{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TJGVCTLZTFHHH4URGEDKWZMNUB","short_pith_number":"pith:TJGVCTLZ","schema_version":"1.0","canonical_sha256":"9a4d514d79994e73f2913106ab658da068294e565eb9cd05b178948c0ffaa42e","source":{"kind":"arxiv","id":"2606.13020","version":1},"attestation_state":"computed","paper":{"title":"SciR: A Controllable Benchmark for Scientific Reasoning in LLMs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Andre Freitas, Marco Valentino, Pierre Beckmann","submitted_at":"2026-06-11T07:54:22Z","abstract_excerpt":"Three paradigmatic forms of inference recur across scientific reasoning: deduction, induction, and causal abduction. Reliably evaluating LLMs on these in scientific settings is currently out of reach: scientific benchmarks built on human annotations are costly and lack mechanistic ground truth, while synthetic logical-reasoning benchmarks do not resemble real scientific documents. We introduce SciR, a benchmark that combines multi-paradigm reasoning with controllable scientific rendering, anchored on three paradigmatic scientific problems. Tasks are generated from formal objects (deduction tre"},"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":"2606.13020","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-11T07:54:22Z","cross_cats_sorted":[],"title_canon_sha256":"1bc73f0b707abcef496dc6e95bb837ef86124de0eef83707d833be27afe8ecc8","abstract_canon_sha256":"81c5910645d6d48e8840c8ecbec5689d439df83f90c955c070f8d3e5be5030cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:09:37.272613Z","signature_b64":"XFXGYJAuDH47h7+lqdg2UsFaPehJEsLjWqJthkETj9TR8fBCyJBMFln6DaPv97+yKxT11fFGjqVzU3m8dNREDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a4d514d79994e73f2913106ab658da068294e565eb9cd05b178948c0ffaa42e","last_reissued_at":"2026-06-12T01:09:37.272208Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:09:37.272208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SciR: A Controllable Benchmark for Scientific Reasoning in LLMs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Andre Freitas, Marco Valentino, Pierre Beckmann","submitted_at":"2026-06-11T07:54:22Z","abstract_excerpt":"Three paradigmatic forms of inference recur across scientific reasoning: deduction, induction, and causal abduction. Reliably evaluating LLMs on these in scientific settings is currently out of reach: scientific benchmarks built on human annotations are costly and lack mechanistic ground truth, while synthetic logical-reasoning benchmarks do not resemble real scientific documents. We introduce SciR, a benchmark that combines multi-paradigm reasoning with controllable scientific rendering, anchored on three paradigmatic scientific problems. Tasks are generated from formal objects (deduction tre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13020","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/2606.13020/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":"2606.13020","created_at":"2026-06-12T01:09:37.272260+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.13020v1","created_at":"2026-06-12T01:09:37.272260+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13020","created_at":"2026-06-12T01:09:37.272260+00:00"},{"alias_kind":"pith_short_12","alias_value":"TJGVCTLZTFHH","created_at":"2026-06-12T01:09:37.272260+00:00"},{"alias_kind":"pith_short_16","alias_value":"TJGVCTLZTFHHH4UR","created_at":"2026-06-12T01:09:37.272260+00:00"},{"alias_kind":"pith_short_8","alias_value":"TJGVCTLZ","created_at":"2026-06-12T01:09:37.272260+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/TJGVCTLZTFHHH4URGEDKWZMNUB","json":"https://pith.science/pith/TJGVCTLZTFHHH4URGEDKWZMNUB.json","graph_json":"https://pith.science/api/pith-number/TJGVCTLZTFHHH4URGEDKWZMNUB/graph.json","events_json":"https://pith.science/api/pith-number/TJGVCTLZTFHHH4URGEDKWZMNUB/events.json","paper":"https://pith.science/paper/TJGVCTLZ"},"agent_actions":{"view_html":"https://pith.science/pith/TJGVCTLZTFHHH4URGEDKWZMNUB","download_json":"https://pith.science/pith/TJGVCTLZTFHHH4URGEDKWZMNUB.json","view_paper":"https://pith.science/paper/TJGVCTLZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.13020&json=true","fetch_graph":"https://pith.science/api/pith-number/TJGVCTLZTFHHH4URGEDKWZMNUB/graph.json","fetch_events":"https://pith.science/api/pith-number/TJGVCTLZTFHHH4URGEDKWZMNUB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TJGVCTLZTFHHH4URGEDKWZMNUB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TJGVCTLZTFHHH4URGEDKWZMNUB/action/storage_attestation","attest_author":"https://pith.science/pith/TJGVCTLZTFHHH4URGEDKWZMNUB/action/author_attestation","sign_citation":"https://pith.science/pith/TJGVCTLZTFHHH4URGEDKWZMNUB/action/citation_signature","submit_replication":"https://pith.science/pith/TJGVCTLZTFHHH4URGEDKWZMNUB/action/replication_record"}},"created_at":"2026-06-12T01:09:37.272260+00:00","updated_at":"2026-06-12T01:09:37.272260+00:00"}