{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:2RGDUNCB46AREAXUFUM6Q5X2A4","short_pith_number":"pith:2RGDUNCB","schema_version":"1.0","canonical_sha256":"d44c3a3441e7811202f42d19e876fa07336c9ad2cc1b88678932fe22353430fe","source":{"kind":"arxiv","id":"1605.04553","version":2},"attestation_state":"computed","paper":{"title":"A Proposal for Linguistic Similarity Datasets Based on Commonality Lists","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dmitrijs Milajevs, Sascha Griffiths","submitted_at":"2016-05-15T14:00:06Z","abstract_excerpt":"Similarity is a core notion that is used in psychology and two branches of linguistics: theoretical and computational. The similarity datasets that come from the two fields differ in design: psychological datasets are focused around a certain topic such as fruit names, while linguistic datasets contain words from various categories. The later makes humans assign low similarity scores to the words that have nothing in common and to the words that have contrast in meaning, making similarity scores ambiguous. In this work we discuss the similarity collection procedure for a multi-category dataset"},"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":"1605.04553","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-05-15T14:00:06Z","cross_cats_sorted":[],"title_canon_sha256":"44ba3dc0f0154b71442a3c7c88307b676a51fd32441aaf47244c75f88d581208","abstract_canon_sha256":"cfe7d26c1a973caf122374e4df8a838245bb54940d25d86d29f46f1f9ac31f7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:19.686749Z","signature_b64":"OaUh4/cYIeWAQOHibAiRoFmJNemUMg0WFXTOLlIf2fvTskGpI9Jh495CooKNONL+GeNeFwLW+xl7o7XUp4FdDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d44c3a3441e7811202f42d19e876fa07336c9ad2cc1b88678932fe22353430fe","last_reissued_at":"2026-05-18T01:12:19.686372Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:19.686372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Proposal for Linguistic Similarity Datasets Based on Commonality Lists","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dmitrijs Milajevs, Sascha Griffiths","submitted_at":"2016-05-15T14:00:06Z","abstract_excerpt":"Similarity is a core notion that is used in psychology and two branches of linguistics: theoretical and computational. The similarity datasets that come from the two fields differ in design: psychological datasets are focused around a certain topic such as fruit names, while linguistic datasets contain words from various categories. The later makes humans assign low similarity scores to the words that have nothing in common and to the words that have contrast in meaning, making similarity scores ambiguous. In this work we discuss the similarity collection procedure for a multi-category dataset"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.04553","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1605.04553","created_at":"2026-05-18T01:12:19.686430+00:00"},{"alias_kind":"arxiv_version","alias_value":"1605.04553v2","created_at":"2026-05-18T01:12:19.686430+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.04553","created_at":"2026-05-18T01:12:19.686430+00:00"},{"alias_kind":"pith_short_12","alias_value":"2RGDUNCB46AR","created_at":"2026-05-18T12:29:55.572404+00:00"},{"alias_kind":"pith_short_16","alias_value":"2RGDUNCB46AREAXU","created_at":"2026-05-18T12:29:55.572404+00:00"},{"alias_kind":"pith_short_8","alias_value":"2RGDUNCB","created_at":"2026-05-18T12:29:55.572404+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/2RGDUNCB46AREAXUFUM6Q5X2A4","json":"https://pith.science/pith/2RGDUNCB46AREAXUFUM6Q5X2A4.json","graph_json":"https://pith.science/api/pith-number/2RGDUNCB46AREAXUFUM6Q5X2A4/graph.json","events_json":"https://pith.science/api/pith-number/2RGDUNCB46AREAXUFUM6Q5X2A4/events.json","paper":"https://pith.science/paper/2RGDUNCB"},"agent_actions":{"view_html":"https://pith.science/pith/2RGDUNCB46AREAXUFUM6Q5X2A4","download_json":"https://pith.science/pith/2RGDUNCB46AREAXUFUM6Q5X2A4.json","view_paper":"https://pith.science/paper/2RGDUNCB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1605.04553&json=true","fetch_graph":"https://pith.science/api/pith-number/2RGDUNCB46AREAXUFUM6Q5X2A4/graph.json","fetch_events":"https://pith.science/api/pith-number/2RGDUNCB46AREAXUFUM6Q5X2A4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2RGDUNCB46AREAXUFUM6Q5X2A4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2RGDUNCB46AREAXUFUM6Q5X2A4/action/storage_attestation","attest_author":"https://pith.science/pith/2RGDUNCB46AREAXUFUM6Q5X2A4/action/author_attestation","sign_citation":"https://pith.science/pith/2RGDUNCB46AREAXUFUM6Q5X2A4/action/citation_signature","submit_replication":"https://pith.science/pith/2RGDUNCB46AREAXUFUM6Q5X2A4/action/replication_record"}},"created_at":"2026-05-18T01:12:19.686430+00:00","updated_at":"2026-05-18T01:12:19.686430+00:00"}