{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YMCFME4LPP2TNIERPIVYQXOYCQ","short_pith_number":"pith:YMCFME4L","schema_version":"1.0","canonical_sha256":"c30456138b7bf536a0917a2b885dd8143f789df4945e0dae2a8ce3c178bc1dd3","source":{"kind":"arxiv","id":"2505.17607","version":3},"attestation_state":"computed","paper":{"title":"Symbolic Intermediaries as a Linguistic-Numerical Interface for LLM-Driven Geometric Reasoning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Andr\\'e Freitas, Jo\\~ao Pedro Gandarela, Stefan Menzel, Thiago Rios","submitted_at":"2025-05-23T08:16:32Z","abstract_excerpt":"Large Language Models (LLMs) display reasoning capabilities over linguistic and symbolic objects but have limited capabilities to directly interpret the continuous numerical outputs of physics simulators, e.g., distances, curvatures, and trajectories that resist discrete tokenisation. Across spatially grounded engineering reasoning tasks, from mechanism design to motion planning, this defines a fundamental gap, which limits the wider application of LLMs within broader geometrical domains, for exmaple interfacing with physics simulators. We propose symbolic intermediaries, compact analytical ex"},"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":"2505.17607","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-23T08:16:32Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c5772a2600f0ac25d7144b3eb36129790f3c8600ba0886f15e51c3b60c10bb9f","abstract_canon_sha256":"3775799c8d2b907937f9ea852e1451d41ee6f21a8852150fbbb250fd720d181f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T02:03:24.032849Z","signature_b64":"JwkNQ09Uy9NB8d9/3C3vGwE4gkMlF8uhZBV1DEBjQczgFalgONqbijgXufJGtpzrEdPcdhxuPknh+HBTDVPhCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c30456138b7bf536a0917a2b885dd8143f789df4945e0dae2a8ce3c178bc1dd3","last_reissued_at":"2026-06-01T02:03:24.031654Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T02:03:24.031654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Symbolic Intermediaries as a Linguistic-Numerical Interface for LLM-Driven Geometric Reasoning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Andr\\'e Freitas, Jo\\~ao Pedro Gandarela, Stefan Menzel, Thiago Rios","submitted_at":"2025-05-23T08:16:32Z","abstract_excerpt":"Large Language Models (LLMs) display reasoning capabilities over linguistic and symbolic objects but have limited capabilities to directly interpret the continuous numerical outputs of physics simulators, e.g., distances, curvatures, and trajectories that resist discrete tokenisation. Across spatially grounded engineering reasoning tasks, from mechanism design to motion planning, this defines a fundamental gap, which limits the wider application of LLMs within broader geometrical domains, for exmaple interfacing with physics simulators. We propose symbolic intermediaries, compact analytical ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17607","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/2505.17607/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":"2505.17607","created_at":"2026-06-01T02:03:24.031919+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.17607v3","created_at":"2026-06-01T02:03:24.031919+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17607","created_at":"2026-06-01T02:03:24.031919+00:00"},{"alias_kind":"pith_short_12","alias_value":"YMCFME4LPP2T","created_at":"2026-06-01T02:03:24.031919+00:00"},{"alias_kind":"pith_short_16","alias_value":"YMCFME4LPP2TNIER","created_at":"2026-06-01T02:03:24.031919+00:00"},{"alias_kind":"pith_short_8","alias_value":"YMCFME4L","created_at":"2026-06-01T02:03:24.031919+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.27962","citing_title":"Language Models Refine Mechanical Linkage Designs Through Symbolic Reflection and Modular Optimisation","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YMCFME4LPP2TNIERPIVYQXOYCQ","json":"https://pith.science/pith/YMCFME4LPP2TNIERPIVYQXOYCQ.json","graph_json":"https://pith.science/api/pith-number/YMCFME4LPP2TNIERPIVYQXOYCQ/graph.json","events_json":"https://pith.science/api/pith-number/YMCFME4LPP2TNIERPIVYQXOYCQ/events.json","paper":"https://pith.science/paper/YMCFME4L"},"agent_actions":{"view_html":"https://pith.science/pith/YMCFME4LPP2TNIERPIVYQXOYCQ","download_json":"https://pith.science/pith/YMCFME4LPP2TNIERPIVYQXOYCQ.json","view_paper":"https://pith.science/paper/YMCFME4L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.17607&json=true","fetch_graph":"https://pith.science/api/pith-number/YMCFME4LPP2TNIERPIVYQXOYCQ/graph.json","fetch_events":"https://pith.science/api/pith-number/YMCFME4LPP2TNIERPIVYQXOYCQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YMCFME4LPP2TNIERPIVYQXOYCQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YMCFME4LPP2TNIERPIVYQXOYCQ/action/storage_attestation","attest_author":"https://pith.science/pith/YMCFME4LPP2TNIERPIVYQXOYCQ/action/author_attestation","sign_citation":"https://pith.science/pith/YMCFME4LPP2TNIERPIVYQXOYCQ/action/citation_signature","submit_replication":"https://pith.science/pith/YMCFME4LPP2TNIERPIVYQXOYCQ/action/replication_record"}},"created_at":"2026-06-01T02:03:24.031919+00:00","updated_at":"2026-06-01T02:03:24.031919+00:00"}