{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GNZ535F6WIKSXLJQR36JSGVBQF","short_pith_number":"pith:GNZ535F6","schema_version":"1.0","canonical_sha256":"3373ddf4beb2152bad308efc991aa1817239825ea69f2904038d6bd57688d47c","source":{"kind":"arxiv","id":"2606.21008","version":1},"attestation_state":"computed","paper":{"title":"The Metanym Game: A Self-Contained, Self-Consistent LLM Peer-Community Benchmark for Structural Intelligence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"David Nordfors","submitted_at":"2026-06-19T00:43:29Z","abstract_excerpt":"The metanym game is a competitive word game for LLMs that measures structural intelligence against established cognitive-science constructs. No content is given in advance; the contestants create all of it -- a new kind of analogy test, analogical production falsifiable sentence by sentence, with no fixed test set to leak into training (contamination-resistant by construction). In the council-of-peers benchmark, the contestants also rate each other's creations. We introduce the first spectral solution, to our knowledge, to the wicked problem of benchmarking LLMs' factual accuracy without golde"},"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":"2606.21008","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-19T00:43:29Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1093cc08239de8ba5aca57f9a9f3825bb0c3ff57fd3db69c4f8ca141ff131b4a","abstract_canon_sha256":"e417a5d49547594b4132015653eeb59bb07f6891c02115ae6750f9e7282463b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:12:25.279255Z","signature_b64":"8tEavZu84YojCiRsEbu5O8xzkC81/SqQITBtw3vkZjrKiecDWYeR3zI/AVMRyazDh17AuwIOS66AJaJKtRk8Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3373ddf4beb2152bad308efc991aa1817239825ea69f2904038d6bd57688d47c","last_reissued_at":"2026-06-23T01:12:25.278788Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:12:25.278788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Metanym Game: A Self-Contained, Self-Consistent LLM Peer-Community Benchmark for Structural Intelligence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"David Nordfors","submitted_at":"2026-06-19T00:43:29Z","abstract_excerpt":"The metanym game is a competitive word game for LLMs that measures structural intelligence against established cognitive-science constructs. No content is given in advance; the contestants create all of it -- a new kind of analogy test, analogical production falsifiable sentence by sentence, with no fixed test set to leak into training (contamination-resistant by construction). In the council-of-peers benchmark, the contestants also rate each other's creations. We introduce the first spectral solution, to our knowledge, to the wicked problem of benchmarking LLMs' factual accuracy without golde"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21008","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/2606.21008/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":"2606.21008","created_at":"2026-06-23T01:12:25.278871+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.21008v1","created_at":"2026-06-23T01:12:25.278871+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21008","created_at":"2026-06-23T01:12:25.278871+00:00"},{"alias_kind":"pith_short_12","alias_value":"GNZ535F6WIKS","created_at":"2026-06-23T01:12:25.278871+00:00"},{"alias_kind":"pith_short_16","alias_value":"GNZ535F6WIKSXLJQ","created_at":"2026-06-23T01:12:25.278871+00:00"},{"alias_kind":"pith_short_8","alias_value":"GNZ535F6","created_at":"2026-06-23T01:12:25.278871+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GNZ535F6WIKSXLJQR36JSGVBQF","json":"https://pith.science/pith/GNZ535F6WIKSXLJQR36JSGVBQF.json","graph_json":"https://pith.science/api/pith-number/GNZ535F6WIKSXLJQR36JSGVBQF/graph.json","events_json":"https://pith.science/api/pith-number/GNZ535F6WIKSXLJQR36JSGVBQF/events.json","paper":"https://pith.science/paper/GNZ535F6"},"agent_actions":{"view_html":"https://pith.science/pith/GNZ535F6WIKSXLJQR36JSGVBQF","download_json":"https://pith.science/pith/GNZ535F6WIKSXLJQR36JSGVBQF.json","view_paper":"https://pith.science/paper/GNZ535F6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.21008&json=true","fetch_graph":"https://pith.science/api/pith-number/GNZ535F6WIKSXLJQR36JSGVBQF/graph.json","fetch_events":"https://pith.science/api/pith-number/GNZ535F6WIKSXLJQR36JSGVBQF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GNZ535F6WIKSXLJQR36JSGVBQF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GNZ535F6WIKSXLJQR36JSGVBQF/action/storage_attestation","attest_author":"https://pith.science/pith/GNZ535F6WIKSXLJQR36JSGVBQF/action/author_attestation","sign_citation":"https://pith.science/pith/GNZ535F6WIKSXLJQR36JSGVBQF/action/citation_signature","submit_replication":"https://pith.science/pith/GNZ535F6WIKSXLJQR36JSGVBQF/action/replication_record"}},"created_at":"2026-06-23T01:12:25.278871+00:00","updated_at":"2026-06-23T01:12:25.278871+00:00"}