{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LGNEU5DVCV46SQGRRDIRAQP3GS","short_pith_number":"pith:LGNEU5DV","schema_version":"1.0","canonical_sha256":"599a4a74751579e940d188d11041fb3496d5329068740ef98d9f2a56915028d8","source":{"kind":"arxiv","id":"2402.00123","version":2},"attestation_state":"computed","paper":{"title":"Comparing Template-based and Template-free Language Model Probing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Katharina von der Wense, Kevin Bennett, Lawrence E Hunter, Sagi Shaier","submitted_at":"2024-01-31T19:07:37Z","abstract_excerpt":"The differences between cloze-task language model (LM) probing with 1) expert-made templates and 2) naturally-occurring text have often been overlooked. Here, we evaluate 16 different LMs on 10 probing English datasets -- 4 template-based and 6 template-free -- in general and biomedical domains to answer the following research questions: (RQ1) Do model rankings differ between the two approaches? (RQ2) Do models' absolute scores differ between the two approaches? (RQ3) Do the answers to RQ1 and RQ2 differ between general and domain-specific models? Our findings are: 1) Template-free and templat"},"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":"2402.00123","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-31T19:07:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"55b4709ca6cf19e7e79cd42ee6a895a2c322aca5f16ec13cfc202e4aaab4a230","abstract_canon_sha256":"3cab90673c2e41d7338497f9265e03c80cf467ad537e407becd9c73ec21b139d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:10.354059Z","signature_b64":"zmHX5BoanixZSK4hXJP10wEvaxZqyaJ5XaVGaR4ajOe35ljRsaU2M8hG4AQiH8Aect31wgvFowpO+cylJsccDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"599a4a74751579e940d188d11041fb3496d5329068740ef98d9f2a56915028d8","last_reissued_at":"2026-07-05T09:28:10.353605Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:10.353605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Comparing Template-based and Template-free Language Model Probing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Katharina von der Wense, Kevin Bennett, Lawrence E Hunter, Sagi Shaier","submitted_at":"2024-01-31T19:07:37Z","abstract_excerpt":"The differences between cloze-task language model (LM) probing with 1) expert-made templates and 2) naturally-occurring text have often been overlooked. Here, we evaluate 16 different LMs on 10 probing English datasets -- 4 template-based and 6 template-free -- in general and biomedical domains to answer the following research questions: (RQ1) Do model rankings differ between the two approaches? (RQ2) Do models' absolute scores differ between the two approaches? (RQ3) Do the answers to RQ1 and RQ2 differ between general and domain-specific models? Our findings are: 1) Template-free and templat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.00123","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.00123/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":"2402.00123","created_at":"2026-07-05T09:28:10.353673+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.00123v2","created_at":"2026-07-05T09:28:10.353673+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.00123","created_at":"2026-07-05T09:28:10.353673+00:00"},{"alias_kind":"pith_short_12","alias_value":"LGNEU5DVCV46","created_at":"2026-07-05T09:28:10.353673+00:00"},{"alias_kind":"pith_short_16","alias_value":"LGNEU5DVCV46SQGR","created_at":"2026-07-05T09:28:10.353673+00:00"},{"alias_kind":"pith_short_8","alias_value":"LGNEU5DV","created_at":"2026-07-05T09:28:10.353673+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.20737","citing_title":"Rethinking Testing for LLM Applications: Characteristics, Challenges, and a Lightweight Interaction Protocol","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LGNEU5DVCV46SQGRRDIRAQP3GS","json":"https://pith.science/pith/LGNEU5DVCV46SQGRRDIRAQP3GS.json","graph_json":"https://pith.science/api/pith-number/LGNEU5DVCV46SQGRRDIRAQP3GS/graph.json","events_json":"https://pith.science/api/pith-number/LGNEU5DVCV46SQGRRDIRAQP3GS/events.json","paper":"https://pith.science/paper/LGNEU5DV"},"agent_actions":{"view_html":"https://pith.science/pith/LGNEU5DVCV46SQGRRDIRAQP3GS","download_json":"https://pith.science/pith/LGNEU5DVCV46SQGRRDIRAQP3GS.json","view_paper":"https://pith.science/paper/LGNEU5DV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.00123&json=true","fetch_graph":"https://pith.science/api/pith-number/LGNEU5DVCV46SQGRRDIRAQP3GS/graph.json","fetch_events":"https://pith.science/api/pith-number/LGNEU5DVCV46SQGRRDIRAQP3GS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LGNEU5DVCV46SQGRRDIRAQP3GS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LGNEU5DVCV46SQGRRDIRAQP3GS/action/storage_attestation","attest_author":"https://pith.science/pith/LGNEU5DVCV46SQGRRDIRAQP3GS/action/author_attestation","sign_citation":"https://pith.science/pith/LGNEU5DVCV46SQGRRDIRAQP3GS/action/citation_signature","submit_replication":"https://pith.science/pith/LGNEU5DVCV46SQGRRDIRAQP3GS/action/replication_record"}},"created_at":"2026-07-05T09:28:10.353673+00:00","updated_at":"2026-07-05T09:28:10.353673+00:00"}