{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:R6IEIHSTC7CW3CXDWYWQQSUS3C","short_pith_number":"pith:R6IEIHST","schema_version":"1.0","canonical_sha256":"8f90441e5317c56d8ae3b62d084a92d88fbe4063d37b0704dd295ef2955e330c","source":{"kind":"arxiv","id":"2606.30610","version":1},"attestation_state":"computed","paper":{"title":"PyMETA: A Benchmark Dataset for Hierarchical Student Code Error Classification with Python-Interpreter-Based Labels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Chuyue Li, Jingyi Wang, Kazuma Hashimoto, Lingyu Gao, Yu Wu, Ziqi Tang","submitted_at":"2026-06-29T17:45:36Z","abstract_excerpt":"With the advancement of Large Language Models (LLMs), code error detection has extended beyond traditional IDE diagnostics to context-sensitive debugging in educational scenarios. However, existing approaches lack large-scale datasets, multi-error analysis, and unified error taxonomies. To address this, we introduce PyMETA, a large-scale Python code error classification dataset of 48,646 student submissions, with single-error labels for all samples and a diagnostic subset of 97 expert-annotated multi-error samples. The dataset uses a three-level hierarchical taxonomy, from a binary error/no-er"},"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":"2606.30610","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-29T17:45:36Z","cross_cats_sorted":[],"title_canon_sha256":"209733249c2f997c1949d52528b964b37505b2cead85d4a1797808c17c4f6843","abstract_canon_sha256":"2c37a136e9967ef924138aa15a0336bc8f5c9925d8e55769c3c9e38d5dac6263"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:18:22.568225Z","signature_b64":"BLyH828ePgoY+MJXohJRQD6dNlIemVpnNYo5wsHHubafwIDnu/S/0O2kVD1dlhDlC0DO7aOk1mFcoqwgeaEzDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f90441e5317c56d8ae3b62d084a92d88fbe4063d37b0704dd295ef2955e330c","last_reissued_at":"2026-06-30T02:18:22.567769Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:18:22.567769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PyMETA: A Benchmark Dataset for Hierarchical Student Code Error Classification with Python-Interpreter-Based Labels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Chuyue Li, Jingyi Wang, Kazuma Hashimoto, Lingyu Gao, Yu Wu, Ziqi Tang","submitted_at":"2026-06-29T17:45:36Z","abstract_excerpt":"With the advancement of Large Language Models (LLMs), code error detection has extended beyond traditional IDE diagnostics to context-sensitive debugging in educational scenarios. However, existing approaches lack large-scale datasets, multi-error analysis, and unified error taxonomies. To address this, we introduce PyMETA, a large-scale Python code error classification dataset of 48,646 student submissions, with single-error labels for all samples and a diagnostic subset of 97 expert-annotated multi-error samples. The dataset uses a three-level hierarchical taxonomy, from a binary error/no-er"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30610","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/2606.30610/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":"2606.30610","created_at":"2026-06-30T02:18:22.567842+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.30610v1","created_at":"2026-06-30T02:18:22.567842+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30610","created_at":"2026-06-30T02:18:22.567842+00:00"},{"alias_kind":"pith_short_12","alias_value":"R6IEIHSTC7CW","created_at":"2026-06-30T02:18:22.567842+00:00"},{"alias_kind":"pith_short_16","alias_value":"R6IEIHSTC7CW3CXD","created_at":"2026-06-30T02:18:22.567842+00:00"},{"alias_kind":"pith_short_8","alias_value":"R6IEIHST","created_at":"2026-06-30T02:18:22.567842+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/R6IEIHSTC7CW3CXDWYWQQSUS3C","json":"https://pith.science/pith/R6IEIHSTC7CW3CXDWYWQQSUS3C.json","graph_json":"https://pith.science/api/pith-number/R6IEIHSTC7CW3CXDWYWQQSUS3C/graph.json","events_json":"https://pith.science/api/pith-number/R6IEIHSTC7CW3CXDWYWQQSUS3C/events.json","paper":"https://pith.science/paper/R6IEIHST"},"agent_actions":{"view_html":"https://pith.science/pith/R6IEIHSTC7CW3CXDWYWQQSUS3C","download_json":"https://pith.science/pith/R6IEIHSTC7CW3CXDWYWQQSUS3C.json","view_paper":"https://pith.science/paper/R6IEIHST","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.30610&json=true","fetch_graph":"https://pith.science/api/pith-number/R6IEIHSTC7CW3CXDWYWQQSUS3C/graph.json","fetch_events":"https://pith.science/api/pith-number/R6IEIHSTC7CW3CXDWYWQQSUS3C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R6IEIHSTC7CW3CXDWYWQQSUS3C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R6IEIHSTC7CW3CXDWYWQQSUS3C/action/storage_attestation","attest_author":"https://pith.science/pith/R6IEIHSTC7CW3CXDWYWQQSUS3C/action/author_attestation","sign_citation":"https://pith.science/pith/R6IEIHSTC7CW3CXDWYWQQSUS3C/action/citation_signature","submit_replication":"https://pith.science/pith/R6IEIHSTC7CW3CXDWYWQQSUS3C/action/replication_record"}},"created_at":"2026-06-30T02:18:22.567842+00:00","updated_at":"2026-06-30T02:18:22.567842+00:00"}