{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:X53CUIIGOAXLQAYODNN2IC5R5K","short_pith_number":"pith:X53CUIIG","schema_version":"1.0","canonical_sha256":"bf762a2106702eb8030e1b5ba40bb1ea98265f5f61ecff5bd416312da91ca099","source":{"kind":"arxiv","id":"2605.20196","version":1},"attestation_state":"computed","paper":{"title":"Data Scaling as Progressive Coverage of a Predictive Contribution Spectrum","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chunlin Huang, Hongxi Li, Shihao Ji, Shuaizhi Cheng, Zihui Song","submitted_at":"2026-04-05T10:47:24Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.20196","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-05T10:47:24Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9c2a9e1557a6347aa29511a95d913386ce66cef711cf53a78ead8c3d35bc9856","abstract_canon_sha256":"92c921f36635119aaa8439a4ddd0b4985fc899ed4820c752851078f7d67fa588"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T00:04:20.635079Z","signature_b64":"L4MMSMXtkf9axOar+zvBLQLU5CdBfRrfC28hSavN7LLYn5xCyrQTAQkIl5UXLfohPAvzQBqq1jNDaGiDhyF7AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf762a2106702eb8030e1b5ba40bb1ea98265f5f61ecff5bd416312da91ca099","last_reissued_at":"2026-05-21T00:04:20.634367Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T00:04:20.634367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Scaling as Progressive Coverage of a Predictive Contribution Spectrum","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chunlin Huang, Hongxi Li, Shihao Ji, Shuaizhi Cheng, Zihui Song","submitted_at":"2026-04-05T10:47:24Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20196","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.20196/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.20196","created_at":"2026-05-21T00:04:20.634472+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.20196v1","created_at":"2026-05-21T00:04:20.634472+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20196","created_at":"2026-05-21T00:04:20.634472+00:00"},{"alias_kind":"pith_short_12","alias_value":"X53CUIIGOAXL","created_at":"2026-05-21T00:04:20.634472+00:00"},{"alias_kind":"pith_short_16","alias_value":"X53CUIIGOAXLQAYO","created_at":"2026-05-21T00:04:20.634472+00:00"},{"alias_kind":"pith_short_8","alias_value":"X53CUIIG","created_at":"2026-05-21T00:04:20.634472+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X53CUIIGOAXLQAYODNN2IC5R5K","json":"https://pith.science/pith/X53CUIIGOAXLQAYODNN2IC5R5K.json","graph_json":"https://pith.science/api/pith-number/X53CUIIGOAXLQAYODNN2IC5R5K/graph.json","events_json":"https://pith.science/api/pith-number/X53CUIIGOAXLQAYODNN2IC5R5K/events.json","paper":"https://pith.science/paper/X53CUIIG"},"agent_actions":{"view_html":"https://pith.science/pith/X53CUIIGOAXLQAYODNN2IC5R5K","download_json":"https://pith.science/pith/X53CUIIGOAXLQAYODNN2IC5R5K.json","view_paper":"https://pith.science/paper/X53CUIIG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.20196&json=true","fetch_graph":"https://pith.science/api/pith-number/X53CUIIGOAXLQAYODNN2IC5R5K/graph.json","fetch_events":"https://pith.science/api/pith-number/X53CUIIGOAXLQAYODNN2IC5R5K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X53CUIIGOAXLQAYODNN2IC5R5K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X53CUIIGOAXLQAYODNN2IC5R5K/action/storage_attestation","attest_author":"https://pith.science/pith/X53CUIIGOAXLQAYODNN2IC5R5K/action/author_attestation","sign_citation":"https://pith.science/pith/X53CUIIGOAXLQAYODNN2IC5R5K/action/citation_signature","submit_replication":"https://pith.science/pith/X53CUIIGOAXLQAYODNN2IC5R5K/action/replication_record"}},"created_at":"2026-05-21T00:04:20.634472+00:00","updated_at":"2026-05-21T00:04:20.634472+00:00"}