant, Noah Fiedel, Peter J. Liu, Piyush Patil, Rishabh Agarwal, Roman Novak, Rosanne Liu, Tris Warkentin, Xavier Garcia, Yamini Bansal, Yundi Qian","submitted_at":"2023-12-11T18:17:43Z","abstract_excerpt":"Fine-tuning language models~(LMs) on human-generated data remains a prevalent practice. However, the performance of such models is often limited by the quantity and diversity of high-quality human data. In this paper, we explore whether we can go beyond human data on tasks where we have access to scalar feedback, for example, on math problems where one can verify correctness. To do so, we investigate a simple self-training method based on expectation-maximization, which we call ReST$^{EM}$, where we (1) generate samples from the model and filter them using binary feedback, (2) fine-tune the mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06585","kind":"arxiv","version":4},"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/2312.06585/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":"2026-07-05T08:09:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JznNJ8busBMV25eeq4cZU6qu9zWP4kUpkRWYKXc10mTQdAMkWrEq0lN29PqipFGp30CmDTjcwWnc61T4HcudAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T05:13:01.959608Z"},"content_sha256":"b4db0d46b2954442df16939e7f65d3246eea368cf79bbfe227f56b823c3f0f99","schema_version":"1.0","event_id":"sha256:b4db0d46b2954442df16939e7f65d3246eea368cf79bbfe227f56b823c3f0f99"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CGIBGO635F67SMMO7ZUYSHIKO5/bundle.json","state_url":"https://pith.science/pith/CGIBGO635F67SMMO7ZUYSHIKO5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CGIBGO635F67SMMO7ZUYSHIKO5/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":"2026-08-07T05:13:01Z","links":{"resolver":"https://pith.science/pith/CGIBGO635F67SMMO7ZUYSHIKO5","bundle":"https://pith.science/pith/CGIBGO635F67SMMO7ZUYSHIKO5/bundle.json","state":"https://pith.science/pith/CGIBGO635F67SMMO7ZUYSHIKO5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CGIBGO635F67SMMO7ZUYSHIKO5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CGIBGO635F67SMMO7ZUYSHIKO5","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":"b4ddb1d9e9a1501c3bbbf08491415a4f11b004e8a7be172142b48cca1fdcc66f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-11T18:17:43Z","title_canon_sha256":"e6f01419f3183ccef4ae6812e0bc345f062a4d13758792b5f93678a3dc639db4"},"schema_version":"1.0","source":{"id":"2312.06585","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.06585","created_at":"2026-07-05T08:09:27Z"},{"alias_kind":"arxiv_version","alias_value":"2312.06585v4","created_at":"2026-07-05T08:09:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06585","created_at":"2026-07-05T08:09:27Z"},{"alias_kind":"pith_short_12","alias_value":"CGIBGO635F67","created_at":"2026-07-05T08:09:27Z"},{"alias_kind":"pith_short_16","alias_value":"CGIBGO635F67SMMO","created_at":"2026-07-05T08:09:27Z"},{"alias_kind":"pith_short_8","alias_value":"CGIBGO63","created_at":"2026-07-05T08:09:27Z"}],"graph_snapshots":[{"event_id":"sha256:b4db0d46b2954442df16939e7f65d3246eea368cf79bbfe227f56b823c3f0f99","target":"graph","created_at":"2026-07-05T08:09:27Z","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/2312.06585/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning language models~(LMs) on human-generated data remains a prevalent practice. However, the performance of such models is often limited by the quantity and diversity of high-quality human data. In this paper, we explore whether we can go beyond human data on tasks where we have access to scalar feedback, for example, on math problems where one can verify correctness. To do so, we investigate a simple self-training method based on expectation-maximization, which we call ReST$^{EM}$, where we (1) generate samples from the model and filter them using binary feedback, (2) fine-tune the mo","authors_text":"Aaron Parisi, Abhishek Kumar, Alex Alemi, Alex Rizkowsky, Ankesh Anand, Avi Singh, Azade Nova, Behnam Neyshabur, Ben Adlam, Bernd Bohnet, Ethan Dyer, Gamaleldin Elsayed, Hanie Sedghi, Igor Mordatch, Isabelle Simpson, Izzeddin Gur, Jaehoon Lee, James Harrison, Jascha Sohl-Dickstein, Jasper Snoek, Jeffrey Pennington, Jiri Hron, John D. Co-Reyes, Kathleen Kenealy, Kelvin Xu, Kevin Swersky, Kshiteej Mahajan, Laura Culp, Lechao Xiao, Maxwell L. Bileschi, Noah Constant, Noah Fiedel, Peter J. Liu, Piyush Patil, Rishabh Agarwal, Roman Novak, Rosanne Liu, Tris Warkentin, Xavier Garcia, Yamini Bansal, Yundi Qian","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-11T18:17:43Z","title":"Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06585","kind":"arxiv","version":4},"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":"sha256:5f46170b59e42eded4448cd456c4e3381f2ac46d774e4672060af12e058ed70b","target":"record","created_at":"2026-07-05T08:09:27Z","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":"b4ddb1d9e9a1501c3bbbf08491415a4f11b004e8a7be172142b48cca1fdcc66f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-11T18:17:43Z","title_canon_sha256":"e6f01419f3183ccef4ae6812e0bc345f062a4d13758792b5f93678a3dc639db4"},"schema_version":"1.0","source":{"id":"2312.06585","kind":"arxiv","version":4}},"canonical_sha256":"1190133bdbe97df9318efe69891d0a7765158f2f07c750ba8010d727bcafe5c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1190133bdbe97df9318efe69891d0a7765158f2f07c750ba8010d727bcafe5c8","first_computed_at":"2026-07-05T08:09:27.039855Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:09:27.039855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Iujldx8qKy2m5y1OB1wIRPf5/Zi04/bPm1DrFao03FofmWmioQsHcR3iuJwn+TuT3rQlBtVBk6G37n1vFQGPAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:09:27.040334Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.06585","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f46170b59e42eded4448cd456c4e3381f2ac46d774e4672060af12e058ed70b","sha256:b4db0d46b2954442df16939e7f65d3246eea368cf79bbfe227f56b823c3f0f99"],"state_sha256":"97163ba6bab0e17b4620d1dccdfa81ba14dbe50c155cc05e17448d1fc52158a3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CEzn787XtQcySEDo3JWz6hFzCTvwz2xdkKfALubntZyyRViLpPtcar15N9YZT9FnIyHHVvtDcohfA+BDi7ksDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T05:13:01.964768Z","bundle_sha256":"00539323f01b09bcb712f3df3f163c09d1d930b573e8dd62c01f0009710bfcb6"}}