{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IRDXWI6EBSPBGZZ25VWE5S4CPE","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":"b3ff5e8b0226950ed1149c5d131329de6c8bb812893407b1f2815cf6dc52c2da","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T13:19:38Z","title_canon_sha256":"d95031b26f8e03c401fad615385ae846a332369243f15bad967268d9dbf60c89"},"schema_version":"1.0","source":{"id":"2412.12893","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.12893","created_at":"2026-07-05T09:50:22Z"},{"alias_kind":"arxiv_version","alias_value":"2412.12893v1","created_at":"2026-07-05T09:50:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12893","created_at":"2026-07-05T09:50:22Z"},{"alias_kind":"pith_short_12","alias_value":"IRDXWI6EBSPB","created_at":"2026-07-05T09:50:22Z"},{"alias_kind":"pith_short_16","alias_value":"IRDXWI6EBSPBGZZ2","created_at":"2026-07-05T09:50:22Z"},{"alias_kind":"pith_short_8","alias_value":"IRDXWI6E","created_at":"2026-07-05T09:50:22Z"}],"graph_snapshots":[{"event_id":"sha256:c0361ae106ee8caa057896b21708352743285927e9ce969bb5be7d452f1663e8","target":"graph","created_at":"2026-07-05T09:50:22Z","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/2412.12893/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have been showing promising results for various NLP-tasks without the explicit need to be trained for these tasks by using few-shot or zero-shot prompting techniques. A common NLP-task is question-answering (QA). In this study, we propose a comprehensive performance comparison between smaller fine-tuned models and out-of-the-box instruction-following LLMs on the Stanford Question Answering Dataset 2.0 (SQuAD2), specifically when using a single-inference prompting technique. Since the dataset contains unanswerable questions, previous work used a double inference met","authors_text":"Darren F\\\"urst, Jakob Lindner, Kevin Fischer, Sebastian Steindl, Ulrich Sch\\\"afer","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T13:19:38Z","title":"Question: How do Large Language Models perform on the Question Answering tasks? Answer:"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12893","kind":"arxiv","version":1},"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":"sha256:70d941bb2f68fff87161526eaac8ba8a79553f5bcfb4319005f59940495eedd3","target":"record","created_at":"2026-07-05T09:50:22Z","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":"b3ff5e8b0226950ed1149c5d131329de6c8bb812893407b1f2815cf6dc52c2da","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T13:19:38Z","title_canon_sha256":"d95031b26f8e03c401fad615385ae846a332369243f15bad967268d9dbf60c89"},"schema_version":"1.0","source":{"id":"2412.12893","kind":"arxiv","version":1}},"canonical_sha256":"44477b23c40c9e13673aed6c4ecb827919dd3b00fdec5e686157973df89737ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"44477b23c40c9e13673aed6c4ecb827919dd3b00fdec5e686157973df89737ab","first_computed_at":"2026-07-05T09:50:22.263961Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:50:22.263961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n6WSymZJValycY30gzsJ5xS+rDrh+w72nG+r7SOnN/ybiREaSvyrY226QhUI4oQdg5KfBsUJ9OE1TTBdo5z6Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:50:22.264447Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.12893","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70d941bb2f68fff87161526eaac8ba8a79553f5bcfb4319005f59940495eedd3","sha256:c0361ae106ee8caa057896b21708352743285927e9ce969bb5be7d452f1663e8"],"state_sha256":"9572cbbc69e4aca47bfa732b561b85223612b934bba19110649bf72d0037777c"}