{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:RUJOJJ7FKYKW36YTJOU7JFQCEX","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":"02f04e8409d36fde424c6e74dd0ab9f453416eeb1815d707591ea610be50330d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-12-02T05:42:41Z","title_canon_sha256":"dab32b42cf42007baf7a1053797e9a7ab4aaa5340ffdb1268ea17fe70a2812aa"},"schema_version":"1.0","source":{"id":"1912.00582","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.00582","created_at":"2026-07-05T05:41:13Z"},{"alias_kind":"arxiv_version","alias_value":"1912.00582v4","created_at":"2026-07-05T05:41:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.00582","created_at":"2026-07-05T05:41:13Z"},{"alias_kind":"pith_short_12","alias_value":"RUJOJJ7FKYKW","created_at":"2026-07-05T05:41:13Z"},{"alias_kind":"pith_short_16","alias_value":"RUJOJJ7FKYKW36YT","created_at":"2026-07-05T05:41:13Z"},{"alias_kind":"pith_short_8","alias_value":"RUJOJJ7F","created_at":"2026-07-05T05:41:13Z"}],"graph_snapshots":[{"event_id":"sha256:ad275d948446f8cc9331d64a51d2a2c10b4bbbaa2924d0d476b941034fada7d5","target":"graph","created_at":"2026-07-05T05:41:13Z","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/1912.00582/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce The Benchmark of Linguistic Minimal Pairs (shortened to BLiMP), a challenge set for evaluating what language models (LMs) know about major grammatical phenomena in English. BLiMP consists of 67 sub-datasets, each containing 1000 minimal pairs isolating specific contrasts in syntax, morphology, or semantics. The data is automatically generated according to expert-crafted grammars, and aggregate human agreement with the labels is 96.4%. We use it to evaluate n-gram, LSTM, and Transformer (GPT-2 and Transformer-XL) LMs. We find that state-of-the-art models identify morphological cont","authors_text":"Alex Warstadt, Alicia Parrish, Anhad Mohananey, Haokun Liu, Samuel R. Bowman, Sheng-Fu Wang, Wei Peng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-12-02T05:42:41Z","title":"BLiMP: The Benchmark of Linguistic Minimal Pairs for English"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.00582","kind":"arxiv","version":4},"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":"sha256:938cd8fb5caff390feda35418b25c8b7659edbcadef905f9d2cfbb74994f9283","target":"record","created_at":"2026-07-05T05:41:13Z","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":"02f04e8409d36fde424c6e74dd0ab9f453416eeb1815d707591ea610be50330d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-12-02T05:42:41Z","title_canon_sha256":"dab32b42cf42007baf7a1053797e9a7ab4aaa5340ffdb1268ea17fe70a2812aa"},"schema_version":"1.0","source":{"id":"1912.00582","kind":"arxiv","version":4}},"canonical_sha256":"8d12e4a7e556156dfb134ba9f4960225cf074009d522360f19c54b7fef88cc59","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d12e4a7e556156dfb134ba9f4960225cf074009d522360f19c54b7fef88cc59","first_computed_at":"2026-07-05T05:41:13.476741Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:41:13.476741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nl57K5bRkgenBzeRJaM45eqE31Pb5gMJBQ+ZFVUmmEVQdMujS1jHwq91eDEoXPXoDOCQjU+eK1t9unwFdtGpDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:41:13.477155Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.00582","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:938cd8fb5caff390feda35418b25c8b7659edbcadef905f9d2cfbb74994f9283","sha256:ad275d948446f8cc9331d64a51d2a2c10b4bbbaa2924d0d476b941034fada7d5"],"state_sha256":"b50f976c27cbbe7ce16bf17aae20b8b82a554806edfa0c2bbc20ca15dba7deb1"}