{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:PJSA6RHBRDAXT4WE3DZMEJFFUV","short_pith_number":"pith:PJSA6RHB","schema_version":"1.0","canonical_sha256":"7a640f44e188c179f2c4d8f2c224a5a577dea900944271958304c43f4e59b95b","source":{"kind":"arxiv","id":"2210.04714","version":2},"attestation_state":"computed","paper":{"title":"Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Louis-Philippe Morency, Paul Pu Liang, Ruslan Salakhutdinov, Umang Bhatt, Willie Neiswanger, Yuxin Xiao","submitted_at":"2022-10-10T14:16:01Z","abstract_excerpt":"Pre-trained language models (PLMs) have gained increasing popularity due to their compelling prediction performance in diverse natural language processing (NLP) tasks. When formulating a PLM-based prediction pipeline for NLP tasks, it is also crucial for the pipeline to minimize the calibration error, especially in safety-critical applications. That is, the pipeline should reliably indicate when we can trust its predictions. In particular, there are various considerations behind the pipeline: (1) the choice and (2) the size of PLM, (3) the choice of uncertainty quantifier, (4) the choice of fi"},"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":"2210.04714","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-10T14:16:01Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"284a4f8ada9d1d220f7c623271bccbc37aa2f67ec4b79f2c0781172eca9d040d","abstract_canon_sha256":"c7ff64d2b7d61f3c2df329cab627a3e4a6e3438546238688183e09720926dccc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:34.561510Z","signature_b64":"pAWpG5u/mZE81JFlWn04vAbH4jMukZSNKNgx5VCnyh7PcFKhQtEc0BCKb5aSqi7REseqQjgeGP+QsbRNQu3HCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a640f44e188c179f2c4d8f2c224a5a577dea900944271958304c43f4e59b95b","last_reissued_at":"2026-07-05T05:06:34.561042Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:34.561042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Louis-Philippe Morency, Paul Pu Liang, Ruslan Salakhutdinov, Umang Bhatt, Willie Neiswanger, Yuxin Xiao","submitted_at":"2022-10-10T14:16:01Z","abstract_excerpt":"Pre-trained language models (PLMs) have gained increasing popularity due to their compelling prediction performance in diverse natural language processing (NLP) tasks. When formulating a PLM-based prediction pipeline for NLP tasks, it is also crucial for the pipeline to minimize the calibration error, especially in safety-critical applications. That is, the pipeline should reliably indicate when we can trust its predictions. In particular, there are various considerations behind the pipeline: (1) the choice and (2) the size of PLM, (3) the choice of uncertainty quantifier, (4) the choice of fi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.04714","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/2210.04714/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":"2210.04714","created_at":"2026-07-05T05:06:34.561122+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.04714v2","created_at":"2026-07-05T05:06:34.561122+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.04714","created_at":"2026-07-05T05:06:34.561122+00:00"},{"alias_kind":"pith_short_12","alias_value":"PJSA6RHBRDAX","created_at":"2026-07-05T05:06:34.561122+00:00"},{"alias_kind":"pith_short_16","alias_value":"PJSA6RHBRDAXT4WE","created_at":"2026-07-05T05:06:34.561122+00:00"},{"alias_kind":"pith_short_8","alias_value":"PJSA6RHB","created_at":"2026-07-05T05:06:34.561122+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.17200","citing_title":"Calibrating Model-Based Evaluation Metrics for Summarization","ref_index":68,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PJSA6RHBRDAXT4WE3DZMEJFFUV","json":"https://pith.science/pith/PJSA6RHBRDAXT4WE3DZMEJFFUV.json","graph_json":"https://pith.science/api/pith-number/PJSA6RHBRDAXT4WE3DZMEJFFUV/graph.json","events_json":"https://pith.science/api/pith-number/PJSA6RHBRDAXT4WE3DZMEJFFUV/events.json","paper":"https://pith.science/paper/PJSA6RHB"},"agent_actions":{"view_html":"https://pith.science/pith/PJSA6RHBRDAXT4WE3DZMEJFFUV","download_json":"https://pith.science/pith/PJSA6RHBRDAXT4WE3DZMEJFFUV.json","view_paper":"https://pith.science/paper/PJSA6RHB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.04714&json=true","fetch_graph":"https://pith.science/api/pith-number/PJSA6RHBRDAXT4WE3DZMEJFFUV/graph.json","fetch_events":"https://pith.science/api/pith-number/PJSA6RHBRDAXT4WE3DZMEJFFUV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PJSA6RHBRDAXT4WE3DZMEJFFUV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PJSA6RHBRDAXT4WE3DZMEJFFUV/action/storage_attestation","attest_author":"https://pith.science/pith/PJSA6RHBRDAXT4WE3DZMEJFFUV/action/author_attestation","sign_citation":"https://pith.science/pith/PJSA6RHBRDAXT4WE3DZMEJFFUV/action/citation_signature","submit_replication":"https://pith.science/pith/PJSA6RHBRDAXT4WE3DZMEJFFUV/action/replication_record"}},"created_at":"2026-07-05T05:06:34.561122+00:00","updated_at":"2026-07-05T05:06:34.561122+00:00"}