{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:M747V2TGGBIY73EQVO224TMITZ","short_pith_number":"pith:M747V2TG","schema_version":"1.0","canonical_sha256":"67f9faea6630518fec90abb5ae4d889e79bf35788015ba3cd68a44da2ca9a48f","source":{"kind":"arxiv","id":"2606.25561","version":1},"attestation_state":"computed","paper":{"title":"CrypFormBench: Benchmarking Formal Analysis Capability of Large Language Models for Cryptographic Schemes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Bingzheng Wang, Haihui Fan, Hengyuan Liu, Hongbo Liu, Li Zhou, Qionglu Zhang, Rui Zhang, Xianhui Lu, Xiaoyan Gu, Zhaoxuan Li, Ziming Zhao","submitted_at":"2026-06-24T08:37:38Z","abstract_excerpt":"Manual formal analysis of cryptographic schemes is labor-intensive and requires substantial expertise. While model-checking tools (e.g., Scyther and Tamarin) and computational-security tools (e.g., CryptoVerif and EasyCrypt) improve the automation of security proofs, they still rely on experts to abstract schemes and write tool-specific formal descriptions. Large language models (LLMs) are a promising alternative, but their effectiveness in this domain remains unexplored due to the absence of standardized evaluation methodologies. To fill this gap, we introduce CrypFormBench (C.F.B for short),"},"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":"2606.25561","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-06-24T08:37:38Z","cross_cats_sorted":[],"title_canon_sha256":"a54e70fda777362fc8b86656225fe23b07eff5c99a2479602fe31eebff78f963","abstract_canon_sha256":"6a707a93cf648fbd22198f02e8f38590d4463e1f91bdbc02eae74b382de6ed90"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:18:08.846852Z","signature_b64":"YmUomHbozToZzdrNFAfe89CC1ytrL9axATKiXfdqB5/oCzUKw99KU1HVtdsKplkQuhtK98gDjLN8J1fUE3F2BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67f9faea6630518fec90abb5ae4d889e79bf35788015ba3cd68a44da2ca9a48f","last_reissued_at":"2026-06-25T01:18:08.846422Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:18:08.846422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CrypFormBench: Benchmarking Formal Analysis Capability of Large Language Models for Cryptographic Schemes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Bingzheng Wang, Haihui Fan, Hengyuan Liu, Hongbo Liu, Li Zhou, Qionglu Zhang, Rui Zhang, Xianhui Lu, Xiaoyan Gu, Zhaoxuan Li, Ziming Zhao","submitted_at":"2026-06-24T08:37:38Z","abstract_excerpt":"Manual formal analysis of cryptographic schemes is labor-intensive and requires substantial expertise. While model-checking tools (e.g., Scyther and Tamarin) and computational-security tools (e.g., CryptoVerif and EasyCrypt) improve the automation of security proofs, they still rely on experts to abstract schemes and write tool-specific formal descriptions. Large language models (LLMs) are a promising alternative, but their effectiveness in this domain remains unexplored due to the absence of standardized evaluation methodologies. To fill this gap, we introduce CrypFormBench (C.F.B for short),"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25561","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/2606.25561/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":"2606.25561","created_at":"2026-06-25T01:18:08.846478+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.25561v1","created_at":"2026-06-25T01:18:08.846478+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25561","created_at":"2026-06-25T01:18:08.846478+00:00"},{"alias_kind":"pith_short_12","alias_value":"M747V2TGGBIY","created_at":"2026-06-25T01:18:08.846478+00:00"},{"alias_kind":"pith_short_16","alias_value":"M747V2TGGBIY73EQ","created_at":"2026-06-25T01:18:08.846478+00:00"},{"alias_kind":"pith_short_8","alias_value":"M747V2TG","created_at":"2026-06-25T01:18:08.846478+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/M747V2TGGBIY73EQVO224TMITZ","json":"https://pith.science/pith/M747V2TGGBIY73EQVO224TMITZ.json","graph_json":"https://pith.science/api/pith-number/M747V2TGGBIY73EQVO224TMITZ/graph.json","events_json":"https://pith.science/api/pith-number/M747V2TGGBIY73EQVO224TMITZ/events.json","paper":"https://pith.science/paper/M747V2TG"},"agent_actions":{"view_html":"https://pith.science/pith/M747V2TGGBIY73EQVO224TMITZ","download_json":"https://pith.science/pith/M747V2TGGBIY73EQVO224TMITZ.json","view_paper":"https://pith.science/paper/M747V2TG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.25561&json=true","fetch_graph":"https://pith.science/api/pith-number/M747V2TGGBIY73EQVO224TMITZ/graph.json","fetch_events":"https://pith.science/api/pith-number/M747V2TGGBIY73EQVO224TMITZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M747V2TGGBIY73EQVO224TMITZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M747V2TGGBIY73EQVO224TMITZ/action/storage_attestation","attest_author":"https://pith.science/pith/M747V2TGGBIY73EQVO224TMITZ/action/author_attestation","sign_citation":"https://pith.science/pith/M747V2TGGBIY73EQVO224TMITZ/action/citation_signature","submit_replication":"https://pith.science/pith/M747V2TGGBIY73EQVO224TMITZ/action/replication_record"}},"created_at":"2026-06-25T01:18:08.846478+00:00","updated_at":"2026-06-25T01:18:08.846478+00:00"}