{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XEUOOSZCYZJAH6V4JHGHAY2XLN","short_pith_number":"pith:XEUOOSZC","schema_version":"1.0","canonical_sha256":"b928e74b22c65203fabc49cc7063575b6dabd857f34f1e498dd136e5297a2380","source":{"kind":"arxiv","id":"2509.00425","version":1},"attestation_state":"computed","paper":{"title":"The Gold Medals in an Empty Room: Diagnosing Metalinguistic Reasoning in LLMs with Camlang","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fenghua Liu, Ming Zhong, Solomon Tsai, Yixuan Liu, Yulong Chen, Zhujun Jin","submitted_at":"2025-08-30T09:13:10Z","abstract_excerpt":"Large Language Models (LLMs) achieve gold-medal performance across many benchmarks, yet it remains unclear whether such success reflects genuine reasoning or pattern matching. From a cognitive science perspective, an informative test is whether models can master an unfamiliar language through explicit metalinguistic deductive learning, a paradigm where human learners can reliably internalise grammatical systems through metalinguistic reasoning. We address this question with Camlang, a novel constructed language that exhibits naturalistic yet unattested feature combinations. Camlang consists of"},"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":"2509.00425","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-30T09:13:10Z","cross_cats_sorted":[],"title_canon_sha256":"ed353492fb05f2b66cdd93f52dfda9aab723157e6177c14f60114b88cc1217bc","abstract_canon_sha256":"38493f97806ac3203be382686d146be803461c8f5523cc79f25fdcba5bcf5b0d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:16.041204Z","signature_b64":"aE7Wu4MzAmd59awTaewJGJG2T3ljxfXKW5xi/up9xLdCkmndRLAhDxkOC+jLjgw0+mH+QUUMCCAUs1PGUoasCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b928e74b22c65203fabc49cc7063575b6dabd857f34f1e498dd136e5297a2380","last_reissued_at":"2026-07-05T12:02:16.040693Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:16.040693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Gold Medals in an Empty Room: Diagnosing Metalinguistic Reasoning in LLMs with Camlang","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fenghua Liu, Ming Zhong, Solomon Tsai, Yixuan Liu, Yulong Chen, Zhujun Jin","submitted_at":"2025-08-30T09:13:10Z","abstract_excerpt":"Large Language Models (LLMs) achieve gold-medal performance across many benchmarks, yet it remains unclear whether such success reflects genuine reasoning or pattern matching. From a cognitive science perspective, an informative test is whether models can master an unfamiliar language through explicit metalinguistic deductive learning, a paradigm where human learners can reliably internalise grammatical systems through metalinguistic reasoning. We address this question with Camlang, a novel constructed language that exhibits naturalistic yet unattested feature combinations. Camlang consists of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00425","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/2509.00425/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":"2509.00425","created_at":"2026-07-05T12:02:16.040753+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.00425v1","created_at":"2026-07-05T12:02:16.040753+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00425","created_at":"2026-07-05T12:02:16.040753+00:00"},{"alias_kind":"pith_short_12","alias_value":"XEUOOSZCYZJA","created_at":"2026-07-05T12:02:16.040753+00:00"},{"alias_kind":"pith_short_16","alias_value":"XEUOOSZCYZJAH6V4","created_at":"2026-07-05T12:02:16.040753+00:00"},{"alias_kind":"pith_short_8","alias_value":"XEUOOSZC","created_at":"2026-07-05T12:02:16.040753+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.20811","citing_title":"Diagnosing CFG Interpretation in LLMs","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XEUOOSZCYZJAH6V4JHGHAY2XLN","json":"https://pith.science/pith/XEUOOSZCYZJAH6V4JHGHAY2XLN.json","graph_json":"https://pith.science/api/pith-number/XEUOOSZCYZJAH6V4JHGHAY2XLN/graph.json","events_json":"https://pith.science/api/pith-number/XEUOOSZCYZJAH6V4JHGHAY2XLN/events.json","paper":"https://pith.science/paper/XEUOOSZC"},"agent_actions":{"view_html":"https://pith.science/pith/XEUOOSZCYZJAH6V4JHGHAY2XLN","download_json":"https://pith.science/pith/XEUOOSZCYZJAH6V4JHGHAY2XLN.json","view_paper":"https://pith.science/paper/XEUOOSZC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.00425&json=true","fetch_graph":"https://pith.science/api/pith-number/XEUOOSZCYZJAH6V4JHGHAY2XLN/graph.json","fetch_events":"https://pith.science/api/pith-number/XEUOOSZCYZJAH6V4JHGHAY2XLN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XEUOOSZCYZJAH6V4JHGHAY2XLN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XEUOOSZCYZJAH6V4JHGHAY2XLN/action/storage_attestation","attest_author":"https://pith.science/pith/XEUOOSZCYZJAH6V4JHGHAY2XLN/action/author_attestation","sign_citation":"https://pith.science/pith/XEUOOSZCYZJAH6V4JHGHAY2XLN/action/citation_signature","submit_replication":"https://pith.science/pith/XEUOOSZCYZJAH6V4JHGHAY2XLN/action/replication_record"}},"created_at":"2026-07-05T12:02:16.040753+00:00","updated_at":"2026-07-05T12:02:16.040753+00:00"}