{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:EOXZTLKFND4XCD5Z3ZO2DV5UZC","short_pith_number":"pith:EOXZTLKF","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"},"canonical_sha256":"23af99ad4568f9710fb9de5da1d7b4c8803aebd186c4dadc4d84bb430a5db2ba","source":{"kind":"arxiv","id":"2605.13408","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13408","created_at":"2026-05-18T02:44:47Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13408v1","created_at":"2026-05-18T02:44:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13408","created_at":"2026-05-18T02:44:47Z"},{"alias_kind":"pith_short_12","alias_value":"EOXZTLKFND4X","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"EOXZTLKFND4XCD5Z","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"EOXZTLKF","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:EOXZTLKFND4XCD5Z3ZO2DV5UZC","target":"record","payload":{"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"},"canonical_sha256":"23af99ad4568f9710fb9de5da1d7b4c8803aebd186c4dadc4d84bb430a5db2ba","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"},"source_kind":"arxiv","source_id":"2605.13408","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qf3Me4aY3OcRutx8IZXyn0x7bRrD6BO/eFWepL9PlkRx5swMg/69Pkp4v0IOr/GUj4dbdOrMWDjGsW9IH7frDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T09:16:48.721504Z"},"content_sha256":"e932e5fdab339b61a6c2912d2ee05cbaf776d87c982ed6bec1a2dc7c490c9c06","schema_version":"1.0","event_id":"sha256:e932e5fdab339b61a6c2912d2ee05cbaf776d87c982ed6bec1a2dc7c490c9c06"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:EOXZTLKFND4XCD5Z3ZO2DV5UZC","target":"graph","payload":{"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"},"verdict_id":"16bbc387-e6bc-4c20-9b0d-65907c4004dd"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a+BHhng/0OMH7dOazI6uu80EMUAAigs79+ZZrEM92PXL4spOXxbz31VKdrpuGbNKHsrDrcixTADuWiZ2KShxAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T09:16:48.722579Z"},"content_sha256":"eefad7bbbe67f8b0851353e8804874c9cff117dcdab22df1ee673f0b74e7fba0","schema_version":"1.0","event_id":"sha256:eefad7bbbe67f8b0851353e8804874c9cff117dcdab22df1ee673f0b74e7fba0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EOXZTLKFND4XCD5Z3ZO2DV5UZC/bundle.json","state_url":"https://pith.science/pith/EOXZTLKFND4XCD5Z3ZO2DV5UZC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EOXZTLKFND4XCD5Z3ZO2DV5UZC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-30T09:16:48Z","links":{"resolver":"https://pith.science/pith/EOXZTLKFND4XCD5Z3ZO2DV5UZC","bundle":"https://pith.science/pith/EOXZTLKFND4XCD5Z3ZO2DV5UZC/bundle.json","state":"https://pith.science/pith/EOXZTLKFND4XCD5Z3ZO2DV5UZC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EOXZTLKFND4XCD5Z3ZO2DV5UZC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EOXZTLKFND4XCD5Z3ZO2DV5UZC","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":"2adc96a7298c922e89e4484b313b5463db7ffca7eaac6d328f46f3db02fc521b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T12:03:35Z","title_canon_sha256":"164259911cf09cb2afcbaf9df6f0ca83ab153f454bbf879a2f30d38a592ef7d3"},"schema_version":"1.0","source":{"id":"2605.13408","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13408","created_at":"2026-05-18T02:44:47Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13408v1","created_at":"2026-05-18T02:44:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13408","created_at":"2026-05-18T02:44:47Z"},{"alias_kind":"pith_short_12","alias_value":"EOXZTLKFND4X","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"EOXZTLKFND4XCD5Z","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"EOXZTLKF","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:eefad7bbbe67f8b0851353e8804874c9cff117dcdab22df1ee673f0b74e7fba0","target":"graph","created_at":"2026-05-18T02:44:47Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A conversion procedure turns Rosetta Stone puzzles into Match-Up versions that both expert humans and LLMs either solve completely or fail entirely."}],"snapshot_sha256":"c16c06fae2c4fe2687034615c5e295ee51dd43e53d0a5ba3f844a88572ba49f6"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Anne Huang, Elena Filatova, Jinfan Frank Hu, Neh Majmudar","cross_cats":[],"headline":"A conversion procedure turns Rosetta Stone puzzles into Match-Up versions that both expert humans and LLMs either solve completely or fail entirely.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T12:03:35Z","title":"From Rosetta to Match-Up: A Paired Corpus of Linguistic Puzzles with Human and LLM Benchmarks"},"references":{"count":13,"internal_anchors":2,"resolved_work":13,"sample":[{"cited_arxiv_id":"2605.13408","doi":"","is_internal_anchor":true,"ref_index":1,"title":"From Rosetta to Match-Up: A Paired Corpus of Linguistic Puzzles with Human and LLM Benchmarks","work_id":"7c1b8513-342a-4171-8771-e059f263a288","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"They provide insight into what constitutes a well-designed linguistic puzzle","work_id":"31206413-cd71-40e7-bcd3-f8ad6a855e5d","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"They can inform and guide the development of future puzzle-generation procedures","work_id":"e8fbc1da-3e9e-4efa-8e1d-b4fe6a134bc0","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"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","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"experienced solvers are better prepared to handle these [Rosetta Stone puzzles] than problems of other types","work_id":"85d2241a-b6e6-4d73-8dda-ea61a0d4ab83","year":2024}],"snapshot_sha256":"2aaac4067b63a94973677f0284faea330106b505f57a2f31938fb9bad66cdc04"},"source":{"id":"2605.13408","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T19:47:54.062872Z","id":"16bbc387-e6bc-4c20-9b0d-65907c4004dd","model_set":{"reader":"grok-4.3"},"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","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.","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.","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."}},"verdict_id":"16bbc387-e6bc-4c20-9b0d-65907c4004dd"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e932e5fdab339b61a6c2912d2ee05cbaf776d87c982ed6bec1a2dc7c490c9c06","target":"record","created_at":"2026-05-18T02:44:47Z","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":"2adc96a7298c922e89e4484b313b5463db7ffca7eaac6d328f46f3db02fc521b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T12:03:35Z","title_canon_sha256":"164259911cf09cb2afcbaf9df6f0ca83ab153f454bbf879a2f30d38a592ef7d3"},"schema_version":"1.0","source":{"id":"2605.13408","kind":"arxiv","version":1}},"canonical_sha256":"23af99ad4568f9710fb9de5da1d7b4c8803aebd186c4dadc4d84bb430a5db2ba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23af99ad4568f9710fb9de5da1d7b4c8803aebd186c4dadc4d84bb430a5db2ba","first_computed_at":"2026-05-18T02:44:47.480397Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:47.480397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NU40hW7SVmtAmiOQNm36mDSA5Ry2DWkqhzDpXCvPrRbOYt1FGbiJo/kxedBTJ60miJ7lnP6INHKWl26WLJVYAg==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:47.480882Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13408","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e932e5fdab339b61a6c2912d2ee05cbaf776d87c982ed6bec1a2dc7c490c9c06","sha256:eefad7bbbe67f8b0851353e8804874c9cff117dcdab22df1ee673f0b74e7fba0"],"state_sha256":"21e322c618c905cbef26e525cc90c5ca73cac47b43cf03d0eddabbc71cb1d71d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fb3yMLmsiUuNysmcMCHH5Vprg5YkwJv3QfUKa+qVFuXTwfjby2CcNu98PkXBMEDX4H/Lbvn54b5ar9+alKFOBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T09:16:48.726765Z","bundle_sha256":"9996cbf66f01f867b8963ebbf4fbdb2bf078ee7e20915678d4b59aaaee5c9188"}}