{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:J3LEBOOLD6MKTIK2HKJZXEO7WY","short_pith_number":"pith:J3LEBOOL","schema_version":"1.0","canonical_sha256":"4ed640b9cb1f98a9a15a3a939b91dfb60c15faf8e0deceee4b6037661adc5157","source":{"kind":"arxiv","id":"2312.16882","version":2},"attestation_state":"computed","paper":{"title":"TypeEvalPy: A Micro-benchmarking Framework for Python Type Inference Tools","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Amir M. Mir, Ashwin Prasad Shivarpatna Venkatesh, Eric Bodden, Jiawei Wang, Li Li, Samkutty Sabu","submitted_at":"2023-12-28T08:13:27Z","abstract_excerpt":"In light of the growing interest in type inference research for Python, both researchers and practitioners require a standardized process to assess the performance of various type inference techniques. This paper introduces TypeEvalPy, a comprehensive micro-benchmarking framework for evaluating type inference tools. TypeEvalPy contains 154 code snippets with 845 type annotations across 18 categories that target various Python features. The framework manages the execution of containerized tools, transforms inferred types into a standardized format, and produces meaningful metrics for assessment"},"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":"2312.16882","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-12-28T08:13:27Z","cross_cats_sorted":[],"title_canon_sha256":"62b15ffc22c8a84e3709f5c2d33467bbe129dc1b794e6c1ecb50b5a0bcb7dbe7","abstract_canon_sha256":"f149320137ba311363a831a1d47ddeee2b9ccb5810e8c9eb37f3e5b5da9a6ae8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:29:30.296734Z","signature_b64":"fo0tjpqi86sFDIUy50pmuzYUXrTinSBupfeFTewyA8JyX1T+bjOL4lzIhgwihKEIE33MYwfZLo4RSwGZztMhDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ed640b9cb1f98a9a15a3a939b91dfb60c15faf8e0deceee4b6037661adc5157","last_reissued_at":"2026-07-05T07:29:30.296305Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:29:30.296305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TypeEvalPy: A Micro-benchmarking Framework for Python Type Inference Tools","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Amir M. Mir, Ashwin Prasad Shivarpatna Venkatesh, Eric Bodden, Jiawei Wang, Li Li, Samkutty Sabu","submitted_at":"2023-12-28T08:13:27Z","abstract_excerpt":"In light of the growing interest in type inference research for Python, both researchers and practitioners require a standardized process to assess the performance of various type inference techniques. This paper introduces TypeEvalPy, a comprehensive micro-benchmarking framework for evaluating type inference tools. TypeEvalPy contains 154 code snippets with 845 type annotations across 18 categories that target various Python features. The framework manages the execution of containerized tools, transforms inferred types into a standardized format, and produces meaningful metrics for assessment"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.16882","kind":"arxiv","version":2},"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/2312.16882/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":"2312.16882","created_at":"2026-07-05T07:29:30.296373+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.16882v2","created_at":"2026-07-05T07:29:30.296373+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.16882","created_at":"2026-07-05T07:29:30.296373+00:00"},{"alias_kind":"pith_short_12","alias_value":"J3LEBOOLD6MK","created_at":"2026-07-05T07:29:30.296373+00:00"},{"alias_kind":"pith_short_16","alias_value":"J3LEBOOLD6MKTIK2","created_at":"2026-07-05T07:29:30.296373+00:00"},{"alias_kind":"pith_short_8","alias_value":"J3LEBOOL","created_at":"2026-07-05T07:29:30.296373+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.01477","citing_title":"Combining Type Inference and Automated Unit Test Generation for Python","ref_index":58,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J3LEBOOLD6MKTIK2HKJZXEO7WY","json":"https://pith.science/pith/J3LEBOOLD6MKTIK2HKJZXEO7WY.json","graph_json":"https://pith.science/api/pith-number/J3LEBOOLD6MKTIK2HKJZXEO7WY/graph.json","events_json":"https://pith.science/api/pith-number/J3LEBOOLD6MKTIK2HKJZXEO7WY/events.json","paper":"https://pith.science/paper/J3LEBOOL"},"agent_actions":{"view_html":"https://pith.science/pith/J3LEBOOLD6MKTIK2HKJZXEO7WY","download_json":"https://pith.science/pith/J3LEBOOLD6MKTIK2HKJZXEO7WY.json","view_paper":"https://pith.science/paper/J3LEBOOL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.16882&json=true","fetch_graph":"https://pith.science/api/pith-number/J3LEBOOLD6MKTIK2HKJZXEO7WY/graph.json","fetch_events":"https://pith.science/api/pith-number/J3LEBOOLD6MKTIK2HKJZXEO7WY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J3LEBOOLD6MKTIK2HKJZXEO7WY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J3LEBOOLD6MKTIK2HKJZXEO7WY/action/storage_attestation","attest_author":"https://pith.science/pith/J3LEBOOLD6MKTIK2HKJZXEO7WY/action/author_attestation","sign_citation":"https://pith.science/pith/J3LEBOOLD6MKTIK2HKJZXEO7WY/action/citation_signature","submit_replication":"https://pith.science/pith/J3LEBOOLD6MKTIK2HKJZXEO7WY/action/replication_record"}},"created_at":"2026-07-05T07:29:30.296373+00:00","updated_at":"2026-07-05T07:29:30.296373+00:00"}