{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VG44V6QBQ2H3XP3QL4GNBTBJXX","short_pith_number":"pith:VG44V6QB","schema_version":"1.0","canonical_sha256":"a9b9cafa01868fbbbf705f0cd0cc29bdf0eb385c50cadd84b9eff4faefb2bbdb","source":{"kind":"arxiv","id":"2501.04661","version":3},"attestation_state":"computed","paper":{"title":"Beyond Memorization: Assessing Semantic Generalization in Large Language Models Using Phrasal Constructions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Austin Blodgett, Claire Bonial, Harish Tayyar Madabushi, Melissa Torgbi, Mollie Shichman, Taylor Hudson, Wesley Scivetti","submitted_at":"2025-01-08T18:15:10Z","abstract_excerpt":"The web-scale of pretraining data has created an important evaluation challenge: to disentangle linguistic competence on cases well-represented in pretraining data from generalization to out-of-domain language, specifically the dynamic, real-world instances less common in pretraining data. To this end, we construct a diagnostic evaluation to systematically assess natural language understanding in LLMs by leveraging Construction Grammar (CxG). CxG provides a psycholinguistically grounded framework for testing generalization, as it explicitly links syntactic forms to abstract, non-lexical meanin"},"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":"2501.04661","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-08T18:15:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8c0916d40b8b20a94bd4c64ec75c486cbf27d6cec80d200df90efe9a253f9cfd","abstract_canon_sha256":"6d9b51b8c7c0a691a20a33c8bf16a2ea3484ce1a9d05b768e26cfe27359aedd6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T02:03:19.190871Z","signature_b64":"umhzUAbZGX8s/Bo4oe0lsTgMvr4Xz7Lqn2yIm5XCeugcXyYsEF76DT+kPV6TdupoF1N4TQ7Z1gXMAzwbL57EAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9b9cafa01868fbbbf705f0cd0cc29bdf0eb385c50cadd84b9eff4faefb2bbdb","last_reissued_at":"2026-06-01T02:03:19.189600Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T02:03:19.189600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Memorization: Assessing Semantic Generalization in Large Language Models Using Phrasal Constructions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Austin Blodgett, Claire Bonial, Harish Tayyar Madabushi, Melissa Torgbi, Mollie Shichman, Taylor Hudson, Wesley Scivetti","submitted_at":"2025-01-08T18:15:10Z","abstract_excerpt":"The web-scale of pretraining data has created an important evaluation challenge: to disentangle linguistic competence on cases well-represented in pretraining data from generalization to out-of-domain language, specifically the dynamic, real-world instances less common in pretraining data. To this end, we construct a diagnostic evaluation to systematically assess natural language understanding in LLMs by leveraging Construction Grammar (CxG). CxG provides a psycholinguistically grounded framework for testing generalization, as it explicitly links syntactic forms to abstract, non-lexical meanin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04661","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/2501.04661/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":"2501.04661","created_at":"2026-06-01T02:03:19.189784+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.04661v3","created_at":"2026-06-01T02:03:19.189784+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04661","created_at":"2026-06-01T02:03:19.189784+00:00"},{"alias_kind":"pith_short_12","alias_value":"VG44V6QBQ2H3","created_at":"2026-06-01T02:03:19.189784+00:00"},{"alias_kind":"pith_short_16","alias_value":"VG44V6QBQ2H3XP3Q","created_at":"2026-06-01T02:03:19.189784+00:00"},{"alias_kind":"pith_short_8","alias_value":"VG44V6QB","created_at":"2026-06-01T02:03:19.189784+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/VG44V6QBQ2H3XP3QL4GNBTBJXX","json":"https://pith.science/pith/VG44V6QBQ2H3XP3QL4GNBTBJXX.json","graph_json":"https://pith.science/api/pith-number/VG44V6QBQ2H3XP3QL4GNBTBJXX/graph.json","events_json":"https://pith.science/api/pith-number/VG44V6QBQ2H3XP3QL4GNBTBJXX/events.json","paper":"https://pith.science/paper/VG44V6QB"},"agent_actions":{"view_html":"https://pith.science/pith/VG44V6QBQ2H3XP3QL4GNBTBJXX","download_json":"https://pith.science/pith/VG44V6QBQ2H3XP3QL4GNBTBJXX.json","view_paper":"https://pith.science/paper/VG44V6QB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.04661&json=true","fetch_graph":"https://pith.science/api/pith-number/VG44V6QBQ2H3XP3QL4GNBTBJXX/graph.json","fetch_events":"https://pith.science/api/pith-number/VG44V6QBQ2H3XP3QL4GNBTBJXX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VG44V6QBQ2H3XP3QL4GNBTBJXX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VG44V6QBQ2H3XP3QL4GNBTBJXX/action/storage_attestation","attest_author":"https://pith.science/pith/VG44V6QBQ2H3XP3QL4GNBTBJXX/action/author_attestation","sign_citation":"https://pith.science/pith/VG44V6QBQ2H3XP3QL4GNBTBJXX/action/citation_signature","submit_replication":"https://pith.science/pith/VG44V6QBQ2H3XP3QL4GNBTBJXX/action/replication_record"}},"created_at":"2026-06-01T02:03:19.189784+00:00","updated_at":"2026-06-01T02:03:19.189784+00:00"}