{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:O3EHPLLW2CIIJ6KOJCZCXQDNW6","short_pith_number":"pith:O3EHPLLW","schema_version":"1.0","canonical_sha256":"76c877ad76d09084f94e48b22bc06db7b7307212ff33848fcebb29e86dc70497","source":{"kind":"arxiv","id":"2301.13382","version":1},"attestation_state":"computed","paper":{"title":"Numeracy from Literacy: Data Science as an Emergent Skill from Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Noever, Forrest McKee","submitted_at":"2023-01-31T03:14:57Z","abstract_excerpt":"Large language models (LLM) such as OpenAI's ChatGPT and GPT-3 offer unique testbeds for exploring the translation challenges of turning literacy into numeracy. Previous publicly-available transformer models from eighteen months prior and 1000 times smaller failed to provide basic arithmetic. The statistical analysis of four complex datasets described here combines arithmetic manipulations that cannot be memorized or encoded by simple rules. The work examines whether next-token prediction succeeds from sentence completion into the realm of actual numerical understanding. For example, the work "},"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":"2301.13382","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-31T03:14:57Z","cross_cats_sorted":[],"title_canon_sha256":"0494df3c345e2667632a15b6b4f1b7e45e260a9b298f6182ee06500a7bcb0079","abstract_canon_sha256":"b7ed7d3de0b164735f9720972982936954e0f3023f84d6279ceef8ff4c32b32d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:37:14.153940Z","signature_b64":"n58nfMbISwSNtcWAq2tEXErAnPmbnB7DyPckxvD9ByJrccQPhaAYJWAtwgIeVok3RgPxghzWIMGGaLc6pyZvAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76c877ad76d09084f94e48b22bc06db7b7307212ff33848fcebb29e86dc70497","last_reissued_at":"2026-07-05T05:37:14.153524Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:37:14.153524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Numeracy from Literacy: Data Science as an Emergent Skill from Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Noever, Forrest McKee","submitted_at":"2023-01-31T03:14:57Z","abstract_excerpt":"Large language models (LLM) such as OpenAI's ChatGPT and GPT-3 offer unique testbeds for exploring the translation challenges of turning literacy into numeracy. Previous publicly-available transformer models from eighteen months prior and 1000 times smaller failed to provide basic arithmetic. The statistical analysis of four complex datasets described here combines arithmetic manipulations that cannot be memorized or encoded by simple rules. The work examines whether next-token prediction succeeds from sentence completion into the realm of actual numerical understanding. For example, the work "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13382","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/2301.13382/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":"2301.13382","created_at":"2026-07-05T05:37:14.153578+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.13382v1","created_at":"2026-07-05T05:37:14.153578+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.13382","created_at":"2026-07-05T05:37:14.153578+00:00"},{"alias_kind":"pith_short_12","alias_value":"O3EHPLLW2CII","created_at":"2026-07-05T05:37:14.153578+00:00"},{"alias_kind":"pith_short_16","alias_value":"O3EHPLLW2CIIJ6KO","created_at":"2026-07-05T05:37:14.153578+00:00"},{"alias_kind":"pith_short_8","alias_value":"O3EHPLLW","created_at":"2026-07-05T05:37:14.153578+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2404.01063","citing_title":"Chat Modeling: Interaction-Enhanced Agent Framework for Visualizing Literature-Grounded Biological Structures","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O3EHPLLW2CIIJ6KOJCZCXQDNW6","json":"https://pith.science/pith/O3EHPLLW2CIIJ6KOJCZCXQDNW6.json","graph_json":"https://pith.science/api/pith-number/O3EHPLLW2CIIJ6KOJCZCXQDNW6/graph.json","events_json":"https://pith.science/api/pith-number/O3EHPLLW2CIIJ6KOJCZCXQDNW6/events.json","paper":"https://pith.science/paper/O3EHPLLW"},"agent_actions":{"view_html":"https://pith.science/pith/O3EHPLLW2CIIJ6KOJCZCXQDNW6","download_json":"https://pith.science/pith/O3EHPLLW2CIIJ6KOJCZCXQDNW6.json","view_paper":"https://pith.science/paper/O3EHPLLW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.13382&json=true","fetch_graph":"https://pith.science/api/pith-number/O3EHPLLW2CIIJ6KOJCZCXQDNW6/graph.json","fetch_events":"https://pith.science/api/pith-number/O3EHPLLW2CIIJ6KOJCZCXQDNW6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O3EHPLLW2CIIJ6KOJCZCXQDNW6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O3EHPLLW2CIIJ6KOJCZCXQDNW6/action/storage_attestation","attest_author":"https://pith.science/pith/O3EHPLLW2CIIJ6KOJCZCXQDNW6/action/author_attestation","sign_citation":"https://pith.science/pith/O3EHPLLW2CIIJ6KOJCZCXQDNW6/action/citation_signature","submit_replication":"https://pith.science/pith/O3EHPLLW2CIIJ6KOJCZCXQDNW6/action/replication_record"}},"created_at":"2026-07-05T05:37:14.153578+00:00","updated_at":"2026-07-05T05:37:14.153578+00:00"}