{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F5F7R23GD3GK5OWHYB3WLQTN3P","short_pith_number":"pith:F5F7R23G","schema_version":"1.0","canonical_sha256":"2f4bf8eb661eccaebac7c07765c26ddbefa28a741b80863d18f688851f09397c","source":{"kind":"arxiv","id":"2410.15173","version":4},"attestation_state":"computed","paper":{"title":"Uncovering Autoregressive LLM Knowledge of Thematic Fit in Event Representation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Daniel Bauer, Safeyah Khaled Alshemali, Yuval Marton","submitted_at":"2024-10-19T18:25:30Z","abstract_excerpt":"The thematic fit estimation task measures semantic arguments' compatibility with a given semantic role for a given predicate. We investigate if autoregressive LLMs have consistent, expressible knowledge of event arguments' thematic fit by experimenting with various prompt designs, manipulating input context, reasoning, and output forms. We set a new state-of-the-art on thematic fit benchmarks, but show that closed and open weight LLMs respond differently to our prompting strategies: Closed models achieve better scores overall and benefit from multi-step reasoning, but they perform worse at fil"},"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":"2410.15173","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-19T18:25:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9fec4518623ff40738be1963adf7d9d8e54432a869717cf527ee4cc27515a952","abstract_canon_sha256":"d52f00c811f59d5e513f7ad06ad0f850ac21c24ca57c3474856e6c676b9baa6e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:09.460838Z","signature_b64":"qPnQi65m3ry942Lt58loTOOHZKdElWHSy78WCTP4Zoo3qlv8bDSodYaAEou4fkVepdShPDa/CX5/k/8jTqT/DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f4bf8eb661eccaebac7c07765c26ddbefa28a741b80863d18f688851f09397c","last_reissued_at":"2026-05-26T01:03:09.460049Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:09.460049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uncovering Autoregressive LLM Knowledge of Thematic Fit in Event Representation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Daniel Bauer, Safeyah Khaled Alshemali, Yuval Marton","submitted_at":"2024-10-19T18:25:30Z","abstract_excerpt":"The thematic fit estimation task measures semantic arguments' compatibility with a given semantic role for a given predicate. We investigate if autoregressive LLMs have consistent, expressible knowledge of event arguments' thematic fit by experimenting with various prompt designs, manipulating input context, reasoning, and output forms. We set a new state-of-the-art on thematic fit benchmarks, but show that closed and open weight LLMs respond differently to our prompting strategies: Closed models achieve better scores overall and benefit from multi-step reasoning, but they perform worse at fil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.15173","kind":"arxiv","version":4},"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/2410.15173/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":"2410.15173","created_at":"2026-05-26T01:03:09.460178+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.15173v4","created_at":"2026-05-26T01:03:09.460178+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15173","created_at":"2026-05-26T01:03:09.460178+00:00"},{"alias_kind":"pith_short_12","alias_value":"F5F7R23GD3GK","created_at":"2026-05-26T01:03:09.460178+00:00"},{"alias_kind":"pith_short_16","alias_value":"F5F7R23GD3GK5OWH","created_at":"2026-05-26T01:03:09.460178+00:00"},{"alias_kind":"pith_short_8","alias_value":"F5F7R23G","created_at":"2026-05-26T01:03:09.460178+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/F5F7R23GD3GK5OWHYB3WLQTN3P","json":"https://pith.science/pith/F5F7R23GD3GK5OWHYB3WLQTN3P.json","graph_json":"https://pith.science/api/pith-number/F5F7R23GD3GK5OWHYB3WLQTN3P/graph.json","events_json":"https://pith.science/api/pith-number/F5F7R23GD3GK5OWHYB3WLQTN3P/events.json","paper":"https://pith.science/paper/F5F7R23G"},"agent_actions":{"view_html":"https://pith.science/pith/F5F7R23GD3GK5OWHYB3WLQTN3P","download_json":"https://pith.science/pith/F5F7R23GD3GK5OWHYB3WLQTN3P.json","view_paper":"https://pith.science/paper/F5F7R23G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.15173&json=true","fetch_graph":"https://pith.science/api/pith-number/F5F7R23GD3GK5OWHYB3WLQTN3P/graph.json","fetch_events":"https://pith.science/api/pith-number/F5F7R23GD3GK5OWHYB3WLQTN3P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F5F7R23GD3GK5OWHYB3WLQTN3P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F5F7R23GD3GK5OWHYB3WLQTN3P/action/storage_attestation","attest_author":"https://pith.science/pith/F5F7R23GD3GK5OWHYB3WLQTN3P/action/author_attestation","sign_citation":"https://pith.science/pith/F5F7R23GD3GK5OWHYB3WLQTN3P/action/citation_signature","submit_replication":"https://pith.science/pith/F5F7R23GD3GK5OWHYB3WLQTN3P/action/replication_record"}},"created_at":"2026-05-26T01:03:09.460178+00:00","updated_at":"2026-05-26T01:03:09.460178+00:00"}