{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7WAP2BCD5DWZUHYWZL33DV5NYT","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":"2dcc39dea006737960ce37a18ff3da283e6620580d3535837861f0195a9d437e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-15T19:11:54Z","title_canon_sha256":"5a69019ab796b096b9779b3cccd7b9a299c7ade8bc43dc79e77ed40effc7044a"},"schema_version":"1.0","source":{"id":"2607.14306","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.14306","created_at":"2026-07-17T00:21:04Z"},{"alias_kind":"arxiv_version","alias_value":"2607.14306v1","created_at":"2026-07-17T00:21:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14306","created_at":"2026-07-17T00:21:04Z"},{"alias_kind":"pith_short_12","alias_value":"7WAP2BCD5DWZ","created_at":"2026-07-17T00:21:04Z"},{"alias_kind":"pith_short_16","alias_value":"7WAP2BCD5DWZUHYW","created_at":"2026-07-17T00:21:04Z"},{"alias_kind":"pith_short_8","alias_value":"7WAP2BCD","created_at":"2026-07-17T00:21:04Z"}],"graph_snapshots":[{"event_id":"sha256:b7295a4461eedef4e1bf3f229ff2323b6e972ff0f94a0e8237e44b99f4167d95","target":"graph","created_at":"2026-07-17T00:21:04Z","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/2607.14306/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we study the connection between an LLM's output distribution and the data used to train it. Specifically, we study the degree to which an LLM's next-token distribution agrees with the empirical next-token distribution (ENTD) given the context in the training data. The ENTD is an appealing target because it is the unrestricted global minimizer of the next-token cross entropy loss used for pretraining, as well as an easily interpretable function of the pretraining corpus. We find that for a significant fraction of inputs, the LLM's distribution agrees with the ENTD almost perfectl","authors_text":"Zachary Izzo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-15T19:11:54Z","title":"Tracing LLM Behavior to the Training Data with Empirical Next-Token Distributions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14306","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":"sha256:437a5b410a7a629c155850f5ffab28671a70c8f59f4d782b07532e7466729fc3","target":"record","created_at":"2026-07-17T00:21:04Z","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":"2dcc39dea006737960ce37a18ff3da283e6620580d3535837861f0195a9d437e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-15T19:11:54Z","title_canon_sha256":"5a69019ab796b096b9779b3cccd7b9a299c7ade8bc43dc79e77ed40effc7044a"},"schema_version":"1.0","source":{"id":"2607.14306","kind":"arxiv","version":1}},"canonical_sha256":"fd80fd0443e8ed9a1f16caf7b1d7adc4f58228907e944fd4dc5769fc2f0065de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd80fd0443e8ed9a1f16caf7b1d7adc4f58228907e944fd4dc5769fc2f0065de","first_computed_at":"2026-07-17T00:21:04.438946Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-17T00:21:04.438946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3F6EC32DGy9XwTAGvpCNJblCrYGY3Q4kw536mD1uTpETkChNRmo8ce5SXGJy12neCCfmoQtlOjiryTmwtWp9Cw==","signature_status":"signed_v1","signed_at":"2026-07-17T00:21:04.439827Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.14306","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:437a5b410a7a629c155850f5ffab28671a70c8f59f4d782b07532e7466729fc3","sha256:b7295a4461eedef4e1bf3f229ff2323b6e972ff0f94a0e8237e44b99f4167d95"],"state_sha256":"f34cc5b7b879965ffa5ded7e06e423d27aec59bb7584dccf4c35dbc169277b5b"}