{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3JFE4PHPYE3MZLVNJUBT2GOUFY","short_pith_number":"pith:3JFE4PHP","schema_version":"1.0","canonical_sha256":"da4a4e3cefc136ccaead4d033d19d42e295947dea5eeb00a1e0ab5c43f3e8040","source":{"kind":"arxiv","id":"2501.17785","version":1},"attestation_state":"computed","paper":{"title":"Reasoning Over the Glyphs: Evaluation of LLM's Decipherment of Rare Scripts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Shu-Kai Hsieh, Yu-Fei Shih, Zheng-Lin Lin","submitted_at":"2025-01-29T17:24:19Z","abstract_excerpt":"We explore the capabilities of LVLMs and LLMs in deciphering rare scripts not encoded in Unicode. We introduce a novel approach to construct a multimodal dataset of linguistic puzzles involving such scripts, utilizing a tokenization method for language glyphs. Our methods include the Picture Method for LVLMs and the Description Method for LLMs, enabling these models to tackle these challenges. We conduct experiments using prominent models, GPT-4o, Gemini, and Claude 3.5 Sonnet, on linguistic puzzles. Our findings reveal the strengths and limitations of current AI methods in linguistic decipher"},"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":"2501.17785","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-29T17:24:19Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fdb5680f432ee7942bac50b62da0beddb617c56e944956215a3d0c44e8c195fb","abstract_canon_sha256":"c8c110558439b7373a01284cffbb69bf6d63645989836cc9ac1527fc9865a496"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:57.791996Z","signature_b64":"6jDnUr6IUDJ3Aqx0U3PPOzMR2CjrywvfUqL2VxUNO24Uqfgww2S1bqV3kqtm20k8etkd9T/IbOv8DwE46O6qAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da4a4e3cefc136ccaead4d033d19d42e295947dea5eeb00a1e0ab5c43f3e8040","last_reissued_at":"2026-07-05T10:06:57.791586Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:57.791586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reasoning Over the Glyphs: Evaluation of LLM's Decipherment of Rare Scripts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Shu-Kai Hsieh, Yu-Fei Shih, Zheng-Lin Lin","submitted_at":"2025-01-29T17:24:19Z","abstract_excerpt":"We explore the capabilities of LVLMs and LLMs in deciphering rare scripts not encoded in Unicode. We introduce a novel approach to construct a multimodal dataset of linguistic puzzles involving such scripts, utilizing a tokenization method for language glyphs. Our methods include the Picture Method for LVLMs and the Description Method for LLMs, enabling these models to tackle these challenges. We conduct experiments using prominent models, GPT-4o, Gemini, and Claude 3.5 Sonnet, on linguistic puzzles. Our findings reveal the strengths and limitations of current AI methods in linguistic decipher"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.17785","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/2501.17785/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":"2501.17785","created_at":"2026-07-05T10:06:57.791642+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.17785v1","created_at":"2026-07-05T10:06:57.791642+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.17785","created_at":"2026-07-05T10:06:57.791642+00:00"},{"alias_kind":"pith_short_12","alias_value":"3JFE4PHPYE3M","created_at":"2026-07-05T10:06:57.791642+00:00"},{"alias_kind":"pith_short_16","alias_value":"3JFE4PHPYE3MZLVN","created_at":"2026-07-05T10:06:57.791642+00:00"},{"alias_kind":"pith_short_8","alias_value":"3JFE4PHP","created_at":"2026-07-05T10:06:57.791642+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01145","citing_title":"Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branches","ref_index":253,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01145","citing_title":"Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branches","ref_index":269,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3JFE4PHPYE3MZLVNJUBT2GOUFY","json":"https://pith.science/pith/3JFE4PHPYE3MZLVNJUBT2GOUFY.json","graph_json":"https://pith.science/api/pith-number/3JFE4PHPYE3MZLVNJUBT2GOUFY/graph.json","events_json":"https://pith.science/api/pith-number/3JFE4PHPYE3MZLVNJUBT2GOUFY/events.json","paper":"https://pith.science/paper/3JFE4PHP"},"agent_actions":{"view_html":"https://pith.science/pith/3JFE4PHPYE3MZLVNJUBT2GOUFY","download_json":"https://pith.science/pith/3JFE4PHPYE3MZLVNJUBT2GOUFY.json","view_paper":"https://pith.science/paper/3JFE4PHP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.17785&json=true","fetch_graph":"https://pith.science/api/pith-number/3JFE4PHPYE3MZLVNJUBT2GOUFY/graph.json","fetch_events":"https://pith.science/api/pith-number/3JFE4PHPYE3MZLVNJUBT2GOUFY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3JFE4PHPYE3MZLVNJUBT2GOUFY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3JFE4PHPYE3MZLVNJUBT2GOUFY/action/storage_attestation","attest_author":"https://pith.science/pith/3JFE4PHPYE3MZLVNJUBT2GOUFY/action/author_attestation","sign_citation":"https://pith.science/pith/3JFE4PHPYE3MZLVNJUBT2GOUFY/action/citation_signature","submit_replication":"https://pith.science/pith/3JFE4PHPYE3MZLVNJUBT2GOUFY/action/replication_record"}},"created_at":"2026-07-05T10:06:57.791642+00:00","updated_at":"2026-07-05T10:06:57.791642+00:00"}