{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:C723WH52AFRCNL2PB2BV2DPNCT","short_pith_number":"pith:C723WH52","schema_version":"1.0","canonical_sha256":"17f5bb1fba016226af4f0e835d0ded14ff53896b3ce3dff9e1697bba289c584d","source":{"kind":"arxiv","id":"2606.21597","version":1},"attestation_state":"computed","paper":{"title":"ATLAS: Agentic Taxonomy of Large-Scale Software Ecosystems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.SE","authors_text":"Chengwei Liu, Chun Zuo, Fengjun Zhang, Jiahui Wu, Junyi Lu, Lei Yu, Li Yang, Mengyao Lyu, Yang Liu","submitted_at":"2026-06-19T16:51:10Z","abstract_excerpt":"The open-source ecosystem on GitHub lacks a systematic hierarchical taxonomy of software repositories. GitHub Topics, the dominant organizational mechanism, is flat, inconsistent, and covers only 67% of projects. We present ATLAS, the first framework that automatically constructs a hierarchical taxonomy for software repositories and classifies projects into it end-to-end. By combining LLM global knowledge with real repository distributions, ATLAS proposes meaningful splitting dimensions and iteratively corrects those that fail to accommodate real projects. A Designer Agent proposes splitting d"},"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":"2606.21597","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-06-19T16:51:10Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"6d3553d475c2f38c4349db4d1ffae1b788695d1e325763ee6696f952695ac839","abstract_canon_sha256":"96cb0ed4996ccacdfc4473feb64df799afb65aca69a175f6207d60c67963dd1b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:13:15.782745Z","signature_b64":"nD///6RAyvmqblDY38DByvbEyFmpnhK3p5w6F+cRpfcLVVH8cF/UNvE0ZE4I+g7FnCM20FTD+y6gA721eYuyBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17f5bb1fba016226af4f0e835d0ded14ff53896b3ce3dff9e1697bba289c584d","last_reissued_at":"2026-06-23T01:13:15.782238Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:13:15.782238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ATLAS: Agentic Taxonomy of Large-Scale Software Ecosystems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.SE","authors_text":"Chengwei Liu, Chun Zuo, Fengjun Zhang, Jiahui Wu, Junyi Lu, Lei Yu, Li Yang, Mengyao Lyu, Yang Liu","submitted_at":"2026-06-19T16:51:10Z","abstract_excerpt":"The open-source ecosystem on GitHub lacks a systematic hierarchical taxonomy of software repositories. GitHub Topics, the dominant organizational mechanism, is flat, inconsistent, and covers only 67% of projects. We present ATLAS, the first framework that automatically constructs a hierarchical taxonomy for software repositories and classifies projects into it end-to-end. By combining LLM global knowledge with real repository distributions, ATLAS proposes meaningful splitting dimensions and iteratively corrects those that fail to accommodate real projects. A Designer Agent proposes splitting d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21597","kind":"arxiv","version":1},"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/2606.21597/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":"2606.21597","created_at":"2026-06-23T01:13:15.782308+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.21597v1","created_at":"2026-06-23T01:13:15.782308+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21597","created_at":"2026-06-23T01:13:15.782308+00:00"},{"alias_kind":"pith_short_12","alias_value":"C723WH52AFRC","created_at":"2026-06-23T01:13:15.782308+00:00"},{"alias_kind":"pith_short_16","alias_value":"C723WH52AFRCNL2P","created_at":"2026-06-23T01:13:15.782308+00:00"},{"alias_kind":"pith_short_8","alias_value":"C723WH52","created_at":"2026-06-23T01:13:15.782308+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C723WH52AFRCNL2PB2BV2DPNCT","json":"https://pith.science/pith/C723WH52AFRCNL2PB2BV2DPNCT.json","graph_json":"https://pith.science/api/pith-number/C723WH52AFRCNL2PB2BV2DPNCT/graph.json","events_json":"https://pith.science/api/pith-number/C723WH52AFRCNL2PB2BV2DPNCT/events.json","paper":"https://pith.science/paper/C723WH52"},"agent_actions":{"view_html":"https://pith.science/pith/C723WH52AFRCNL2PB2BV2DPNCT","download_json":"https://pith.science/pith/C723WH52AFRCNL2PB2BV2DPNCT.json","view_paper":"https://pith.science/paper/C723WH52","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.21597&json=true","fetch_graph":"https://pith.science/api/pith-number/C723WH52AFRCNL2PB2BV2DPNCT/graph.json","fetch_events":"https://pith.science/api/pith-number/C723WH52AFRCNL2PB2BV2DPNCT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C723WH52AFRCNL2PB2BV2DPNCT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C723WH52AFRCNL2PB2BV2DPNCT/action/storage_attestation","attest_author":"https://pith.science/pith/C723WH52AFRCNL2PB2BV2DPNCT/action/author_attestation","sign_citation":"https://pith.science/pith/C723WH52AFRCNL2PB2BV2DPNCT/action/citation_signature","submit_replication":"https://pith.science/pith/C723WH52AFRCNL2PB2BV2DPNCT/action/replication_record"}},"created_at":"2026-06-23T01:13:15.782308+00:00","updated_at":"2026-06-23T01:13:15.782308+00:00"}