{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5OENQNRSVSFIYEV3NULZH3NCSL","short_pith_number":"pith:5OENQNRS","schema_version":"1.0","canonical_sha256":"eb88d83632ac8a8c12bb6d1793eda292efcbf6188154cf8b20485a3996b93c50","source":{"kind":"arxiv","id":"2606.29630","version":1},"attestation_state":"computed","paper":{"title":"SFBench: The SciFy Scientific Feasibility Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alex Memory, Cash Costello, Chris Ribaudo, Christina K. Pikas, Christine Piatko, Elsbeth Turcan, James Mayfield, Justin Rokisky, Ritwik Bose, Sam Scheck","submitted_at":"2026-06-28T22:27:26Z","abstract_excerpt":"We present SFBench, a benchmark dataset for evaluating systems that assess the feasibility of scientific claims. SFBench includes 197 claims in materials science, each annotated with a ground-truth feasibility score on a five-point scale along with an explanation of that assessment. The collection differs from previous collections in several important ways: 1) it defines a complex task that requires reasoning over claims of varying scientific feasibility; 2) its claims are not extracted from existing scientific publications but are created de novo, greatly reducing the chances that LLMs have t"},"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":"2606.29630","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-28T22:27:26Z","cross_cats_sorted":[],"title_canon_sha256":"f826139d39fdc2aab871002faf2877146a1a91e9e0a0deff8585b2ccf5e0eace","abstract_canon_sha256":"5f7c8b56bf1870bf80349d367dec8c958269523095c5fb434b0fed693cb31919"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:18:20.274981Z","signature_b64":"PbeeoRNCbu3DWZHZVeSbTk+stftiAI+iMQqgujDn2KFJxuUF1jcTzyBugmK+SVv8rfDYavsI6gL5/bZrCKWnBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb88d83632ac8a8c12bb6d1793eda292efcbf6188154cf8b20485a3996b93c50","last_reissued_at":"2026-06-30T01:18:20.274223Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:18:20.274223Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SFBench: The SciFy Scientific Feasibility Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alex Memory, Cash Costello, Chris Ribaudo, Christina K. Pikas, Christine Piatko, Elsbeth Turcan, James Mayfield, Justin Rokisky, Ritwik Bose, Sam Scheck","submitted_at":"2026-06-28T22:27:26Z","abstract_excerpt":"We present SFBench, a benchmark dataset for evaluating systems that assess the feasibility of scientific claims. SFBench includes 197 claims in materials science, each annotated with a ground-truth feasibility score on a five-point scale along with an explanation of that assessment. The collection differs from previous collections in several important ways: 1) it defines a complex task that requires reasoning over claims of varying scientific feasibility; 2) its claims are not extracted from existing scientific publications but are created de novo, greatly reducing the chances that LLMs have t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29630","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/2606.29630/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":"2606.29630","created_at":"2026-06-30T01:18:20.274351+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29630v1","created_at":"2026-06-30T01:18:20.274351+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29630","created_at":"2026-06-30T01:18:20.274351+00:00"},{"alias_kind":"pith_short_12","alias_value":"5OENQNRSVSFI","created_at":"2026-06-30T01:18:20.274351+00:00"},{"alias_kind":"pith_short_16","alias_value":"5OENQNRSVSFIYEV3","created_at":"2026-06-30T01:18:20.274351+00:00"},{"alias_kind":"pith_short_8","alias_value":"5OENQNRS","created_at":"2026-06-30T01:18:20.274351+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/5OENQNRSVSFIYEV3NULZH3NCSL","json":"https://pith.science/pith/5OENQNRSVSFIYEV3NULZH3NCSL.json","graph_json":"https://pith.science/api/pith-number/5OENQNRSVSFIYEV3NULZH3NCSL/graph.json","events_json":"https://pith.science/api/pith-number/5OENQNRSVSFIYEV3NULZH3NCSL/events.json","paper":"https://pith.science/paper/5OENQNRS"},"agent_actions":{"view_html":"https://pith.science/pith/5OENQNRSVSFIYEV3NULZH3NCSL","download_json":"https://pith.science/pith/5OENQNRSVSFIYEV3NULZH3NCSL.json","view_paper":"https://pith.science/paper/5OENQNRS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29630&json=true","fetch_graph":"https://pith.science/api/pith-number/5OENQNRSVSFIYEV3NULZH3NCSL/graph.json","fetch_events":"https://pith.science/api/pith-number/5OENQNRSVSFIYEV3NULZH3NCSL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5OENQNRSVSFIYEV3NULZH3NCSL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5OENQNRSVSFIYEV3NULZH3NCSL/action/storage_attestation","attest_author":"https://pith.science/pith/5OENQNRSVSFIYEV3NULZH3NCSL/action/author_attestation","sign_citation":"https://pith.science/pith/5OENQNRSVSFIYEV3NULZH3NCSL/action/citation_signature","submit_replication":"https://pith.science/pith/5OENQNRSVSFIYEV3NULZH3NCSL/action/replication_record"}},"created_at":"2026-06-30T01:18:20.274351+00:00","updated_at":"2026-06-30T01:18:20.274351+00:00"}