{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ERZNNMCP2EQJSOSDFOXBNGGHPH","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"22e265d326ba387a44975e48de68bcbafd5cb319d9b056b82bddc90e2543e541","cross_cats_sorted":["cs.AI","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-26T10:48:50Z","title_canon_sha256":"b96bfddc8b6cd1d92c6194d0c41d9d65c80585ab73d0802e1b39857c2ea33424"},"schema_version":"1.0","source":{"id":"2306.14583","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.14583","created_at":"2026-07-05T06:24:38Z"},{"alias_kind":"arxiv_version","alias_value":"2306.14583v1","created_at":"2026-07-05T06:24:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.14583","created_at":"2026-07-05T06:24:38Z"},{"alias_kind":"pith_short_12","alias_value":"ERZNNMCP2EQJ","created_at":"2026-07-05T06:24:38Z"},{"alias_kind":"pith_short_16","alias_value":"ERZNNMCP2EQJSOSD","created_at":"2026-07-05T06:24:38Z"},{"alias_kind":"pith_short_8","alias_value":"ERZNNMCP","created_at":"2026-07-05T06:24:38Z"}],"graph_snapshots":[{"event_id":"sha256:5ce2822269aaa817c42ed484652804a94bf88f27f99370b6b8543006006f02d3","target":"graph","created_at":"2026-07-05T06:24:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2306.14583/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Using large language models (LLMs) for source code has recently gained attention. LLMs, such as Transformer-based models like Codex and ChatGPT, have been shown to be highly capable of solving a wide range of programming problems. However, the extent to which LLMs understand problem descriptions and generate programs accordingly or just retrieve source code from the most relevant problem in training data based on superficial cues has not been discovered yet. To explore this research question, we conduct experiments to understand the robustness of several popular LLMs, CodeGen and GPT-3.5 serie","authors_text":"Atsushi Shirafuji, Jun Suzuki, Makoto Morishita, Takumi Ito, Yuki Nakamura, Yusuke Oda, Yutaka Watanobe","cross_cats":["cs.AI","cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-26T10:48:50Z","title":"Exploring the Robustness of Large Language Models for Solving Programming Problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.14583","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1b8da7aaa3b0a6f6244380cbd5dc3f278fe7662c0d59c93b919f835ef35ed827","target":"record","created_at":"2026-07-05T06:24:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"22e265d326ba387a44975e48de68bcbafd5cb319d9b056b82bddc90e2543e541","cross_cats_sorted":["cs.AI","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-26T10:48:50Z","title_canon_sha256":"b96bfddc8b6cd1d92c6194d0c41d9d65c80585ab73d0802e1b39857c2ea33424"},"schema_version":"1.0","source":{"id":"2306.14583","kind":"arxiv","version":1}},"canonical_sha256":"2472d6b04fd120993a432bae1698c779d5bbd88cb00322cad09583d25498b791","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2472d6b04fd120993a432bae1698c779d5bbd88cb00322cad09583d25498b791","first_computed_at":"2026-07-05T06:24:38.116993Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:24:38.116993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OtsjGY4gkAOBuBOgrua+hs1h8YbSlQbaXXR6TOPf/hfn6mcwxebbf+3pktPBqPv3TX8uc9fdyg05QQwJgxuFBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:24:38.117415Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.14583","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1b8da7aaa3b0a6f6244380cbd5dc3f278fe7662c0d59c93b919f835ef35ed827","sha256:5ce2822269aaa817c42ed484652804a94bf88f27f99370b6b8543006006f02d3"],"state_sha256":"84ebdabb1bcafce6646758a735d3d9e636600ec6ef7b1c54799bb9133e4cf1c0"}