{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WAQ4UR5Z4MEA4K6XYFIVUXFWM4","short_pith_number":"pith:WAQ4UR5Z","schema_version":"1.0","canonical_sha256":"b021ca47b9e3080e2bd7c1515a5cb66709de07dc164c6bbe4776d7827718285e","source":{"kind":"arxiv","id":"2406.11930","version":1},"attestation_state":"computed","paper":{"title":"A Critical Study of What Code-LLMs (Do Not) Learn","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Abhinav Anand, Krishna Narasimhan, Mira Mezini, Shweta Verma","submitted_at":"2024-06-17T13:11:17Z","abstract_excerpt":"Large Language Models trained on code corpora (code-LLMs) have demonstrated impressive performance in various coding assistance tasks. However, despite their increased size and training dataset, code-LLMs still have limitations such as suggesting codes with syntactic errors, variable misuse etc. Some studies argue that code-LLMs perform well on coding tasks because they use self-attention and hidden representations to encode relations among input tokens. However, previous works have not studied what code properties are not encoded by code-LLMs. In this paper, we conduct a fine-grained analysis"},"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":"2406.11930","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-06-17T13:11:17Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"96799a14c533c04084810349d89c1657b150b9b232285d3f85b9196852a174ac","abstract_canon_sha256":"102d99a3d71eb570b0e4941098e77115b4ac28831d18fea9e92ebd4c224fd26a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:33:03.758856Z","signature_b64":"CYbezj8mYJv7TGoIaD6BNx8SzYYYomG8EFD3w5k61fvPrp3a7ZFY3k/QumCAi0ot7uwN0JQlnn5vITL22YyrCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b021ca47b9e3080e2bd7c1515a5cb66709de07dc164c6bbe4776d7827718285e","last_reissued_at":"2026-07-05T08:33:03.758251Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:33:03.758251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Critical Study of What Code-LLMs (Do Not) Learn","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Abhinav Anand, Krishna Narasimhan, Mira Mezini, Shweta Verma","submitted_at":"2024-06-17T13:11:17Z","abstract_excerpt":"Large Language Models trained on code corpora (code-LLMs) have demonstrated impressive performance in various coding assistance tasks. However, despite their increased size and training dataset, code-LLMs still have limitations such as suggesting codes with syntactic errors, variable misuse etc. Some studies argue that code-LLMs perform well on coding tasks because they use self-attention and hidden representations to encode relations among input tokens. However, previous works have not studied what code properties are not encoded by code-LLMs. In this paper, we conduct a fine-grained analysis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11930","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/2406.11930/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":"2406.11930","created_at":"2026-07-05T08:33:03.758325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.11930v1","created_at":"2026-07-05T08:33:03.758325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11930","created_at":"2026-07-05T08:33:03.758325+00:00"},{"alias_kind":"pith_short_12","alias_value":"WAQ4UR5Z4MEA","created_at":"2026-07-05T08:33:03.758325+00:00"},{"alias_kind":"pith_short_16","alias_value":"WAQ4UR5Z4MEA4K6X","created_at":"2026-07-05T08:33:03.758325+00:00"},{"alias_kind":"pith_short_8","alias_value":"WAQ4UR5Z","created_at":"2026-07-05T08:33:03.758325+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/WAQ4UR5Z4MEA4K6XYFIVUXFWM4","json":"https://pith.science/pith/WAQ4UR5Z4MEA4K6XYFIVUXFWM4.json","graph_json":"https://pith.science/api/pith-number/WAQ4UR5Z4MEA4K6XYFIVUXFWM4/graph.json","events_json":"https://pith.science/api/pith-number/WAQ4UR5Z4MEA4K6XYFIVUXFWM4/events.json","paper":"https://pith.science/paper/WAQ4UR5Z"},"agent_actions":{"view_html":"https://pith.science/pith/WAQ4UR5Z4MEA4K6XYFIVUXFWM4","download_json":"https://pith.science/pith/WAQ4UR5Z4MEA4K6XYFIVUXFWM4.json","view_paper":"https://pith.science/paper/WAQ4UR5Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.11930&json=true","fetch_graph":"https://pith.science/api/pith-number/WAQ4UR5Z4MEA4K6XYFIVUXFWM4/graph.json","fetch_events":"https://pith.science/api/pith-number/WAQ4UR5Z4MEA4K6XYFIVUXFWM4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WAQ4UR5Z4MEA4K6XYFIVUXFWM4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WAQ4UR5Z4MEA4K6XYFIVUXFWM4/action/storage_attestation","attest_author":"https://pith.science/pith/WAQ4UR5Z4MEA4K6XYFIVUXFWM4/action/author_attestation","sign_citation":"https://pith.science/pith/WAQ4UR5Z4MEA4K6XYFIVUXFWM4/action/citation_signature","submit_replication":"https://pith.science/pith/WAQ4UR5Z4MEA4K6XYFIVUXFWM4/action/replication_record"}},"created_at":"2026-07-05T08:33:03.758325+00:00","updated_at":"2026-07-05T08:33:03.758325+00:00"}