{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YOM5ZNLWAM6OBBC5PZEXJHFDAA","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":"1a2fb14901e992b8b4eda218ab636cc18f7b5f3cb2bbc8eff19617951a965dfe","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-13T19:47:33Z","title_canon_sha256":"0b2b62909a29c37c435a5c62f4fa21c86859920143bae7e1a9085e3b3925bcf6"},"schema_version":"1.0","source":{"id":"2309.08632","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.08632","created_at":"2026-07-05T06:51:11Z"},{"alias_kind":"arxiv_version","alias_value":"2309.08632v1","created_at":"2026-07-05T06:51:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08632","created_at":"2026-07-05T06:51:11Z"},{"alias_kind":"pith_short_12","alias_value":"YOM5ZNLWAM6O","created_at":"2026-07-05T06:51:11Z"},{"alias_kind":"pith_short_16","alias_value":"YOM5ZNLWAM6OBBC5","created_at":"2026-07-05T06:51:11Z"},{"alias_kind":"pith_short_8","alias_value":"YOM5ZNLW","created_at":"2026-07-05T06:51:11Z"}],"graph_snapshots":[{"event_id":"sha256:53a98dfeb8e064280fc96ed7abde92dde43c0aa0ea8fb45cd1ed5dfe93c23dea","target":"graph","created_at":"2026-07-05T06:51:11Z","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/2309.08632/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Inspired by recent work demonstrating the promise of smaller Transformer-based language models pretrained on carefully curated data, we supercharge such approaches by investing heavily in curating a novel, high quality, non-synthetic data mixture based solely on evaluation benchmarks. Using our novel dataset mixture consisting of less than 100 thousand tokens, we pretrain a 1 million parameter transformer-based LLM \\textbf{phi-CTNL} (pronounced ``fictional\") that achieves perfect results across diverse academic benchmarks, strictly outperforming all known foundation models. \\textbf{phi-CTNL} a","authors_text":"Rylan Schaeffer","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-13T19:47:33Z","title":"Pretraining on the Test Set Is All You Need"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08632","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:b3c7a6e45a9b1808b60d34c5e7a862e795eeb62c8a0dc0682ad3709fb69bb543","target":"record","created_at":"2026-07-05T06:51:11Z","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":"1a2fb14901e992b8b4eda218ab636cc18f7b5f3cb2bbc8eff19617951a965dfe","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-13T19:47:33Z","title_canon_sha256":"0b2b62909a29c37c435a5c62f4fa21c86859920143bae7e1a9085e3b3925bcf6"},"schema_version":"1.0","source":{"id":"2309.08632","kind":"arxiv","version":1}},"canonical_sha256":"c399dcb576033ce0845d7e49749ca300058cace38bb4eed58ff43cbae1aa1ad4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c399dcb576033ce0845d7e49749ca300058cace38bb4eed58ff43cbae1aa1ad4","first_computed_at":"2026-07-05T06:51:11.073335Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:51:11.073335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u0JTwwBn/wOM2l3C/ENnLHZQNZ7Qb3cUhq27NJu40hChEWKui1JlpziWxM5hTK/K0pdK8kVvZqBKHMZNQ7E+CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:51:11.073778Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.08632","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b3c7a6e45a9b1808b60d34c5e7a862e795eeb62c8a0dc0682ad3709fb69bb543","sha256:53a98dfeb8e064280fc96ed7abde92dde43c0aa0ea8fb45cd1ed5dfe93c23dea"],"state_sha256":"f79a96f4c2e9d0f17e9d97cc746464938023dae541ca7d5139edfdcc4f5da6e5"}