{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OUCQRLPHJAITI45IHJP4NIDWTN","short_pith_number":"pith:OUCQRLPH","schema_version":"1.0","canonical_sha256":"750508ade748113473a83a5fc6a0769b47fe6a54ff94afcb62b425915acd8bb9","source":{"kind":"arxiv","id":"2508.19200","version":3},"attestation_state":"computed","paper":{"title":"The Ramon Llull's Thinking Machine for Automated Ideation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Boyuan Zheng, Chenglei Si, Haofei Yu, Ken Liu, Runlong Zhou, Ruochen Li, Tong Chen, Tongshuang Wu, Xiang Li, Xinran Zhao, Yiming Zhang","submitted_at":"2025-08-26T17:03:43Z","abstract_excerpt":"This paper revisits Ramon Llull's Ars combinatoria - a medieval framework for generating knowledge through symbolic recombination - as a conceptual foundation for building a modern Llull's thinking machine for research ideation. Our approach defines three compositional axes: Theme (e.g., efficiency, adaptivity), Domain (e.g., question answering, machine translation), and Method (e.g., adversarial training, linear attention). These elements represent high-level abstractions common in scientific work - motivations, problem settings, and technical approaches - and serve as building blocks for LLM"},"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":"2508.19200","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-26T17:03:43Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"238214cb10a952db2c3906192aff22b631b5d46a4af576c1a4793db75d96eb45","abstract_canon_sha256":"3b0eb5442276eb8109ac3061ba0a4bea1419859b602e82127ea8b69d9a20f547"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:17.374788Z","signature_b64":"BxsQuRsSWrfsJmSOZT+SnWkcQrqaHB+Vfo8F5Igf9i0c7WiyiLZgfzlVyz6ZidnmpDgLOaUJn+ss3kWS8PRTBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"750508ade748113473a83a5fc6a0769b47fe6a54ff94afcb62b425915acd8bb9","last_reissued_at":"2026-07-05T12:04:17.374177Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:17.374177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Ramon Llull's Thinking Machine for Automated Ideation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Boyuan Zheng, Chenglei Si, Haofei Yu, Ken Liu, Runlong Zhou, Ruochen Li, Tong Chen, Tongshuang Wu, Xiang Li, Xinran Zhao, Yiming Zhang","submitted_at":"2025-08-26T17:03:43Z","abstract_excerpt":"This paper revisits Ramon Llull's Ars combinatoria - a medieval framework for generating knowledge through symbolic recombination - as a conceptual foundation for building a modern Llull's thinking machine for research ideation. Our approach defines three compositional axes: Theme (e.g., efficiency, adaptivity), Domain (e.g., question answering, machine translation), and Method (e.g., adversarial training, linear attention). These elements represent high-level abstractions common in scientific work - motivations, problem settings, and technical approaches - and serve as building blocks for LLM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.19200","kind":"arxiv","version":3},"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/2508.19200/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":"2508.19200","created_at":"2026-07-05T12:04:17.374254+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.19200v3","created_at":"2026-07-05T12:04:17.374254+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.19200","created_at":"2026-07-05T12:04:17.374254+00:00"},{"alias_kind":"pith_short_12","alias_value":"OUCQRLPHJAIT","created_at":"2026-07-05T12:04:17.374254+00:00"},{"alias_kind":"pith_short_16","alias_value":"OUCQRLPHJAITI45I","created_at":"2026-07-05T12:04:17.374254+00:00"},{"alias_kind":"pith_short_8","alias_value":"OUCQRLPH","created_at":"2026-07-05T12:04:17.374254+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.01092","citing_title":"The Alien Space of Science: Sampling Coherent but Cognitively Unavailable Research Directions","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09793","citing_title":"GIANTS: Generative Insight Anticipation from Scientific Literature","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OUCQRLPHJAITI45IHJP4NIDWTN","json":"https://pith.science/pith/OUCQRLPHJAITI45IHJP4NIDWTN.json","graph_json":"https://pith.science/api/pith-number/OUCQRLPHJAITI45IHJP4NIDWTN/graph.json","events_json":"https://pith.science/api/pith-number/OUCQRLPHJAITI45IHJP4NIDWTN/events.json","paper":"https://pith.science/paper/OUCQRLPH"},"agent_actions":{"view_html":"https://pith.science/pith/OUCQRLPHJAITI45IHJP4NIDWTN","download_json":"https://pith.science/pith/OUCQRLPHJAITI45IHJP4NIDWTN.json","view_paper":"https://pith.science/paper/OUCQRLPH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.19200&json=true","fetch_graph":"https://pith.science/api/pith-number/OUCQRLPHJAITI45IHJP4NIDWTN/graph.json","fetch_events":"https://pith.science/api/pith-number/OUCQRLPHJAITI45IHJP4NIDWTN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OUCQRLPHJAITI45IHJP4NIDWTN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OUCQRLPHJAITI45IHJP4NIDWTN/action/storage_attestation","attest_author":"https://pith.science/pith/OUCQRLPHJAITI45IHJP4NIDWTN/action/author_attestation","sign_citation":"https://pith.science/pith/OUCQRLPHJAITI45IHJP4NIDWTN/action/citation_signature","submit_replication":"https://pith.science/pith/OUCQRLPHJAITI45IHJP4NIDWTN/action/replication_record"}},"created_at":"2026-07-05T12:04:17.374254+00:00","updated_at":"2026-07-05T12:04:17.374254+00:00"}