{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7W4APHUA6G6NENFY4ELYIJGIFQ","short_pith_number":"pith:7W4APHUA","schema_version":"1.0","canonical_sha256":"fdb8079e80f1bcd234b8e1178424c82c24790a3f216867a156f59d4cc4fcb9c1","source":{"kind":"arxiv","id":"2502.04184","version":4},"attestation_state":"computed","paper":{"title":"Are the Majority of Public Computational Notebooks Pathologically Non-Executable?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Muhammad Ali Gulzar, Tien Nguyen, Waris Gill","submitted_at":"2025-02-06T16:16:20Z","abstract_excerpt":"Computational notebooks are the de facto platforms for exploratory data science, offering an interactive programming environment where users can create, modify, and execute code cells in any sequence. However, this flexibility often introduces code quality issues, with prior studies showing that approximately 76% of public notebooks are non-executable, raising significant concerns about reusability. We argue that the traditional notion of executability - requiring a notebook to run fully and without error - is overly rigid, misclassifying many notebooks and overestimating their non-executabili"},"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":"2502.04184","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-06T16:16:20Z","cross_cats_sorted":[],"title_canon_sha256":"8d98cd0d7a3df6b7f2c8d1854990caf6b22e7874e249b57ef414d84019bcb8a6","abstract_canon_sha256":"a723b66b31bec2ea034667b44ae471a9c9cbd288e7b0ff259c4e14ae5afc7605"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:20.784491Z","signature_b64":"1KN90SMPpIILazvoWljeiSdEU1dnVrGxuzijl6rUlMo9SFVlN4XSJymZxsjqL07AI2c4ARktf95bnSTeHBuyCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdb8079e80f1bcd234b8e1178424c82c24790a3f216867a156f59d4cc4fcb9c1","last_reissued_at":"2026-07-05T12:01:20.783916Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:20.783916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are the Majority of Public Computational Notebooks Pathologically Non-Executable?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Muhammad Ali Gulzar, Tien Nguyen, Waris Gill","submitted_at":"2025-02-06T16:16:20Z","abstract_excerpt":"Computational notebooks are the de facto platforms for exploratory data science, offering an interactive programming environment where users can create, modify, and execute code cells in any sequence. However, this flexibility often introduces code quality issues, with prior studies showing that approximately 76% of public notebooks are non-executable, raising significant concerns about reusability. We argue that the traditional notion of executability - requiring a notebook to run fully and without error - is overly rigid, misclassifying many notebooks and overestimating their non-executabili"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04184","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/2502.04184/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":"2502.04184","created_at":"2026-07-05T12:01:20.783976+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.04184v4","created_at":"2026-07-05T12:01:20.783976+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04184","created_at":"2026-07-05T12:01:20.783976+00:00"},{"alias_kind":"pith_short_12","alias_value":"7W4APHUA6G6N","created_at":"2026-07-05T12:01:20.783976+00:00"},{"alias_kind":"pith_short_16","alias_value":"7W4APHUA6G6NENFY","created_at":"2026-07-05T12:01:20.783976+00:00"},{"alias_kind":"pith_short_8","alias_value":"7W4APHUA","created_at":"2026-07-05T12:01:20.783976+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.02233","citing_title":"A Methodological Framework for LLM-Based Mining of Software Repositories","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7W4APHUA6G6NENFY4ELYIJGIFQ","json":"https://pith.science/pith/7W4APHUA6G6NENFY4ELYIJGIFQ.json","graph_json":"https://pith.science/api/pith-number/7W4APHUA6G6NENFY4ELYIJGIFQ/graph.json","events_json":"https://pith.science/api/pith-number/7W4APHUA6G6NENFY4ELYIJGIFQ/events.json","paper":"https://pith.science/paper/7W4APHUA"},"agent_actions":{"view_html":"https://pith.science/pith/7W4APHUA6G6NENFY4ELYIJGIFQ","download_json":"https://pith.science/pith/7W4APHUA6G6NENFY4ELYIJGIFQ.json","view_paper":"https://pith.science/paper/7W4APHUA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.04184&json=true","fetch_graph":"https://pith.science/api/pith-number/7W4APHUA6G6NENFY4ELYIJGIFQ/graph.json","fetch_events":"https://pith.science/api/pith-number/7W4APHUA6G6NENFY4ELYIJGIFQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7W4APHUA6G6NENFY4ELYIJGIFQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7W4APHUA6G6NENFY4ELYIJGIFQ/action/storage_attestation","attest_author":"https://pith.science/pith/7W4APHUA6G6NENFY4ELYIJGIFQ/action/author_attestation","sign_citation":"https://pith.science/pith/7W4APHUA6G6NENFY4ELYIJGIFQ/action/citation_signature","submit_replication":"https://pith.science/pith/7W4APHUA6G6NENFY4ELYIJGIFQ/action/replication_record"}},"created_at":"2026-07-05T12:01:20.783976+00:00","updated_at":"2026-07-05T12:01:20.783976+00:00"}