{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:BPROKP4IQW2PZDBWPAAUIMDQJC","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3a138a970f30f09142decececffdb0d783c533def121354e077cf769e03eef44","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-08-21T08:46:36Z","title_canon_sha256":"fd6d4624b6d7006f58ccc1c64d31a4baa433d722ab46ecd9114d0d5f0a82b482"},"schema_version":"1.0","source":{"id":"2008.09371","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.09371","created_at":"2026-07-05T04:12:14Z"},{"alias_kind":"arxiv_version","alias_value":"2008.09371v3","created_at":"2026-07-05T04:12:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.09371","created_at":"2026-07-05T04:12:14Z"},{"alias_kind":"pith_short_12","alias_value":"BPROKP4IQW2P","created_at":"2026-07-05T04:12:14Z"},{"alias_kind":"pith_short_16","alias_value":"BPROKP4IQW2PZDBW","created_at":"2026-07-05T04:12:14Z"},{"alias_kind":"pith_short_8","alias_value":"BPROKP4I","created_at":"2026-07-05T04:12:14Z"}],"graph_snapshots":[{"event_id":"sha256:1dd96a57d0ea69437407daa6a793813b9a3971e72d67720575ff99736dc5757d","target":"graph","created_at":"2026-07-05T04:12:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2008.09371/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"It's better to say \"I can't answer\" than to answer incorrectly. This selective prediction ability is crucial for NLP systems to be reliably deployed in real-world applications. Prior work has shown that existing selective prediction techniques fail to perform well, especially in the out-of-domain setting. In this work, we propose a method that improves probability estimates of models by calibrating them using prediction confidence and difficulty score of instances. Using these two signals, we first annotate held-out instances and then train a calibrator to predict the likelihood of correctness","authors_text":"Chitta Baral, Neeraj Varshney, Swaroop Mishra","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-08-21T08:46:36Z","title":"Towards Improving Selective Prediction Ability of NLP Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.09371","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:67e8d3f34438937f20244000df0b780675fda2faf82e706bd0139bf1b91248be","target":"record","created_at":"2026-07-05T04:12:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3a138a970f30f09142decececffdb0d783c533def121354e077cf769e03eef44","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-08-21T08:46:36Z","title_canon_sha256":"fd6d4624b6d7006f58ccc1c64d31a4baa433d722ab46ecd9114d0d5f0a82b482"},"schema_version":"1.0","source":{"id":"2008.09371","kind":"arxiv","version":3}},"canonical_sha256":"0be2e53f8885b4fc8c36780144307048a64ce0a88ee0d59f4dfeed66325fb2fb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0be2e53f8885b4fc8c36780144307048a64ce0a88ee0d59f4dfeed66325fb2fb","first_computed_at":"2026-07-05T04:12:14.570754Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:12:14.570754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ee3Hz+6oWd1tul6yzSmEAK49Qrbxqo8GE+PK/4gxt+GqXR+BihE1KzSb0ioOTnI8KvdAFb5b1bab7NKzBJfwAA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:12:14.571286Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.09371","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:67e8d3f34438937f20244000df0b780675fda2faf82e706bd0139bf1b91248be","sha256:1dd96a57d0ea69437407daa6a793813b9a3971e72d67720575ff99736dc5757d"],"state_sha256":"d983459330c5c9be1a18daa60803cdef3ce7f608709b44db1a30d76ee4d4ce9f"}