{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7YJHZKCYOAGWKECT2FSSN4HDTP","short_pith_number":"pith:7YJHZKCY","schema_version":"1.0","canonical_sha256":"fe127ca858700d651053d16526f0e39beef76102e20751ef6a30e008b2326660","source":{"kind":"arxiv","id":"2404.07544","version":3},"attestation_state":"computed","paper":{"title":"From Words to Numbers: Your Large Language Model Is Secretly A Capable Regressor When Given In-Context Examples","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Mihai Surdeanu, Robert Vacareanu, Vasile Suciu, Vlad-Andrei Negru","submitted_at":"2024-04-11T08:12:43Z","abstract_excerpt":"We analyze how well pre-trained large language models (e.g., Llama2, GPT-4, Claude 3, etc) can do linear and non-linear regression when given in-context examples, without any additional training or gradient updates. Our findings reveal that several large language models (e.g., GPT-4, Claude 3) are able to perform regression tasks with a performance rivaling (or even outperforming) that of traditional supervised methods such as Random Forest, Bagging, or Gradient Boosting. For example, on the challenging Friedman #2 regression dataset, Claude 3 outperforms many supervised methods such as AdaBoo"},"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":"2404.07544","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-11T08:12:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1ac419a041f7b4074524852ce6f7a33e2ef9701776eb3e411f98e8ff65cdcb8d","abstract_canon_sha256":"95587f1e3804acff700290f5d17a55272bede5dffc1f6d2aa27719ea322a4eec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:05:34.933943Z","signature_b64":"fSDLqaMOGvCKXEXwH3O/EwNj/BBVrPXm9J25AUXi5rYWgQEQmrWXoiRiZvBxOCLIYWw91kCiyE+2oP3RsU2BCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe127ca858700d651053d16526f0e39beef76102e20751ef6a30e008b2326660","last_reissued_at":"2026-07-05T09:05:34.933535Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:05:34.933535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Words to Numbers: Your Large Language Model Is Secretly A Capable Regressor When Given In-Context Examples","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Mihai Surdeanu, Robert Vacareanu, Vasile Suciu, Vlad-Andrei Negru","submitted_at":"2024-04-11T08:12:43Z","abstract_excerpt":"We analyze how well pre-trained large language models (e.g., Llama2, GPT-4, Claude 3, etc) can do linear and non-linear regression when given in-context examples, without any additional training or gradient updates. Our findings reveal that several large language models (e.g., GPT-4, Claude 3) are able to perform regression tasks with a performance rivaling (or even outperforming) that of traditional supervised methods such as Random Forest, Bagging, or Gradient Boosting. For example, on the challenging Friedman #2 regression dataset, Claude 3 outperforms many supervised methods such as AdaBoo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07544","kind":"arxiv","version":3},"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/2404.07544/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":"2404.07544","created_at":"2026-07-05T09:05:34.933589+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.07544v3","created_at":"2026-07-05T09:05:34.933589+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07544","created_at":"2026-07-05T09:05:34.933589+00:00"},{"alias_kind":"pith_short_12","alias_value":"7YJHZKCYOAGW","created_at":"2026-07-05T09:05:34.933589+00:00"},{"alias_kind":"pith_short_16","alias_value":"7YJHZKCYOAGWKECT","created_at":"2026-07-05T09:05:34.933589+00:00"},{"alias_kind":"pith_short_8","alias_value":"7YJHZKCY","created_at":"2026-07-05T09:05:34.933589+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.16217","citing_title":"Towards Compute-Optimal Many-Shot In-Context Learning","ref_index":1953,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7YJHZKCYOAGWKECT2FSSN4HDTP","json":"https://pith.science/pith/7YJHZKCYOAGWKECT2FSSN4HDTP.json","graph_json":"https://pith.science/api/pith-number/7YJHZKCYOAGWKECT2FSSN4HDTP/graph.json","events_json":"https://pith.science/api/pith-number/7YJHZKCYOAGWKECT2FSSN4HDTP/events.json","paper":"https://pith.science/paper/7YJHZKCY"},"agent_actions":{"view_html":"https://pith.science/pith/7YJHZKCYOAGWKECT2FSSN4HDTP","download_json":"https://pith.science/pith/7YJHZKCYOAGWKECT2FSSN4HDTP.json","view_paper":"https://pith.science/paper/7YJHZKCY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.07544&json=true","fetch_graph":"https://pith.science/api/pith-number/7YJHZKCYOAGWKECT2FSSN4HDTP/graph.json","fetch_events":"https://pith.science/api/pith-number/7YJHZKCYOAGWKECT2FSSN4HDTP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7YJHZKCYOAGWKECT2FSSN4HDTP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7YJHZKCYOAGWKECT2FSSN4HDTP/action/storage_attestation","attest_author":"https://pith.science/pith/7YJHZKCYOAGWKECT2FSSN4HDTP/action/author_attestation","sign_citation":"https://pith.science/pith/7YJHZKCYOAGWKECT2FSSN4HDTP/action/citation_signature","submit_replication":"https://pith.science/pith/7YJHZKCYOAGWKECT2FSSN4HDTP/action/replication_record"}},"created_at":"2026-07-05T09:05:34.933589+00:00","updated_at":"2026-07-05T09:05:34.933589+00:00"}