{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LZHPLYYRFXU4Z5AGSINQBBVA7Y","short_pith_number":"pith:LZHPLYYR","schema_version":"1.0","canonical_sha256":"5e4ef5e3112de9ccf406921b0086a0fe1a68c83ffae60475c92e328c47256cd1","source":{"kind":"arxiv","id":"2403.16437","version":3},"attestation_state":"computed","paper":{"title":"Reasoning Runtime Behavior of a Program with LLM: How Far Are We?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Ge Li, Junkai Chen, Xing Hu, Xin Xia, Zhenhao Li, Zhiyuan Pan","submitted_at":"2024-03-25T05:37:16Z","abstract_excerpt":"Large language models for code (i.e., code LLMs) have shown strong code understanding and generation capabilities. To evaluate the capabilities of code LLMs in various aspects, many benchmarks have been proposed (e.g., HumanEval and ClassEval). Code reasoning is one of the most essential abilities of code LLMs, but existing benchmarks for code reasoning are not sufficient. Typically, they focus on predicting the input and output of a program, ignoring the evaluation of the intermediate behavior during program execution, as well as the logical consistency (e.g., the model should not give the co"},"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":"2403.16437","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-03-25T05:37:16Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7b72ae99cfd20363cfbfd5801d4dcb97ed909ba8c61ea1b8f2d0e339c7961f92","abstract_canon_sha256":"750d2e8b51770e0fda022830c3cfb2dd889920c60d650dd137e782e22f46f773"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:57.640675Z","signature_b64":"HGIm+yEcf9vIZDrc/SDOzJNhcMwF/O1Ws8IjQKBocftGQwORBiRmXpRoPQ/P3UXLkmggywMJx4fnqht03LuLBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e4ef5e3112de9ccf406921b0086a0fe1a68c83ffae60475c92e328c47256cd1","last_reissued_at":"2026-07-05T09:09:57.640166Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:57.640166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reasoning Runtime Behavior of a Program with LLM: How Far Are We?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Ge Li, Junkai Chen, Xing Hu, Xin Xia, Zhenhao Li, Zhiyuan Pan","submitted_at":"2024-03-25T05:37:16Z","abstract_excerpt":"Large language models for code (i.e., code LLMs) have shown strong code understanding and generation capabilities. To evaluate the capabilities of code LLMs in various aspects, many benchmarks have been proposed (e.g., HumanEval and ClassEval). Code reasoning is one of the most essential abilities of code LLMs, but existing benchmarks for code reasoning are not sufficient. Typically, they focus on predicting the input and output of a program, ignoring the evaluation of the intermediate behavior during program execution, as well as the logical consistency (e.g., the model should not give the co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16437","kind":"arxiv","version":3},"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/2403.16437/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":"2403.16437","created_at":"2026-07-05T09:09:57.640221+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.16437v3","created_at":"2026-07-05T09:09:57.640221+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16437","created_at":"2026-07-05T09:09:57.640221+00:00"},{"alias_kind":"pith_short_12","alias_value":"LZHPLYYRFXU4","created_at":"2026-07-05T09:09:57.640221+00:00"},{"alias_kind":"pith_short_16","alias_value":"LZHPLYYRFXU4Z5AG","created_at":"2026-07-05T09:09:57.640221+00:00"},{"alias_kind":"pith_short_8","alias_value":"LZHPLYYR","created_at":"2026-07-05T09:09:57.640221+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17958","citing_title":"Enhancing the Code Reasoning Capabilities of LLMs via Consistency-based Reinforcement Learning","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2512.14917","citing_title":"Evaluating Code Reasoning Abilities of Large Language Models Under Real-World Settings","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15097","citing_title":"Veritas: Grounding LLM Agents for Reliable Vulnerability Reasoning over Stripped Binaries","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11922","citing_title":"StepCodeReasoner: Aligning Code Reasoning with Stepwise Execution Traces via Reinforcement Learning","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21765","citing_title":"PrismaDV: Automated Task-Aware Data Unit Test Generation","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LZHPLYYRFXU4Z5AGSINQBBVA7Y","json":"https://pith.science/pith/LZHPLYYRFXU4Z5AGSINQBBVA7Y.json","graph_json":"https://pith.science/api/pith-number/LZHPLYYRFXU4Z5AGSINQBBVA7Y/graph.json","events_json":"https://pith.science/api/pith-number/LZHPLYYRFXU4Z5AGSINQBBVA7Y/events.json","paper":"https://pith.science/paper/LZHPLYYR"},"agent_actions":{"view_html":"https://pith.science/pith/LZHPLYYRFXU4Z5AGSINQBBVA7Y","download_json":"https://pith.science/pith/LZHPLYYRFXU4Z5AGSINQBBVA7Y.json","view_paper":"https://pith.science/paper/LZHPLYYR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.16437&json=true","fetch_graph":"https://pith.science/api/pith-number/LZHPLYYRFXU4Z5AGSINQBBVA7Y/graph.json","fetch_events":"https://pith.science/api/pith-number/LZHPLYYRFXU4Z5AGSINQBBVA7Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LZHPLYYRFXU4Z5AGSINQBBVA7Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LZHPLYYRFXU4Z5AGSINQBBVA7Y/action/storage_attestation","attest_author":"https://pith.science/pith/LZHPLYYRFXU4Z5AGSINQBBVA7Y/action/author_attestation","sign_citation":"https://pith.science/pith/LZHPLYYRFXU4Z5AGSINQBBVA7Y/action/citation_signature","submit_replication":"https://pith.science/pith/LZHPLYYRFXU4Z5AGSINQBBVA7Y/action/replication_record"}},"created_at":"2026-07-05T09:09:57.640221+00:00","updated_at":"2026-07-05T09:09:57.640221+00:00"}