{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:X3ZRTUE56N4L7TL7QMG33H3ROI","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":"be1e1c4f300343cc078ab44111726a3d17c3960c9d0e88318a8f58e59a01b55f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T16:34:20Z","title_canon_sha256":"86b066c0dfeac220b54b9e0a638ce5a02a9de7810516a4aeb743f76876a85bbf"},"schema_version":"1.0","source":{"id":"2412.04318","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04318","created_at":"2026-07-05T10:20:18Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04318v2","created_at":"2026-07-05T10:20:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04318","created_at":"2026-07-05T10:20:18Z"},{"alias_kind":"pith_short_12","alias_value":"X3ZRTUE56N4L","created_at":"2026-07-05T10:20:18Z"},{"alias_kind":"pith_short_16","alias_value":"X3ZRTUE56N4L7TL7","created_at":"2026-07-05T10:20:18Z"},{"alias_kind":"pith_short_8","alias_value":"X3ZRTUE5","created_at":"2026-07-05T10:20:18Z"}],"graph_snapshots":[{"event_id":"sha256:8a1ae8207f80b30ba08a836f9926574288938a29fb2fe828182fda12dcbb6ba1","target":"graph","created_at":"2026-07-05T10:20:18Z","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/2412.04318/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces the counter-intuitive generalization results of overfitting pre-trained large language models (LLMs) on very small datasets. In the setting of open-ended text generation, it is well-documented that LLMs tend to generate repetitive and dull sequences, a phenomenon that is especially apparent when generating using greedy decoding. This issue persists even with state-of-the-art LLMs containing billions of parameters, trained via next-token prediction on large datasets. We find that by further fine-tuning these models to achieve a near-zero training loss on a small set of sam","authors_text":"Daniel Ward, Fangyu Liu, Fredrik Carlsson, Joakim Nivre, Murathan Kurfali","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T16:34:20Z","title":"The Hyperfitting Phenomenon: Sharpening and Stabilizing LLMs for Open-Ended Text Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04318","kind":"arxiv","version":2},"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":"sha256:7e3869c94345367b0fc3e83857bb0391c45c569a3a33efd91cdd5531c747c651","target":"record","created_at":"2026-07-05T10:20:18Z","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":"be1e1c4f300343cc078ab44111726a3d17c3960c9d0e88318a8f58e59a01b55f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T16:34:20Z","title_canon_sha256":"86b066c0dfeac220b54b9e0a638ce5a02a9de7810516a4aeb743f76876a85bbf"},"schema_version":"1.0","source":{"id":"2412.04318","kind":"arxiv","version":2}},"canonical_sha256":"bef319d09df378bfcd7f830dbd9f717209b243084e8a6696ea92367a7729fc4b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bef319d09df378bfcd7f830dbd9f717209b243084e8a6696ea92367a7729fc4b","first_computed_at":"2026-07-05T10:20:18.021815Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:20:18.021815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xaPo2dsiyIrLuejwAJZ0Yqcl/UHKmcHguNygRyqM5dqxJErAyJrvhuqAo9L3HXtxoGHdtwcCsiupOP5K/uLQAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:20:18.022361Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.04318","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e3869c94345367b0fc3e83857bb0391c45c569a3a33efd91cdd5531c747c651","sha256:8a1ae8207f80b30ba08a836f9926574288938a29fb2fe828182fda12dcbb6ba1"],"state_sha256":"d5f96994188dff320e2161428fdd8c5ff4dd8c22adc431e41a396707f75eb07c"}