{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:P6OZKSJFO5DAZLYBOUH34UDJKG","short_pith_number":"pith:P6OZKSJF","schema_version":"1.0","canonical_sha256":"7f9d95492577460caf01750fbe506951aa9a1ee826878ba359ba77e5a7837ea6","source":{"kind":"arxiv","id":"2508.11828","version":1},"attestation_state":"computed","paper":{"title":"A Survey of Idiom Datasets for Psycholinguistic and Computational Research","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anna Feldman, Michael Flor, Xinyi Liu","submitted_at":"2025-08-15T22:24:09Z","abstract_excerpt":"Idioms are figurative expressions whose meanings often cannot be inferred from their individual words, making them difficult to process computationally and posing challenges for human experimental studies. This survey reviews datasets developed in psycholinguistics and computational linguistics for studying idioms, focusing on their content, form, and intended use. Psycholinguistic resources typically contain normed ratings along dimensions such as familiarity, transparency, and compositionality, while computational datasets support tasks like idiomaticity detection/classification, paraphrasin"},"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":"2508.11828","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-15T22:24:09Z","cross_cats_sorted":[],"title_canon_sha256":"39ef78fae6eb1ea81bf918d7b102ef5333b36c45720f5b8db2fc184540d1bf16","abstract_canon_sha256":"d5bee17323c396adefac3926a8e8295616a28bc98237804f93a1f93b14fe4968"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:55.381000Z","signature_b64":"U2yadpwUDU4hTbZi8fZgPSMUxeFt66qaBD9YfODFXyGRkyVgE0Ncqqoud5IMsujGAQxWOql3TUcQeaHOMdx9Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f9d95492577460caf01750fbe506951aa9a1ee826878ba359ba77e5a7837ea6","last_reissued_at":"2026-07-05T11:54:55.380540Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:55.380540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey of Idiom Datasets for Psycholinguistic and Computational Research","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anna Feldman, Michael Flor, Xinyi Liu","submitted_at":"2025-08-15T22:24:09Z","abstract_excerpt":"Idioms are figurative expressions whose meanings often cannot be inferred from their individual words, making them difficult to process computationally and posing challenges for human experimental studies. This survey reviews datasets developed in psycholinguistics and computational linguistics for studying idioms, focusing on their content, form, and intended use. Psycholinguistic resources typically contain normed ratings along dimensions such as familiarity, transparency, and compositionality, while computational datasets support tasks like idiomaticity detection/classification, paraphrasin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.11828","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/2508.11828/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":"2508.11828","created_at":"2026-07-05T11:54:55.380605+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.11828v1","created_at":"2026-07-05T11:54:55.380605+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.11828","created_at":"2026-07-05T11:54:55.380605+00:00"},{"alias_kind":"pith_short_12","alias_value":"P6OZKSJFO5DA","created_at":"2026-07-05T11:54:55.380605+00:00"},{"alias_kind":"pith_short_16","alias_value":"P6OZKSJFO5DAZLYB","created_at":"2026-07-05T11:54:55.380605+00:00"},{"alias_kind":"pith_short_8","alias_value":"P6OZKSJF","created_at":"2026-07-05T11:54:55.380605+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/P6OZKSJFO5DAZLYBOUH34UDJKG","json":"https://pith.science/pith/P6OZKSJFO5DAZLYBOUH34UDJKG.json","graph_json":"https://pith.science/api/pith-number/P6OZKSJFO5DAZLYBOUH34UDJKG/graph.json","events_json":"https://pith.science/api/pith-number/P6OZKSJFO5DAZLYBOUH34UDJKG/events.json","paper":"https://pith.science/paper/P6OZKSJF"},"agent_actions":{"view_html":"https://pith.science/pith/P6OZKSJFO5DAZLYBOUH34UDJKG","download_json":"https://pith.science/pith/P6OZKSJFO5DAZLYBOUH34UDJKG.json","view_paper":"https://pith.science/paper/P6OZKSJF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.11828&json=true","fetch_graph":"https://pith.science/api/pith-number/P6OZKSJFO5DAZLYBOUH34UDJKG/graph.json","fetch_events":"https://pith.science/api/pith-number/P6OZKSJFO5DAZLYBOUH34UDJKG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P6OZKSJFO5DAZLYBOUH34UDJKG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P6OZKSJFO5DAZLYBOUH34UDJKG/action/storage_attestation","attest_author":"https://pith.science/pith/P6OZKSJFO5DAZLYBOUH34UDJKG/action/author_attestation","sign_citation":"https://pith.science/pith/P6OZKSJFO5DAZLYBOUH34UDJKG/action/citation_signature","submit_replication":"https://pith.science/pith/P6OZKSJFO5DAZLYBOUH34UDJKG/action/replication_record"}},"created_at":"2026-07-05T11:54:55.380605+00:00","updated_at":"2026-07-05T11:54:55.380605+00:00"}