{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AY3GNTZHRTT6QRBDHRHQG63OC6","short_pith_number":"pith:AY3GNTZH","schema_version":"1.0","canonical_sha256":"063666cf278ce7e844233c4f037b6e1794c6003ea7c4d18fb9f07a479a772b55","source":{"kind":"arxiv","id":"2603.04448","version":2},"attestation_state":"computed","paper":{"title":"SkillNet: Create, Evaluate, and Connect AI Skills","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Changliang Xu, Chen Jiang, Chenxi Wang, Chiyu Wu, Fei Huang, Feiyu Xiong, Gang Yu, Guilin Qi, Haiwen Hong, Hangcheng Zhu, Haofen Wang, Haoming Xu, Hongjie Deng, Huajun Chen, Hui Xue, Jeff Z. Pan, Jia-Chen Gu, Jin Shang, Jungang Lou, Junyu Lin, Jun Zhou, Keyan Ding, Kun Wang, Lei Liang, Longtao Huang, Mengru Wang, Ningyu Zhang, Peng Zhang, Qiang Zhang, Runnan Fang, Ruobin Zhong, Shumin Deng, Shuofei Qiao, Tongtong Wu, Wen Zhang, Xi Chen, Xin Xie, Xin Xu, Yang Liu, Yida Xue, Yijun Wang, Yi Zhong, Yuan Liang, Yuchen Eleanor Jiang, Yu Gong, Yunzhi Yao, Zhaopeng Tu, Zhen Bi, Zhengke Gui, Zifei Shan","submitted_at":"2026-02-26T14:24:02Z","abstract_excerpt":"Current AI agents can flexibly invoke tools and execute complex tasks, yet their long-term advancement is hindered by the lack of systematic accumulation and transfer of skills. Without a unified mechanism for skill consolidation, agents frequently ``reinvent the wheel'', rediscovering solutions in isolated contexts without leveraging prior strategies. To address this challenge, we introduce SkillNet, an open infrastructure for creating, evaluating, and organizing AI skills at scale. SkillNet structures skills within a unified ontology that supports creating skills from heterogeneous sources, "},"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":"2603.04448","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-26T14:24:02Z","cross_cats_sorted":["cs.CL","cs.CV","cs.LG","cs.MA"],"title_canon_sha256":"606dc61d66418537b042706c73747979515485e4046116111a0bb956c8e1485d","abstract_canon_sha256":"b01688ad571428bd387929f4f526a90cefab435a3cc320d10504ff4abc40ca2a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-20T01:24:55.242814Z","signature_b64":"tVTDW9ucmHULyPTeCY9Ux5rDGXENzoftAosKp3qkIHebuqYdEW9B6rchPUq7pT44XrfB75SF86nDo/JW1EnuCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"063666cf278ce7e844233c4f037b6e1794c6003ea7c4d18fb9f07a479a772b55","last_reissued_at":"2026-08-20T01:24:55.240978Z","signature_status":"signed_v1","first_computed_at":"2026-08-20T01:24:55.240978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SkillNet: Create, Evaluate, and Connect AI Skills","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Changliang Xu, Chen Jiang, Chenxi Wang, Chiyu Wu, Fei Huang, Feiyu Xiong, Gang Yu, Guilin Qi, Haiwen Hong, Hangcheng Zhu, Haofen Wang, Haoming Xu, Hongjie Deng, Huajun Chen, Hui Xue, Jeff Z. Pan, Jia-Chen Gu, Jin Shang, Jungang Lou, Junyu Lin, Jun Zhou, Keyan Ding, Kun Wang, Lei Liang, Longtao Huang, Mengru Wang, Ningyu Zhang, Peng Zhang, Qiang Zhang, Runnan Fang, Ruobin Zhong, Shumin Deng, Shuofei Qiao, Tongtong Wu, Wen Zhang, Xi Chen, Xin Xie, Xin Xu, Yang Liu, Yida Xue, Yijun Wang, Yi Zhong, Yuan Liang, Yuchen Eleanor Jiang, Yu Gong, Yunzhi Yao, Zhaopeng Tu, Zhen Bi, Zhengke Gui, Zifei Shan","submitted_at":"2026-02-26T14:24:02Z","abstract_excerpt":"Current AI agents can flexibly invoke tools and execute complex tasks, yet their long-term advancement is hindered by the lack of systematic accumulation and transfer of skills. Without a unified mechanism for skill consolidation, agents frequently ``reinvent the wheel'', rediscovering solutions in isolated contexts without leveraging prior strategies. To address this challenge, we introduce SkillNet, an open infrastructure for creating, evaluating, and organizing AI skills at scale. SkillNet structures skills within a unified ontology that supports creating skills from heterogeneous sources, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.04448","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/2603.04448/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":"2603.04448","created_at":"2026-08-20T01:24:55.240642+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.04448v2","created_at":"2026-08-20T01:24:55.240642+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.04448","created_at":"2026-08-20T01:24:55.240642+00:00"},{"alias_kind":"pith_short_12","alias_value":"AY3GNTZHRTT6","created_at":"2026-08-20T01:24:55.240642+00:00"},{"alias_kind":"pith_short_16","alias_value":"AY3GNTZHRTT6QRBD","created_at":"2026-08-20T01:24:55.240642+00:00"},{"alias_kind":"pith_short_8","alias_value":"AY3GNTZH","created_at":"2026-08-20T01:24:55.240642+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":35,"internal_anchor_count":35,"sample":[{"citing_arxiv_id":"2607.06283","citing_title":"Task Decomposition-Guided Reranking for Adaptive Agent Skill Retrieval","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2606.10546","citing_title":"SkillAxe: Sharpening LLM-Authored Agent Skills Through Evaluation-Guided Self-Refinement","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2606.06752","citing_title":"Pomona: Continuous Code Quality Improvement via Small, Agentic Pull Requests at Bloomberg","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2606.06741","citing_title":"OpenSkill: Open-World Self-Evolution for LLM Agents","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2606.03692","citing_title":"SkillPyramid: A Hierarchical Skill Consolidation Framework for Self-Evolving Agents","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2606.03056","citing_title":"SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2606.01311","citing_title":"SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2606.01185","citing_title":"\"Skill Issues'': Data-Centric Optimization of Lakehouse Agents","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2605.26200","citing_title":"Workflow Closure Is Not Scientific Closure in Auto-Research Systems","ref_index":67,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09192","citing_title":"Evidence Over Plans: Online Trajectory Verification for Skill Distillation","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24198","citing_title":"Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07358","citing_title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","ref_index":66,"is_internal_anchor":true},{"citing_arxiv_id":"2605.29940","citing_title":"Make LLM Learn to Synthesize from Streaming Experiences through Feedback","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2606.20631","citing_title":"Harnessing Agent Skills: Architectural Patterns and a Reference Architecture for Skill-Mediated LLM Agents","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2606.00510","citing_title":"Skill or Skip? Learning Selective Skill Invocation in Agentic Tasks via Dual-Granularity Preference Learning","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2606.06416","citing_title":"Unsupervised Skill Discovery for Agentic Data Analysis","ref_index":63,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07358","citing_title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","ref_index":68,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18401","citing_title":"SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13064","citing_title":"Red Skills or Blue Skills? A Dive Into Skills Published on ClawHub","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13391","citing_title":"RS-Claw: Progressive Active Tool Exploration via Hierarchical Skill Trees for Remote Sensing Agents","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06130","citing_title":"Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning","ref_index":63,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27660","citing_title":"From Context to Skills: Can Language Models Learn from Context Skillfully?","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09192","citing_title":"Evidence Over Plans: Online Trajectory Verification for Skill Distillation","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2604.25727","citing_title":"Toward Scalable Terminal Task Synthesis via Skill Graphs","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06130","citing_title":"Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning","ref_index":63,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AY3GNTZHRTT6QRBDHRHQG63OC6","json":"https://pith.science/pith/AY3GNTZHRTT6QRBDHRHQG63OC6.json","graph_json":"https://pith.science/api/pith-number/AY3GNTZHRTT6QRBDHRHQG63OC6/graph.json","events_json":"https://pith.science/api/pith-number/AY3GNTZHRTT6QRBDHRHQG63OC6/events.json","paper":"https://pith.science/paper/AY3GNTZH"},"agent_actions":{"view_html":"https://pith.science/pith/AY3GNTZHRTT6QRBDHRHQG63OC6","download_json":"https://pith.science/pith/AY3GNTZHRTT6QRBDHRHQG63OC6.json","view_paper":"https://pith.science/paper/AY3GNTZH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.04448&json=true","fetch_graph":"https://pith.science/api/pith-number/AY3GNTZHRTT6QRBDHRHQG63OC6/graph.json","fetch_events":"https://pith.science/api/pith-number/AY3GNTZHRTT6QRBDHRHQG63OC6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AY3GNTZHRTT6QRBDHRHQG63OC6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AY3GNTZHRTT6QRBDHRHQG63OC6/action/storage_attestation","attest_author":"https://pith.science/pith/AY3GNTZHRTT6QRBDHRHQG63OC6/action/author_attestation","sign_citation":"https://pith.science/pith/AY3GNTZHRTT6QRBDHRHQG63OC6/action/citation_signature","submit_replication":"https://pith.science/pith/AY3GNTZHRTT6QRBDHRHQG63OC6/action/replication_record"}},"created_at":"2026-08-20T01:24:55.240642+00:00","updated_at":"2026-08-20T01:24:55.240642+00:00"}