{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M3OZDLGBAPVCVR77P6DVAAJWYO","short_pith_number":"pith:M3OZDLGB","schema_version":"1.0","canonical_sha256":"66dd91acc103ea2ac7ff7f87500136c38790d403ea9248f3f483e43b6427c8fd","source":{"kind":"arxiv","id":"2406.17038","version":1},"attestation_state":"computed","paper":{"title":"modeLing: A Novel Dataset for Testing Linguistic Reasoning in Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dragomir Radev, Ethan A. Chi, Lucas Huang, Nathan A. Chi, Riley Kong, R. Thomas McCoy, Ryan A. Chi, Teodor Malchev","submitted_at":"2024-06-24T18:00:59Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2406.17038","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T18:00:59Z","cross_cats_sorted":[],"title_canon_sha256":"6c1e6002181b5686707468bf93b6f84cba8c14d2d3f25c49dd6408bb8bf67aae","abstract_canon_sha256":"bae9ffd3e797471ac3698a5660730155797e29d64970239bf7e56795b99a76dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:09.190975Z","signature_b64":"TMIKUAShNWoJKGv6PQi75oDEVwpUtpYz80m6gwO2svrQJztwIQYzpQjDDFWPVTz6XU9BGrej8BYq4+uuPKceCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66dd91acc103ea2ac7ff7f87500136c38790d403ea9248f3f483e43b6427c8fd","last_reissued_at":"2026-07-05T08:36:09.190441Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:09.190441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"modeLing: A Novel Dataset for Testing Linguistic Reasoning in Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dragomir Radev, Ethan A. Chi, Lucas Huang, Nathan A. Chi, Riley Kong, R. Thomas McCoy, Ryan A. Chi, Teodor Malchev","submitted_at":"2024-06-24T18:00:59Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17038","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2406.17038/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2406.17038","created_at":"2026-07-05T08:36:09.190509+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.17038v1","created_at":"2026-07-05T08:36:09.190509+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17038","created_at":"2026-07-05T08:36:09.190509+00:00"},{"alias_kind":"pith_short_12","alias_value":"M3OZDLGBAPVC","created_at":"2026-07-05T08:36:09.190509+00:00"},{"alias_kind":"pith_short_16","alias_value":"M3OZDLGBAPVCVR77","created_at":"2026-07-05T08:36:09.190509+00:00"},{"alias_kind":"pith_short_8","alias_value":"M3OZDLGB","created_at":"2026-07-05T08:36:09.190509+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.06211","citing_title":"PuzzleWorld: A Benchmark for Multimodal, Open-Ended Reasoning in Puzzlehunts","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M3OZDLGBAPVCVR77P6DVAAJWYO","json":"https://pith.science/pith/M3OZDLGBAPVCVR77P6DVAAJWYO.json","graph_json":"https://pith.science/api/pith-number/M3OZDLGBAPVCVR77P6DVAAJWYO/graph.json","events_json":"https://pith.science/api/pith-number/M3OZDLGBAPVCVR77P6DVAAJWYO/events.json","paper":"https://pith.science/paper/M3OZDLGB"},"agent_actions":{"view_html":"https://pith.science/pith/M3OZDLGBAPVCVR77P6DVAAJWYO","download_json":"https://pith.science/pith/M3OZDLGBAPVCVR77P6DVAAJWYO.json","view_paper":"https://pith.science/paper/M3OZDLGB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.17038&json=true","fetch_graph":"https://pith.science/api/pith-number/M3OZDLGBAPVCVR77P6DVAAJWYO/graph.json","fetch_events":"https://pith.science/api/pith-number/M3OZDLGBAPVCVR77P6DVAAJWYO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M3OZDLGBAPVCVR77P6DVAAJWYO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M3OZDLGBAPVCVR77P6DVAAJWYO/action/storage_attestation","attest_author":"https://pith.science/pith/M3OZDLGBAPVCVR77P6DVAAJWYO/action/author_attestation","sign_citation":"https://pith.science/pith/M3OZDLGBAPVCVR77P6DVAAJWYO/action/citation_signature","submit_replication":"https://pith.science/pith/M3OZDLGBAPVCVR77P6DVAAJWYO/action/replication_record"}},"created_at":"2026-07-05T08:36:09.190509+00:00","updated_at":"2026-07-05T08:36:09.190509+00:00"}