{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KBPMUJ5JBWBL2YJH7BNBE66CHL","short_pith_number":"pith:KBPMUJ5J","schema_version":"1.0","canonical_sha256":"505eca27a90d82bd6127f85a127bc23af6ed58ecdd1bbf64a40dc40391c2bc5d","source":{"kind":"arxiv","id":"2502.01540","version":1},"attestation_state":"computed","paper":{"title":"What is a Number, That a Large Language Model May Know It?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ilia Sucholutsky, Raja Marjieh, Thomas L. Griffiths, Veniamin Veselovsky","submitted_at":"2025-02-03T17:17:26Z","abstract_excerpt":"Numbers are a basic part of how humans represent and describe the world around them. As a consequence, learning effective representations of numbers is critical for the success of large language models as they become more integrated into everyday decisions. However, these models face a challenge: depending on context, the same sequence of digit tokens, e.g., 911, can be treated as a number or as a string. What kind of representations arise from this duality, and what are its downstream implications? Using a similarity-based prompting technique from cognitive science, we show that LLMs learn re"},"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":"2502.01540","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-03T17:17:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4f3fc2321d19728b0d90d52df1b135ba52e4547642407e815310e6a421d55a3b","abstract_canon_sha256":"3cf684453adbaae2748fc39cbab874c51b939c7aca8507a04518d705d1307c10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:56.449696Z","signature_b64":"7kUNP+jMZm3orvYLY9wX8jwvDJK9GQ+JEtUiiw1m4crJ9ikyLV/DGEEDEewM0Kr6+Sf9lQVzTgyrq4pLTsirBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"505eca27a90d82bd6127f85a127bc23af6ed58ecdd1bbf64a40dc40391c2bc5d","last_reissued_at":"2026-07-05T10:08:56.448252Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:56.448252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What is a Number, That a Large Language Model May Know It?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ilia Sucholutsky, Raja Marjieh, Thomas L. Griffiths, Veniamin Veselovsky","submitted_at":"2025-02-03T17:17:26Z","abstract_excerpt":"Numbers are a basic part of how humans represent and describe the world around them. As a consequence, learning effective representations of numbers is critical for the success of large language models as they become more integrated into everyday decisions. However, these models face a challenge: depending on context, the same sequence of digit tokens, e.g., 911, can be treated as a number or as a string. What kind of representations arise from this duality, and what are its downstream implications? Using a similarity-based prompting technique from cognitive science, we show that LLMs learn re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01540","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/2502.01540/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":"2502.01540","created_at":"2026-07-05T10:08:56.448959+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.01540v1","created_at":"2026-07-05T10:08:56.448959+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01540","created_at":"2026-07-05T10:08:56.448959+00:00"},{"alias_kind":"pith_short_12","alias_value":"KBPMUJ5JBWBL","created_at":"2026-07-05T10:08:56.448959+00:00"},{"alias_kind":"pith_short_16","alias_value":"KBPMUJ5JBWBL2YJH","created_at":"2026-07-05T10:08:56.448959+00:00"},{"alias_kind":"pith_short_8","alias_value":"KBPMUJ5J","created_at":"2026-07-05T10:08:56.448959+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.01025","citing_title":"Hypothesis-Driven Feature Manifold Analysis in LLMs via Supervised Multi-Dimensional Scaling","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KBPMUJ5JBWBL2YJH7BNBE66CHL","json":"https://pith.science/pith/KBPMUJ5JBWBL2YJH7BNBE66CHL.json","graph_json":"https://pith.science/api/pith-number/KBPMUJ5JBWBL2YJH7BNBE66CHL/graph.json","events_json":"https://pith.science/api/pith-number/KBPMUJ5JBWBL2YJH7BNBE66CHL/events.json","paper":"https://pith.science/paper/KBPMUJ5J"},"agent_actions":{"view_html":"https://pith.science/pith/KBPMUJ5JBWBL2YJH7BNBE66CHL","download_json":"https://pith.science/pith/KBPMUJ5JBWBL2YJH7BNBE66CHL.json","view_paper":"https://pith.science/paper/KBPMUJ5J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.01540&json=true","fetch_graph":"https://pith.science/api/pith-number/KBPMUJ5JBWBL2YJH7BNBE66CHL/graph.json","fetch_events":"https://pith.science/api/pith-number/KBPMUJ5JBWBL2YJH7BNBE66CHL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KBPMUJ5JBWBL2YJH7BNBE66CHL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KBPMUJ5JBWBL2YJH7BNBE66CHL/action/storage_attestation","attest_author":"https://pith.science/pith/KBPMUJ5JBWBL2YJH7BNBE66CHL/action/author_attestation","sign_citation":"https://pith.science/pith/KBPMUJ5JBWBL2YJH7BNBE66CHL/action/citation_signature","submit_replication":"https://pith.science/pith/KBPMUJ5JBWBL2YJH7BNBE66CHL/action/replication_record"}},"created_at":"2026-07-05T10:08:56.448959+00:00","updated_at":"2026-07-05T10:08:56.448959+00:00"}