{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5H2R2DL2NOJRDT7VKINXQDVOPV","short_pith_number":"pith:5H2R2DL2","schema_version":"1.0","canonical_sha256":"e9f51d0d7a6b9311cff5521b780eae7d42d545d05d5c58bef75276d8a8e3929f","source":{"kind":"arxiv","id":"2608.13545","version":1},"attestation_state":"computed","paper":{"title":"LittleLearner: Language Models Under Pedagogically Controlled Knowledge Exposure","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Fanfei Li, Jana Zeller, Manuel Prada-Corral, Prasanna Mayilvahanan, Ryan Cotterell, Thadd\\\"aus Wiedemer, Wieland Brendel","submitted_at":"2026-08-13T17:56:12Z","abstract_excerpt":"Modern language models are trained on heterogeneous web-scale text corpora. Consequently, studying knowledge and skill acquisition is difficult, as prior exposure to related content is hard to characterize. To address this challenge, we introduce LITTLECURRICULUM, a curated 88B-token pretraining corpus tailored to U.S. elementary school material, explicitly excluding concepts, facts, and vocabulary taught above Grade 5. Training a 5B-parameter LLM from scratch on LITTLECURRICULUM yields LITTLELEARNER, a model with sufficient language competence for open-ended evaluation, yet with clear knowled"},"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":"2608.13545","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-13T17:56:12Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"8ff6c26a14b48dc7034b1f6e16c724b627ab0486676c07666e40c70ec745e776","abstract_canon_sha256":"3ae4c401196637bdc397cca706155543f0245dd6aeebef02da07c9db5af9d2a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-14T01:25:02.016519Z","signature_b64":"qqTh5JwCzEiOlY4TuUXAZA+1BdHBjF6BILIzSRCzPopE/NVl/blxnS+2RgpxEcwvZLMlgTp7jmoIaNkOVqoFBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9f51d0d7a6b9311cff5521b780eae7d42d545d05d5c58bef75276d8a8e3929f","last_reissued_at":"2026-08-14T01:25:02.014072Z","signature_status":"signed_v1","first_computed_at":"2026-08-14T01:25:02.014072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LittleLearner: Language Models Under Pedagogically Controlled Knowledge Exposure","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Fanfei Li, Jana Zeller, Manuel Prada-Corral, Prasanna Mayilvahanan, Ryan Cotterell, Thadd\\\"aus Wiedemer, Wieland Brendel","submitted_at":"2026-08-13T17:56:12Z","abstract_excerpt":"Modern language models are trained on heterogeneous web-scale text corpora. Consequently, studying knowledge and skill acquisition is difficult, as prior exposure to related content is hard to characterize. To address this challenge, we introduce LITTLECURRICULUM, a curated 88B-token pretraining corpus tailored to U.S. elementary school material, explicitly excluding concepts, facts, and vocabulary taught above Grade 5. Training a 5B-parameter LLM from scratch on LITTLECURRICULUM yields LITTLELEARNER, a model with sufficient language competence for open-ended evaluation, yet with clear knowled"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.13545","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/2608.13545/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":"2608.13545","created_at":"2026-08-14T01:25:02.015719+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.13545v1","created_at":"2026-08-14T01:25:02.015719+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.13545","created_at":"2026-08-14T01:25:02.015719+00:00"},{"alias_kind":"pith_short_12","alias_value":"5H2R2DL2NOJR","created_at":"2026-08-14T01:25:02.015719+00:00"},{"alias_kind":"pith_short_16","alias_value":"5H2R2DL2NOJRDT7V","created_at":"2026-08-14T01:25:02.015719+00:00"},{"alias_kind":"pith_short_8","alias_value":"5H2R2DL2","created_at":"2026-08-14T01:25:02.015719+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/5H2R2DL2NOJRDT7VKINXQDVOPV","json":"https://pith.science/pith/5H2R2DL2NOJRDT7VKINXQDVOPV.json","graph_json":"https://pith.science/api/pith-number/5H2R2DL2NOJRDT7VKINXQDVOPV/graph.json","events_json":"https://pith.science/api/pith-number/5H2R2DL2NOJRDT7VKINXQDVOPV/events.json","paper":"https://pith.science/paper/5H2R2DL2"},"agent_actions":{"view_html":"https://pith.science/pith/5H2R2DL2NOJRDT7VKINXQDVOPV","download_json":"https://pith.science/pith/5H2R2DL2NOJRDT7VKINXQDVOPV.json","view_paper":"https://pith.science/paper/5H2R2DL2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.13545&json=true","fetch_graph":"https://pith.science/api/pith-number/5H2R2DL2NOJRDT7VKINXQDVOPV/graph.json","fetch_events":"https://pith.science/api/pith-number/5H2R2DL2NOJRDT7VKINXQDVOPV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5H2R2DL2NOJRDT7VKINXQDVOPV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5H2R2DL2NOJRDT7VKINXQDVOPV/action/storage_attestation","attest_author":"https://pith.science/pith/5H2R2DL2NOJRDT7VKINXQDVOPV/action/author_attestation","sign_citation":"https://pith.science/pith/5H2R2DL2NOJRDT7VKINXQDVOPV/action/citation_signature","submit_replication":"https://pith.science/pith/5H2R2DL2NOJRDT7VKINXQDVOPV/action/replication_record"}},"created_at":"2026-08-14T01:25:02.015719+00:00","updated_at":"2026-08-14T01:25:02.015719+00:00"}