{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6ESIYSBXP5ZYF5SYF6TT2TMYUT","short_pith_number":"pith:6ESIYSBX","schema_version":"1.0","canonical_sha256":"f1248c48377f7382f6582fa73d4d98a4ebe57a8728ff4789d655dfc71d6b63f4","source":{"kind":"arxiv","id":"2507.01903","version":2},"attestation_state":"computed","paper":{"title":"AI4Research: A Survey of Artificial Intelligence for Scientific Research","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dengyun Peng, Hanjing Li, Jiannan Guan, Jiaqi Wang, Jinhao Liu, Libo Qin, Mengkang Hu, Mingda Yang, Qiguang Chen, Wanxiang Che, Yihao Liang, Yimeng Zhang, Yiyan Ji, Yuhang Zhou, Zheng Yan, Zhi Chen","submitted_at":"2025-07-02T17:19:20Z","abstract_excerpt":"Recent advancements in artificial intelligence (AI), particularly in large language models (LLMs) such as OpenAI-o1 and DeepSeek-R1, have demonstrated remarkable capabilities in complex domains such as logical reasoning and experimental coding. Motivated by these advancements, numerous studies have explored the application of AI in the innovation process, particularly in the context of scientific research. These AI technologies primarily aim to develop systems that can autonomously conduct research processes across a wide range of scientific disciplines. Despite these significant strides, a 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":"2507.01903","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-02T17:19:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"101724be2da9d93bb417d494b0c399a1aaacc841c9fcea0db19c11e824c4a9d7","abstract_canon_sha256":"d0f8047785e4e9b15a7cf6eaf9a907c660d21909ca583a650d8e5632323971bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:51.099537Z","signature_b64":"ZX+Medkkbk+EdmmFw6jPKVCX4ARanZuG/70uVB4Lzq5JljKnz+z5wu2wkkmETkmpkDammd/ysdfoxjUt5MFZBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1248c48377f7382f6582fa73d4d98a4ebe57a8728ff4789d655dfc71d6b63f4","last_reissued_at":"2026-07-05T11:48:51.099050Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:51.099050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AI4Research: A Survey of Artificial Intelligence for Scientific Research","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dengyun Peng, Hanjing Li, Jiannan Guan, Jiaqi Wang, Jinhao Liu, Libo Qin, Mengkang Hu, Mingda Yang, Qiguang Chen, Wanxiang Che, Yihao Liang, Yimeng Zhang, Yiyan Ji, Yuhang Zhou, Zheng Yan, Zhi Chen","submitted_at":"2025-07-02T17:19:20Z","abstract_excerpt":"Recent advancements in artificial intelligence (AI), particularly in large language models (LLMs) such as OpenAI-o1 and DeepSeek-R1, have demonstrated remarkable capabilities in complex domains such as logical reasoning and experimental coding. Motivated by these advancements, numerous studies have explored the application of AI in the innovation process, particularly in the context of scientific research. These AI technologies primarily aim to develop systems that can autonomously conduct research processes across a wide range of scientific disciplines. Despite these significant strides, a co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01903","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/2507.01903/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":"2507.01903","created_at":"2026-07-05T11:48:51.099101+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.01903v2","created_at":"2026-07-05T11:48:51.099101+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01903","created_at":"2026-07-05T11:48:51.099101+00:00"},{"alias_kind":"pith_short_12","alias_value":"6ESIYSBXP5ZY","created_at":"2026-07-05T11:48:51.099101+00:00"},{"alias_kind":"pith_short_16","alias_value":"6ESIYSBXP5ZYF5SY","created_at":"2026-07-05T11:48:51.099101+00:00"},{"alias_kind":"pith_short_8","alias_value":"6ESIYSBX","created_at":"2026-07-05T11:48:51.099101+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":25,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23233","citing_title":"Judgment-Grounded Expansion for Peer Review Generation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22188","citing_title":"Bayesian Adaptation Gym: A Benchmark for the Bayesian Low-Rank Adaptation of Multi-Modal Language Models","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01013","citing_title":"Can AI Review Improve Paper Drafting? An Empirical Study on 20 Computer Architecture Submissions","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10246","citing_title":"SciIntegrity-Bench: A Benchmark for Evaluating Academic Integrity in AI Scientist Systems","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24198","citing_title":"Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24043","citing_title":"LLM-AutoSciLab: Closed-Loop Scientific Discovery via Active Experimentation with LLMs","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29981","citing_title":"Hephaestus: Toward a Cybersecurity AI Scientist","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22878","citing_title":"SciAtlas: A Large-Scale Knowledge Graph for Automated Scientific Research","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23204","citing_title":"AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16508","citing_title":"The Scaling Laws of Skills in LLM Agent Systems","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18661","citing_title":"AI for Auto-Research: Roadmap & User Guide","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2507.11810","citing_title":"Evolving Roles of LLMs in Scientific Innovation: Assistant, Collaborator, Scientist, and Evaluator","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2508.11548","citing_title":"Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2603.27771","citing_title":"Emergent Social Intelligence Risks in Generative Multi-Agent Systems","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2507.13334","citing_title":"A Survey of Context Engineering for Large Language Models","ref_index":152,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26645","citing_title":"SciHorizon-DataEVA: An Agentic System for AI-Readiness Evaluation of Heterogeneous Scientific Data","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2503.09567","citing_title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","ref_index":97,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10246","citing_title":"SciIntegrity-Bench: A Benchmark for Evaluating Academic Integrity in AI Scientist Systems","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23136","citing_title":"How Researchers Navigate Accountability, Transparency, and Trust When Using AI Tools in Early-Stage Research: A Think-Aloud Study","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20806","citing_title":"OMIBench: Benchmarking Olympiad-Level Multi-Image Reasoning in Large Vision-Language Model","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19606","citing_title":"AblateCell: A Reproduce-then-Ablate Agent for Virtual Cell Repositories","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16929","citing_title":"MeasHalu: Mitigation of Scientific Measurement Hallucinations for Large Language Models with Enhanced Reasoning","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27351","citing_title":"Heterogeneous Scientific Foundation Model Collaboration","ref_index":109,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24198","citing_title":"Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23593","citing_title":"When AI reviews science: Can we trust the referee?","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6ESIYSBXP5ZYF5SYF6TT2TMYUT","json":"https://pith.science/pith/6ESIYSBXP5ZYF5SYF6TT2TMYUT.json","graph_json":"https://pith.science/api/pith-number/6ESIYSBXP5ZYF5SYF6TT2TMYUT/graph.json","events_json":"https://pith.science/api/pith-number/6ESIYSBXP5ZYF5SYF6TT2TMYUT/events.json","paper":"https://pith.science/paper/6ESIYSBX"},"agent_actions":{"view_html":"https://pith.science/pith/6ESIYSBXP5ZYF5SYF6TT2TMYUT","download_json":"https://pith.science/pith/6ESIYSBXP5ZYF5SYF6TT2TMYUT.json","view_paper":"https://pith.science/paper/6ESIYSBX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.01903&json=true","fetch_graph":"https://pith.science/api/pith-number/6ESIYSBXP5ZYF5SYF6TT2TMYUT/graph.json","fetch_events":"https://pith.science/api/pith-number/6ESIYSBXP5ZYF5SYF6TT2TMYUT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6ESIYSBXP5ZYF5SYF6TT2TMYUT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6ESIYSBXP5ZYF5SYF6TT2TMYUT/action/storage_attestation","attest_author":"https://pith.science/pith/6ESIYSBXP5ZYF5SYF6TT2TMYUT/action/author_attestation","sign_citation":"https://pith.science/pith/6ESIYSBXP5ZYF5SYF6TT2TMYUT/action/citation_signature","submit_replication":"https://pith.science/pith/6ESIYSBXP5ZYF5SYF6TT2TMYUT/action/replication_record"}},"created_at":"2026-07-05T11:48:51.099101+00:00","updated_at":"2026-07-05T11:48:51.099101+00:00"}