{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:M422PF53DA7V7O2JVMVDPUJQII","short_pith_number":"pith:M422PF53","schema_version":"1.0","canonical_sha256":"6735a797bb183f5fbb49ab2a37d13042336ef31d3367b78436f4f2cf98acd210","source":{"kind":"arxiv","id":"2506.22370","version":4},"attestation_state":"computed","paper":{"title":"Can Large Language Models Help Students Prove Software Correctness? An Experimental Study with Dafny","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PL"],"primary_cat":"cs.SE","authors_text":"Alexandra Mendes, Alexandre Abreu, \\'Alvaro Silva, Carolina Carreira","submitted_at":"2025-06-27T16:34:13Z","abstract_excerpt":"Students in computing education increasingly use large language models (LLMs) such as ChatGPT. Yet, the role of LLMs in supporting cognitively demanding tasks, like deductive program verification, remains poorly understood. This paper investigates how students interact with an LLM when solving formal verification exercises in Dafny, a language that supports functional correctness, by allowing programmers to write formal specifications and automatically verifying that the implementation satisfies the specification. We conducted a mixed-methods study with master's students enrolled in a formal m"},"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":"2506.22370","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-06-27T16:34:13Z","cross_cats_sorted":["cs.PL"],"title_canon_sha256":"a902e27a2768ef45c1db416e72738a1ce3576787a8004c62beb7899686b95dd0","abstract_canon_sha256":"4028c7b62ecbbd4c173d55cf2a401b4d509ac4548ff5f79d7ee044842c2e6410"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:15.721943Z","signature_b64":"G8U727n8kVlClPZ0taHVEgPYxUihlOaUqfRQ9eVbg+Jz4W0RaUH9Jnx/otPjU/0TtVv/iy7lwtPjE3Q8I7YrCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6735a797bb183f5fbb49ab2a37d13042336ef31d3367b78436f4f2cf98acd210","last_reissued_at":"2026-07-05T12:06:15.721325Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:15.721325Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Large Language Models Help Students Prove Software Correctness? An Experimental Study with Dafny","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PL"],"primary_cat":"cs.SE","authors_text":"Alexandra Mendes, Alexandre Abreu, \\'Alvaro Silva, Carolina Carreira","submitted_at":"2025-06-27T16:34:13Z","abstract_excerpt":"Students in computing education increasingly use large language models (LLMs) such as ChatGPT. Yet, the role of LLMs in supporting cognitively demanding tasks, like deductive program verification, remains poorly understood. This paper investigates how students interact with an LLM when solving formal verification exercises in Dafny, a language that supports functional correctness, by allowing programmers to write formal specifications and automatically verifying that the implementation satisfies the specification. We conducted a mixed-methods study with master's students enrolled in a formal m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22370","kind":"arxiv","version":4},"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/2506.22370/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":"2506.22370","created_at":"2026-07-05T12:06:15.721400+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.22370v4","created_at":"2026-07-05T12:06:15.721400+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22370","created_at":"2026-07-05T12:06:15.721400+00:00"},{"alias_kind":"pith_short_12","alias_value":"M422PF53DA7V","created_at":"2026-07-05T12:06:15.721400+00:00"},{"alias_kind":"pith_short_16","alias_value":"M422PF53DA7V7O2J","created_at":"2026-07-05T12:06:15.721400+00:00"},{"alias_kind":"pith_short_8","alias_value":"M422PF53","created_at":"2026-07-05T12:06:15.721400+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/M422PF53DA7V7O2JVMVDPUJQII","json":"https://pith.science/pith/M422PF53DA7V7O2JVMVDPUJQII.json","graph_json":"https://pith.science/api/pith-number/M422PF53DA7V7O2JVMVDPUJQII/graph.json","events_json":"https://pith.science/api/pith-number/M422PF53DA7V7O2JVMVDPUJQII/events.json","paper":"https://pith.science/paper/M422PF53"},"agent_actions":{"view_html":"https://pith.science/pith/M422PF53DA7V7O2JVMVDPUJQII","download_json":"https://pith.science/pith/M422PF53DA7V7O2JVMVDPUJQII.json","view_paper":"https://pith.science/paper/M422PF53","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.22370&json=true","fetch_graph":"https://pith.science/api/pith-number/M422PF53DA7V7O2JVMVDPUJQII/graph.json","fetch_events":"https://pith.science/api/pith-number/M422PF53DA7V7O2JVMVDPUJQII/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M422PF53DA7V7O2JVMVDPUJQII/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M422PF53DA7V7O2JVMVDPUJQII/action/storage_attestation","attest_author":"https://pith.science/pith/M422PF53DA7V7O2JVMVDPUJQII/action/author_attestation","sign_citation":"https://pith.science/pith/M422PF53DA7V7O2JVMVDPUJQII/action/citation_signature","submit_replication":"https://pith.science/pith/M422PF53DA7V7O2JVMVDPUJQII/action/replication_record"}},"created_at":"2026-07-05T12:06:15.721400+00:00","updated_at":"2026-07-05T12:06:15.721400+00:00"}