{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:M3OZDLGBAPVCVR77P6DVAAJWYO","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":"bae9ffd3e797471ac3698a5660730155797e29d64970239bf7e56795b99a76dc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T18:00:59Z","title_canon_sha256":"6c1e6002181b5686707468bf93b6f84cba8c14d2d3f25c49dd6408bb8bf67aae"},"schema_version":"1.0","source":{"id":"2406.17038","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.17038","created_at":"2026-07-05T08:36:09Z"},{"alias_kind":"arxiv_version","alias_value":"2406.17038v1","created_at":"2026-07-05T08:36:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17038","created_at":"2026-07-05T08:36:09Z"},{"alias_kind":"pith_short_12","alias_value":"M3OZDLGBAPVC","created_at":"2026-07-05T08:36:09Z"},{"alias_kind":"pith_short_16","alias_value":"M3OZDLGBAPVCVR77","created_at":"2026-07-05T08:36:09Z"},{"alias_kind":"pith_short_8","alias_value":"M3OZDLGB","created_at":"2026-07-05T08:36:09Z"}],"graph_snapshots":[{"event_id":"sha256:18472e6e4e347481bd08abf65d91f57b65d6110a8416ad70fd1990862f706262","target":"graph","created_at":"2026-07-05T08:36:09Z","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/2406.17038/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce modeLing, a novel benchmark of Linguistics Olympiad-style puzzles which tests few-shot reasoning in AI systems. Solving these puzzles necessitates inferring aspects of a language's grammatical structure from a small number of examples. Such puzzles provide a natural testbed for language models, as they require compositional generalization and few-shot inductive reasoning. Consisting solely of new puzzles written specifically for this work, modeLing has no risk of appearing in the training data of existing AI systems: this ameliorates the risk of data leakage, a potential confounde","authors_text":"Dragomir Radev, Ethan A. Chi, Lucas Huang, Nathan A. Chi, Riley Kong, R. Thomas McCoy, Ryan A. Chi, Teodor Malchev","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T18:00:59Z","title":"modeLing: A Novel Dataset for Testing Linguistic Reasoning in Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17038","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":"sha256:5e8540bbc50fccb46c4db5c515c89c77b7ce418e313c80cb407b69e21488fe48","target":"record","created_at":"2026-07-05T08:36:09Z","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":"bae9ffd3e797471ac3698a5660730155797e29d64970239bf7e56795b99a76dc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T18:00:59Z","title_canon_sha256":"6c1e6002181b5686707468bf93b6f84cba8c14d2d3f25c49dd6408bb8bf67aae"},"schema_version":"1.0","source":{"id":"2406.17038","kind":"arxiv","version":1}},"canonical_sha256":"66dd91acc103ea2ac7ff7f87500136c38790d403ea9248f3f483e43b6427c8fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66dd91acc103ea2ac7ff7f87500136c38790d403ea9248f3f483e43b6427c8fd","first_computed_at":"2026-07-05T08:36:09.190441Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:36:09.190441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TMIKUAShNWoJKGv6PQi75oDEVwpUtpYz80m6gwO2svrQJztwIQYzpQjDDFWPVTz6XU9BGrej8BYq4+uuPKceCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:36:09.190975Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.17038","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e8540bbc50fccb46c4db5c515c89c77b7ce418e313c80cb407b69e21488fe48","sha256:18472e6e4e347481bd08abf65d91f57b65d6110a8416ad70fd1990862f706262"],"state_sha256":"1db6d9408b54e95c6707df372e5086003fbbc74d1ffb7e9cb4221f11e60788ea"}