{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:F6QWXLWLHLZ3HNAKEK62UCD3S5","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":"9fe569d6d5868ccb578517cd55e1f30d9cc18c3a5bab47d83d05f9ad3c1dd4f7","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-27T00:07:17Z","title_canon_sha256":"f36091534b2e24bc50a5f59295ce496554e0d2fb0c9ced417aaff890f51fe4dc"},"schema_version":"1.0","source":{"id":"2305.17311","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.17311","created_at":"2026-07-05T06:14:26Z"},{"alias_kind":"arxiv_version","alias_value":"2305.17311v1","created_at":"2026-07-05T06:14:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17311","created_at":"2026-07-05T06:14:26Z"},{"alias_kind":"pith_short_12","alias_value":"F6QWXLWLHLZ3","created_at":"2026-07-05T06:14:26Z"},{"alias_kind":"pith_short_16","alias_value":"F6QWXLWLHLZ3HNAK","created_at":"2026-07-05T06:14:26Z"},{"alias_kind":"pith_short_8","alias_value":"F6QWXLWL","created_at":"2026-07-05T06:14:26Z"}],"graph_snapshots":[{"event_id":"sha256:76b7057bb0384fc47acfde0f1b9b0bca4394e2a6a2734d8d99b6db69139694e1","target":"graph","created_at":"2026-07-05T06:14:26Z","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/2305.17311/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models have been shown to exhibit positive scaling, where performance improves as models are scaled up in terms of size, compute, or data. In this work, we introduce NeQA, a dataset consisting of questions with negation in which language models do not exhibit straightforward positive scaling. We show that this task can exhibit inverse scaling, U-shaped scaling, or positive scaling, and the three scaling trends shift in this order as we use more powerful prompting methods or model families. We hypothesize that solving NeQA depends on two subtasks: question answering (task 1) and negati","authors_text":"James Zou, Jeff Z. HaoChen, Michihiro Yasunaga, Percy Liang, Serena Yeung, Yuhui Zhang, Zhengping Zhou","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-27T00:07:17Z","title":"Beyond Positive Scaling: How Negation Impacts Scaling Trends of Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17311","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:c961f6a7bfb226fe28b3f64242186f763fab229b12a5fa945cabf53ad64e1542","target":"record","created_at":"2026-07-05T06:14:26Z","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":"9fe569d6d5868ccb578517cd55e1f30d9cc18c3a5bab47d83d05f9ad3c1dd4f7","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-27T00:07:17Z","title_canon_sha256":"f36091534b2e24bc50a5f59295ce496554e0d2fb0c9ced417aaff890f51fe4dc"},"schema_version":"1.0","source":{"id":"2305.17311","kind":"arxiv","version":1}},"canonical_sha256":"2fa16baecb3af3b3b40a22bdaa087b9773e7dc310f5dd03a568eeaef13d790f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2fa16baecb3af3b3b40a22bdaa087b9773e7dc310f5dd03a568eeaef13d790f2","first_computed_at":"2026-07-05T06:14:26.370991Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:14:26.370991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XkoEDWKc1poo4TSuTk1exzZVbNnCPUzZMTeH2puvPl7gK8xTp1naJq5mgNOTPQrDTo8xL7mbMN8RQPB5+YLBAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:14:26.371469Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.17311","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c961f6a7bfb226fe28b3f64242186f763fab229b12a5fa945cabf53ad64e1542","sha256:76b7057bb0384fc47acfde0f1b9b0bca4394e2a6a2734d8d99b6db69139694e1"],"state_sha256":"f2d9b7c9617719d4c4ae4d807d9fe57529ff5d45c5f7354232be24f219b3fc88"}