{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:X53CUIIGOAXLQAYODNN2IC5R5K","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":"92c921f36635119aaa8439a4ddd0b4985fc899ed4820c752851078f7d67fa588","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-05T10:47:24Z","title_canon_sha256":"9c2a9e1557a6347aa29511a95d913386ce66cef711cf53a78ead8c3d35bc9856"},"schema_version":"1.0","source":{"id":"2605.20196","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20196","created_at":"2026-05-21T00:04:20Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20196v1","created_at":"2026-05-21T00:04:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20196","created_at":"2026-05-21T00:04:20Z"},{"alias_kind":"pith_short_12","alias_value":"X53CUIIGOAXL","created_at":"2026-05-21T00:04:20Z"},{"alias_kind":"pith_short_16","alias_value":"X53CUIIGOAXLQAYO","created_at":"2026-05-21T00:04:20Z"},{"alias_kind":"pith_short_8","alias_value":"X53CUIIG","created_at":"2026-05-21T00:04:20Z"}],"graph_snapshots":[{"event_id":"sha256:31de6bc847bd52e990e03624fd28c6dd3ac76c8d40352db4122b0ccb0086db8f","target":"graph","created_at":"2026-05-21T00:04:20Z","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/2605.20196/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We investigate the hypothesis that real-data scaling laws are governed by progressive coverage of a latent predictive contribution spectrum rather than by token-frequency tails alone. We work with a suffix-automaton representation of text corpora and define a data-intrinsic global-KL predictive contribution spectrum, in which each state contributes according to its empirical mass times its KL deviation from a global next-token baseline. Across 12 real corpora, the tail slope of this spectrum is already strongly correlated with the empirical data-scaling exponent of a fixed small GPT learner. W","authors_text":"Chunlin Huang, Hongxi Li, Shihao Ji, Shuaizhi Cheng, Zihui Song","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-05T10:47:24Z","title":"Data Scaling as Progressive Coverage of a Predictive Contribution Spectrum"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20196","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:d3cfbc1c14c68a32ab662f5e6f0c120873e27e6aee387bf601d3c83020a263f6","target":"record","created_at":"2026-05-21T00:04:20Z","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":"92c921f36635119aaa8439a4ddd0b4985fc899ed4820c752851078f7d67fa588","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-05T10:47:24Z","title_canon_sha256":"9c2a9e1557a6347aa29511a95d913386ce66cef711cf53a78ead8c3d35bc9856"},"schema_version":"1.0","source":{"id":"2605.20196","kind":"arxiv","version":1}},"canonical_sha256":"bf762a2106702eb8030e1b5ba40bb1ea98265f5f61ecff5bd416312da91ca099","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf762a2106702eb8030e1b5ba40bb1ea98265f5f61ecff5bd416312da91ca099","first_computed_at":"2026-05-21T00:04:20.634367Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T00:04:20.634367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L4MMSMXtkf9axOar+zvBLQLU5CdBfRrfC28hSavN7LLYn5xCyrQTAQkIl5UXLfohPAvzQBqq1jNDaGiDhyF7AQ==","signature_status":"signed_v1","signed_at":"2026-05-21T00:04:20.635079Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.20196","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d3cfbc1c14c68a32ab662f5e6f0c120873e27e6aee387bf601d3c83020a263f6","sha256:31de6bc847bd52e990e03624fd28c6dd3ac76c8d40352db4122b0ccb0086db8f"],"state_sha256":"b9060ec08a40bed722b641653ea9d3fcd2342f2a8d26f5f6a98a1159e42da2f4"}