{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EOXZTLKFND4XCD5Z3ZO2DV5UZC","short_pith_number":"pith:EOXZTLKF","schema_version":"1.0","canonical_sha256":"23af99ad4568f9710fb9de5da1d7b4c8803aebd186c4dadc4d84bb430a5db2ba","source":{"kind":"arxiv","id":"2605.13408","version":1},"attestation_state":"computed","paper":{"title":"From Rosetta to Match-Up: A Paired Corpus of Linguistic Puzzles with Human and LLM Benchmarks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A conversion procedure turns Rosetta Stone puzzles into Match-Up versions that both expert humans and LLMs either solve completely or fail entirely.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anne Huang, Elena Filatova, Jinfan Frank Hu, Neh Majmudar","submitted_at":"2026-05-13T12:03:35Z","abstract_excerpt":"In this paper, we examine linguistic puzzles used in high school linguistics competitions, focusing on two common formats: Rosetta Stone and Match-Up. We propose a systematic procedure for converting existing Rosetta Stone puzzles into corresponding Match-Up counterparts. Because linguistic puzzle creation is complex and time-consuming, our method provides an efficient way to accelerate the generation of new puzzles. We evaluate the resulting Rosetta Stone-Match-Up pairs with both human participants and large language models (LLMs). Our results show that both expert human solvers and LLMs disp"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.13408","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T12:03:35Z","cross_cats_sorted":[],"title_canon_sha256":"164259911cf09cb2afcbaf9df6f0ca83ab153f454bbf879a2f30d38a592ef7d3","abstract_canon_sha256":"2adc96a7298c922e89e4484b313b5463db7ffca7eaac6d328f46f3db02fc521b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:47.480882Z","signature_b64":"NU40hW7SVmtAmiOQNm36mDSA5Ry2DWkqhzDpXCvPrRbOYt1FGbiJo/kxedBTJ60miJ7lnP6INHKWl26WLJVYAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23af99ad4568f9710fb9de5da1d7b4c8803aebd186c4dadc4d84bb430a5db2ba","last_reissued_at":"2026-05-18T02:44:47.480397Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:47.480397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Rosetta to Match-Up: A Paired Corpus of Linguistic Puzzles with Human and LLM Benchmarks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A conversion procedure turns Rosetta Stone puzzles into Match-Up versions that both expert humans and LLMs either solve completely or fail entirely.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anne Huang, Elena Filatova, Jinfan Frank Hu, Neh Majmudar","submitted_at":"2026-05-13T12:03:35Z","abstract_excerpt":"In this paper, we examine linguistic puzzles used in high school linguistics competitions, focusing on two common formats: Rosetta Stone and Match-Up. We propose a systematic procedure for converting existing Rosetta Stone puzzles into corresponding Match-Up counterparts. Because linguistic puzzle creation is complex and time-consuming, our method provides an efficient way to accelerate the generation of new puzzles. We evaluate the resulting Rosetta Stone-Match-Up pairs with both human participants and large language models (LLMs). Our results show that both expert human solvers and LLMs disp"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our results show that both expert human solvers and LLMs display an all-or-nothing pattern on Match-Up puzzles, either solving them completely or failing entirely.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that the proposed systematic conversion procedure produces Match-Up puzzles that preserve the original linguistic reasoning demands and difficulty level of the Rosetta Stone versions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A conversion method generates paired Rosetta Stone and Match-Up linguistic puzzles, with benchmarks revealing that both humans and LLMs either fully solve or completely fail the Match-Up puzzles.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A conversion procedure turns Rosetta Stone puzzles into Match-Up versions that both expert humans and LLMs either solve completely or fail entirely.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"c16c06fae2c4fe2687034615c5e295ee51dd43e53d0a5ba3f844a88572ba49f6"},"source":{"id":"2605.13408","kind":"arxiv","version":1},"verdict":{"id":"16bbc387-e6bc-4c20-9b0d-65907c4004dd","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:47:54.062872Z","strongest_claim":"Our results show that both expert human solvers and LLMs display an all-or-nothing pattern on Match-Up puzzles, either solving them completely or failing entirely.","one_line_summary":"A conversion method generates paired Rosetta Stone and Match-Up linguistic puzzles, with benchmarks revealing that both humans and LLMs either fully solve or completely fail the Match-Up puzzles.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that the proposed systematic conversion procedure produces Match-Up puzzles that preserve the original linguistic reasoning demands and difficulty level of the Rosetta Stone versions.","pith_extraction_headline":"A conversion procedure turns Rosetta Stone puzzles into Match-Up versions that both expert humans and LLMs either solve completely or fail entirely."},"references":{"count":13,"sample":[{"doi":"","year":2024,"title":"From Rosetta to Match-Up: A Paired Corpus of Linguistic Puzzles with Human and LLM Benchmarks","work_id":"7c1b8513-342a-4171-8771-e059f263a288","ref_index":1,"cited_arxiv_id":"2605.13408","is_internal_anchor":true},{"doi":"","year":null,"title":"They provide insight into what constitutes a well-designed linguistic puzzle","work_id":"31206413-cd71-40e7-bcd3-f8ad6a855e5d","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"They can inform and guide the development of future puzzle-generation procedures","work_id":"e8fbc1da-3e9e-4efa-8e1d-b4fe6a134bc0","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"They can support the analysis of LLMs’ chain- of-thought reasoning, helping to better under- stand differences in decision-making between humans and LLMs. The rest of the paper is organized as follows","work_id":"31eff160-dc74-40ee-9560-74ed827a9aff","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"experienced solvers are better prepared to handle these [Rosetta Stone puzzles] than problems of other types","work_id":"85d2241a-b6e6-4d73-8dda-ea61a0d4ab83","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":13,"snapshot_sha256":"2aaac4067b63a94973677f0284faea330106b505f57a2f31938fb9bad66cdc04","internal_anchors":2},"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":"2605.13408","created_at":"2026-05-18T02:44:47.480470+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.13408v1","created_at":"2026-05-18T02:44:47.480470+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13408","created_at":"2026-05-18T02:44:47.480470+00:00"},{"alias_kind":"pith_short_12","alias_value":"EOXZTLKFND4X","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"EOXZTLKFND4XCD5Z","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"EOXZTLKF","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.13408","citing_title":"From Rosetta to Match-Up: A Paired Corpus of Linguistic Puzzles with Human and LLM Benchmarks","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EOXZTLKFND4XCD5Z3ZO2DV5UZC","json":"https://pith.science/pith/EOXZTLKFND4XCD5Z3ZO2DV5UZC.json","graph_json":"https://pith.science/api/pith-number/EOXZTLKFND4XCD5Z3ZO2DV5UZC/graph.json","events_json":"https://pith.science/api/pith-number/EOXZTLKFND4XCD5Z3ZO2DV5UZC/events.json","paper":"https://pith.science/paper/EOXZTLKF"},"agent_actions":{"view_html":"https://pith.science/pith/EOXZTLKFND4XCD5Z3ZO2DV5UZC","download_json":"https://pith.science/pith/EOXZTLKFND4XCD5Z3ZO2DV5UZC.json","view_paper":"https://pith.science/paper/EOXZTLKF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.13408&json=true","fetch_graph":"https://pith.science/api/pith-number/EOXZTLKFND4XCD5Z3ZO2DV5UZC/graph.json","fetch_events":"https://pith.science/api/pith-number/EOXZTLKFND4XCD5Z3ZO2DV5UZC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EOXZTLKFND4XCD5Z3ZO2DV5UZC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EOXZTLKFND4XCD5Z3ZO2DV5UZC/action/storage_attestation","attest_author":"https://pith.science/pith/EOXZTLKFND4XCD5Z3ZO2DV5UZC/action/author_attestation","sign_citation":"https://pith.science/pith/EOXZTLKFND4XCD5Z3ZO2DV5UZC/action/citation_signature","submit_replication":"https://pith.science/pith/EOXZTLKFND4XCD5Z3ZO2DV5UZC/action/replication_record"}},"created_at":"2026-05-18T02:44:47.480470+00:00","updated_at":"2026-05-18T02:44:47.480470+00:00"}