{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:A2PD2UJSF4M6YTUN5LJD3UQS3P","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":"03980d4029903321d10c8de4223a07ae17a53dd6df3c5b835443b5d4e6e9103a","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-28T18:34:53Z","title_canon_sha256":"9bcefe5fb0932260034c6372fff718a7b42aabb149be8170a82a8087640e8541"},"schema_version":"1.0","source":{"id":"2402.18551","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.18551","created_at":"2026-07-05T09:29:14Z"},{"alias_kind":"arxiv_version","alias_value":"2402.18551v2","created_at":"2026-07-05T09:29:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18551","created_at":"2026-07-05T09:29:14Z"},{"alias_kind":"pith_short_12","alias_value":"A2PD2UJSF4M6","created_at":"2026-07-05T09:29:14Z"},{"alias_kind":"pith_short_16","alias_value":"A2PD2UJSF4M6YTUN","created_at":"2026-07-05T09:29:14Z"},{"alias_kind":"pith_short_8","alias_value":"A2PD2UJS","created_at":"2026-07-05T09:29:14Z"}],"graph_snapshots":[{"event_id":"sha256:15c721f4b4c1ac9d636224ace6fcfb7f25e26eaf7848f33c01e478d09248fb01","target":"graph","created_at":"2026-07-05T09:29:14Z","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/2402.18551/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We initiate an investigation into the optimization properties of next-token prediction (NTP), the dominant training paradigm for modern language models. Specifically, we study the structural properties of the solutions selected by gradient-based optimizers among the many possible minimizers of the NTP objective. By framing NTP as cross-entropy minimization across distinct contexts, each tied with a sparse conditional probability distribution across a finite vocabulary of tokens, we introduce \"NTP-separability conditions\" that enable reaching the data-entropy lower bound. With this setup, and f","authors_text":"Christos Thrampoulidis","cross_cats":["cs.CL","stat.ML"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-28T18:34:53Z","title":"Implicit Optimization Bias of Next-Token Prediction in Linear Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18551","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:b615c4da55ac4a7fe7b996f01c9e25af9e73629d2d99e9906b261b3fa8de4baa","target":"record","created_at":"2026-07-05T09:29:14Z","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":"03980d4029903321d10c8de4223a07ae17a53dd6df3c5b835443b5d4e6e9103a","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-28T18:34:53Z","title_canon_sha256":"9bcefe5fb0932260034c6372fff718a7b42aabb149be8170a82a8087640e8541"},"schema_version":"1.0","source":{"id":"2402.18551","kind":"arxiv","version":2}},"canonical_sha256":"069e3d51322f19ec4e8dead23dd212dbd22ce94e857b5bcdbf6bb3fb934d8342","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"069e3d51322f19ec4e8dead23dd212dbd22ce94e857b5bcdbf6bb3fb934d8342","first_computed_at":"2026-07-05T09:29:14.002826Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:29:14.002826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zyc405R3shlefq1Vs7EQcVOwxaVzcZp6wqY214se6HRyKXmsuqwLAOV606FKmiXwUQHxneS7UUm6bo0lwN4qCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:29:14.003278Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.18551","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b615c4da55ac4a7fe7b996f01c9e25af9e73629d2d99e9906b261b3fa8de4baa","sha256:15c721f4b4c1ac9d636224ace6fcfb7f25e26eaf7848f33c01e478d09248fb01"],"state_sha256":"c77b2bfa998acf65f4057b6068709007bc2b88de1771d51027bb39d8b360a296"}