{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7TMAMBZ36TK6HLDKHJYPV3KCDC","short_pith_number":"pith:7TMAMBZ3","schema_version":"1.0","canonical_sha256":"fcd806073bf4d5e3ac6a3a70faed42188594effa7b7a7e4255fd39b18c6f65b6","source":{"kind":"arxiv","id":"2504.20115","version":2},"attestation_state":"computed","paper":{"title":"AutoP2C: An LLM-Based Agent Framework for Code Repository Generation from Multimodal Content in Academic Papers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"He Sun, Jinrui Zhou, Mingjun Xiao, Qilin Cai, Yiqing Shen, Zijie Lin","submitted_at":"2025-04-28T05:47:37Z","abstract_excerpt":"Machine Learning (ML) research is spread through academic papers featuring rich multimodal content, including text, diagrams, and tabular results. However, translating these multimodal elements into executable code remains a challenging and time-consuming process that requires substantial ML expertise. We introduce ``Paper-to-Code'' (P2C), a novel task that transforms the multimodal content of scientific publications into fully executable code repositories, which extends beyond the existing formulation of code generation that merely converts textual descriptions into isolated code snippets. To"},"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":"2504.20115","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-04-28T05:47:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f04f305d4ee98db61482cd79b59ab7c75252bc5627af8df7e32ef6167bed9274","abstract_canon_sha256":"75dbb5ddf816ee1f0eeaf4f2d1ada6d4eeabe3c9bad04d5702752628ad08b7c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:12.309010Z","signature_b64":"4mfeeDrQ80vEqkCSRODXpmYr3gzeOzAxoorjAM9eNUGeIDIVs/AlsLjGoGxhX4pujh0ioGIpQnZt3/XykblOBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcd806073bf4d5e3ac6a3a70faed42188594effa7b7a7e4255fd39b18c6f65b6","last_reissued_at":"2026-07-05T11:09:12.308490Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:12.308490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AutoP2C: An LLM-Based Agent Framework for Code Repository Generation from Multimodal Content in Academic Papers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"He Sun, Jinrui Zhou, Mingjun Xiao, Qilin Cai, Yiqing Shen, Zijie Lin","submitted_at":"2025-04-28T05:47:37Z","abstract_excerpt":"Machine Learning (ML) research is spread through academic papers featuring rich multimodal content, including text, diagrams, and tabular results. However, translating these multimodal elements into executable code remains a challenging and time-consuming process that requires substantial ML expertise. We introduce ``Paper-to-Code'' (P2C), a novel task that transforms the multimodal content of scientific publications into fully executable code repositories, which extends beyond the existing formulation of code generation that merely converts textual descriptions into isolated code snippets. To"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.20115","kind":"arxiv","version":2},"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/2504.20115/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":"2504.20115","created_at":"2026-07-05T11:09:12.308551+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.20115v2","created_at":"2026-07-05T11:09:12.308551+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.20115","created_at":"2026-07-05T11:09:12.308551+00:00"},{"alias_kind":"pith_short_12","alias_value":"7TMAMBZ36TK6","created_at":"2026-07-05T11:09:12.308551+00:00"},{"alias_kind":"pith_short_16","alias_value":"7TMAMBZ36TK6HLDK","created_at":"2026-07-05T11:09:12.308551+00:00"},{"alias_kind":"pith_short_8","alias_value":"7TMAMBZ3","created_at":"2026-07-05T11:09:12.308551+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07341","citing_title":"Empirical Evaluation of Large Language Models for Migration of Code Fragments to Post-Quantum Cryptography","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28371","citing_title":"From paper to benchmark: agentic, framework-based reproduction of under-specified methods in machine health intelligence","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17324","citing_title":"ASPI: Seeking Ambiguity Clarification Amplifies Prompt Injection Vulnerability in LLM Agents","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10813","citing_title":"NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10718","citing_title":"SciPredict: Can LLMs Predict the Outcomes of Scientific Experiments in Natural Sciences?","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7TMAMBZ36TK6HLDKHJYPV3KCDC","json":"https://pith.science/pith/7TMAMBZ36TK6HLDKHJYPV3KCDC.json","graph_json":"https://pith.science/api/pith-number/7TMAMBZ36TK6HLDKHJYPV3KCDC/graph.json","events_json":"https://pith.science/api/pith-number/7TMAMBZ36TK6HLDKHJYPV3KCDC/events.json","paper":"https://pith.science/paper/7TMAMBZ3"},"agent_actions":{"view_html":"https://pith.science/pith/7TMAMBZ36TK6HLDKHJYPV3KCDC","download_json":"https://pith.science/pith/7TMAMBZ36TK6HLDKHJYPV3KCDC.json","view_paper":"https://pith.science/paper/7TMAMBZ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.20115&json=true","fetch_graph":"https://pith.science/api/pith-number/7TMAMBZ36TK6HLDKHJYPV3KCDC/graph.json","fetch_events":"https://pith.science/api/pith-number/7TMAMBZ36TK6HLDKHJYPV3KCDC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7TMAMBZ36TK6HLDKHJYPV3KCDC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7TMAMBZ36TK6HLDKHJYPV3KCDC/action/storage_attestation","attest_author":"https://pith.science/pith/7TMAMBZ36TK6HLDKHJYPV3KCDC/action/author_attestation","sign_citation":"https://pith.science/pith/7TMAMBZ36TK6HLDKHJYPV3KCDC/action/citation_signature","submit_replication":"https://pith.science/pith/7TMAMBZ36TK6HLDKHJYPV3KCDC/action/replication_record"}},"created_at":"2026-07-05T11:09:12.308551+00:00","updated_at":"2026-07-05T11:09:12.308551+00:00"}