{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2005:PIFBYF2GBBIDL2AKA7HDNTGAOU","short_pith_number":"pith:PIFBYF2G","schema_version":"1.0","canonical_sha256":"7a0a1c1746085035e80a07ce36ccc0751313557933cf4348ced5fa99b3c40efa","source":{"kind":"arxiv","id":"cs/0508103","version":1},"attestation_state":"computed","paper":{"title":"Corpus-based Learning of Analogies and Semantic Relations","license":"","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.LG","authors_text":"Michael L. Littman (Rutgers University), Peter D. Turney (National Research Council of Canada)","submitted_at":"2005-08-23T20:21:56Z","abstract_excerpt":"We present an algorithm for learning from unlabeled text, based on the Vector Space Model (VSM) of information retrieval, that can solve verbal analogy questions of the kind found in the SAT college entrance exam. A verbal analogy has the form A:B::C:D, meaning \"A is to B as C is to D\"; for example, mason:stone::carpenter:wood. SAT analogy questions provide a word pair, A:B, and the problem is to select the most analogous word pair, C:D, from a set of five choices. The VSM algorithm correctly answers 47% of a collection of 374 college-level analogy questions (random guessing would yield 20% co"},"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":"cs/0508103","kind":"arxiv","version":1},"metadata":{"license":"","primary_cat":"cs.LG","submitted_at":"2005-08-23T20:21:56Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"3e143f9f4e085c5314a1bc2e84cadd0fa3d72de56201c457a25e90d7704d380d","abstract_canon_sha256":"f9f9a2cd65f32464d0e49db729347c45965911ebd3cf1e41fb1ccec02cb0540e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T14:25:04.898060Z","signature_b64":"v5to30xWxIvxXsT6vQLJC5n4NpS/EOA8XPxNbMYRLFc45Buiv05kKNb9L8MQqzgMrCNqTjiiR+SO/yjM4IQkCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a0a1c1746085035e80a07ce36ccc0751313557933cf4348ced5fa99b3c40efa","last_reissued_at":"2026-07-04T14:25:04.897662Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T14:25:04.897662Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Corpus-based Learning of Analogies and Semantic Relations","license":"","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.LG","authors_text":"Michael L. Littman (Rutgers University), Peter D. Turney (National Research Council of Canada)","submitted_at":"2005-08-23T20:21:56Z","abstract_excerpt":"We present an algorithm for learning from unlabeled text, based on the Vector Space Model (VSM) of information retrieval, that can solve verbal analogy questions of the kind found in the SAT college entrance exam. A verbal analogy has the form A:B::C:D, meaning \"A is to B as C is to D\"; for example, mason:stone::carpenter:wood. SAT analogy questions provide a word pair, A:B, and the problem is to select the most analogous word pair, C:D, from a set of five choices. The VSM algorithm correctly answers 47% of a collection of 374 college-level analogy questions (random guessing would yield 20% co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cs/0508103","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/cs/0508103/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":"cs/0508103","created_at":"2026-07-04T14:25:04.897722+00:00"},{"alias_kind":"arxiv_version","alias_value":"cs/0508103v1","created_at":"2026-07-04T14:25:04.897722+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cs/0508103","created_at":"2026-07-04T14:25:04.897722+00:00"},{"alias_kind":"pith_short_12","alias_value":"PIFBYF2GBBID","created_at":"2026-07-04T14:25:04.897722+00:00"},{"alias_kind":"pith_short_16","alias_value":"PIFBYF2GBBIDL2AK","created_at":"2026-07-04T14:25:04.897722+00:00"},{"alias_kind":"pith_short_8","alias_value":"PIFBYF2G","created_at":"2026-07-04T14:25:04.897722+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2005.14165","citing_title":"Language Models are Few-Shot Learners","ref_index":77,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PIFBYF2GBBIDL2AKA7HDNTGAOU","json":"https://pith.science/pith/PIFBYF2GBBIDL2AKA7HDNTGAOU.json","graph_json":"https://pith.science/api/pith-number/PIFBYF2GBBIDL2AKA7HDNTGAOU/graph.json","events_json":"https://pith.science/api/pith-number/PIFBYF2GBBIDL2AKA7HDNTGAOU/events.json","paper":"https://pith.science/paper/PIFBYF2G"},"agent_actions":{"view_html":"https://pith.science/pith/PIFBYF2GBBIDL2AKA7HDNTGAOU","download_json":"https://pith.science/pith/PIFBYF2GBBIDL2AKA7HDNTGAOU.json","view_paper":"https://pith.science/paper/PIFBYF2G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=cs/0508103&json=true","fetch_graph":"https://pith.science/api/pith-number/PIFBYF2GBBIDL2AKA7HDNTGAOU/graph.json","fetch_events":"https://pith.science/api/pith-number/PIFBYF2GBBIDL2AKA7HDNTGAOU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PIFBYF2GBBIDL2AKA7HDNTGAOU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PIFBYF2GBBIDL2AKA7HDNTGAOU/action/storage_attestation","attest_author":"https://pith.science/pith/PIFBYF2GBBIDL2AKA7HDNTGAOU/action/author_attestation","sign_citation":"https://pith.science/pith/PIFBYF2GBBIDL2AKA7HDNTGAOU/action/citation_signature","submit_replication":"https://pith.science/pith/PIFBYF2GBBIDL2AKA7HDNTGAOU/action/replication_record"}},"created_at":"2026-07-04T14:25:04.897722+00:00","updated_at":"2026-07-04T14:25:04.897722+00:00"}