{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VYKB253BAZL24HZ7USTIDFDMOA","short_pith_number":"pith:VYKB253B","schema_version":"1.0","canonical_sha256":"ae141d77610657ae1f3fa4a681946c70117e420e0ddca5a1db4e1f8d81f78b5b","source":{"kind":"arxiv","id":"2310.06204","version":1},"attestation_state":"computed","paper":{"title":"Estimating Numbers without Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ashwin Kalyan, Avijit Thawani, Jay Pujara","submitted_at":"2023-10-09T23:07:05Z","abstract_excerpt":"Despite recent successes in language models, their ability to represent numbers is insufficient. Humans conceptualize numbers based on their magnitudes, effectively projecting them on a number line; whereas subword tokenization fails to explicitly capture magnitude by splitting numbers into arbitrary chunks. To alleviate this shortcoming, alternative approaches have been proposed that modify numbers at various stages of the language modeling pipeline. These methods change either the (1) notation in which numbers are written (\\eg scientific vs decimal), the (2) vocabulary used to represent numb"},"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":"2310.06204","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-09T23:07:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6adb641b5af4f770f70ad08bb684893e57ab9acff6d2bbb346dc8497a6652be6","abstract_canon_sha256":"b9001fb0cace9e01fed0324af87fe2dd2891979c401c18bd5cce2d8a5f1ac671"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:06.854894Z","signature_b64":"SnPffFZzmNOFREws52boBM9k73QI+PTwp9MVuwy5ErKyzX02IBkZJV0svJujfe/fNx3yNCC/cjsHDR/Ze+PKDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae141d77610657ae1f3fa4a681946c70117e420e0ddca5a1db4e1f8d81f78b5b","last_reissued_at":"2026-07-05T06:59:06.854436Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:06.854436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Estimating Numbers without Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ashwin Kalyan, Avijit Thawani, Jay Pujara","submitted_at":"2023-10-09T23:07:05Z","abstract_excerpt":"Despite recent successes in language models, their ability to represent numbers is insufficient. Humans conceptualize numbers based on their magnitudes, effectively projecting them on a number line; whereas subword tokenization fails to explicitly capture magnitude by splitting numbers into arbitrary chunks. To alleviate this shortcoming, alternative approaches have been proposed that modify numbers at various stages of the language modeling pipeline. These methods change either the (1) notation in which numbers are written (\\eg scientific vs decimal), the (2) vocabulary used to represent numb"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.06204","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/2310.06204/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":"2310.06204","created_at":"2026-07-05T06:59:06.854499+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.06204v1","created_at":"2026-07-05T06:59:06.854499+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.06204","created_at":"2026-07-05T06:59:06.854499+00:00"},{"alias_kind":"pith_short_12","alias_value":"VYKB253BAZL2","created_at":"2026-07-05T06:59:06.854499+00:00"},{"alias_kind":"pith_short_16","alias_value":"VYKB253BAZL24HZ7","created_at":"2026-07-05T06:59:06.854499+00:00"},{"alias_kind":"pith_short_8","alias_value":"VYKB253B","created_at":"2026-07-05T06:59:06.854499+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/VYKB253BAZL24HZ7USTIDFDMOA","json":"https://pith.science/pith/VYKB253BAZL24HZ7USTIDFDMOA.json","graph_json":"https://pith.science/api/pith-number/VYKB253BAZL24HZ7USTIDFDMOA/graph.json","events_json":"https://pith.science/api/pith-number/VYKB253BAZL24HZ7USTIDFDMOA/events.json","paper":"https://pith.science/paper/VYKB253B"},"agent_actions":{"view_html":"https://pith.science/pith/VYKB253BAZL24HZ7USTIDFDMOA","download_json":"https://pith.science/pith/VYKB253BAZL24HZ7USTIDFDMOA.json","view_paper":"https://pith.science/paper/VYKB253B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.06204&json=true","fetch_graph":"https://pith.science/api/pith-number/VYKB253BAZL24HZ7USTIDFDMOA/graph.json","fetch_events":"https://pith.science/api/pith-number/VYKB253BAZL24HZ7USTIDFDMOA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VYKB253BAZL24HZ7USTIDFDMOA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VYKB253BAZL24HZ7USTIDFDMOA/action/storage_attestation","attest_author":"https://pith.science/pith/VYKB253BAZL24HZ7USTIDFDMOA/action/author_attestation","sign_citation":"https://pith.science/pith/VYKB253BAZL24HZ7USTIDFDMOA/action/citation_signature","submit_replication":"https://pith.science/pith/VYKB253BAZL24HZ7USTIDFDMOA/action/replication_record"}},"created_at":"2026-07-05T06:59:06.854499+00:00","updated_at":"2026-07-05T06:59:06.854499+00:00"}