{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7K6BBF67PL2RD2WXLCPN4GMDI7","short_pith_number":"pith:7K6BBF67","schema_version":"1.0","canonical_sha256":"fabc1097df7af511ead7589ede198347d6ace6b16dce50b1c3dde76e78f259d6","source":{"kind":"arxiv","id":"2505.15859","version":1},"attestation_state":"computed","paper":{"title":"AutoData: A Multi-Agent System for Open Web Data Collection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Chuxu Zhang, Feifan Bai, Keerthiram Murugesan, Shinan Zhang, Tianyi Ma, Xiaoye Qian, Xuwei Luo, Yanfang Ye, Yifan Ding, Yiyue Qian, Zehong Wang, Zheyuan Zhang","submitted_at":"2025-05-21T04:32:35Z","abstract_excerpt":"The exponential growth of data-driven systems and AI technologies has intensified the demand for high-quality web-sourced datasets. While existing datasets have proven valuable, conventional web data collection approaches face significant limitations in terms of human effort and scalability. Current data-collecting solutions fall into two categories: wrapper-based methods that struggle with adaptability and reproducibility, and large language model (LLM)-based approaches that incur substantial computational and financial costs. To address these challenges, we propose AutoData, a novel multi-ag"},"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":"2505.15859","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-21T04:32:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5dce2ec204da98cab023dc80d96004fe6dbffa43e09fe411c2e337744dcc0d46","abstract_canon_sha256":"78fa12f1f4f7b0b927c938bb57c5ab897ec0cbbe77626463e7b13f256b9b20e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:26.465642Z","signature_b64":"hk01G+R/g63qE0rCaWKssSgAQVcgeGPOvYdyArNfoVBViyqPK4JG9t0U8449UQNuPH+7PZ7Qu2C4/tctco9/Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fabc1097df7af511ead7589ede198347d6ace6b16dce50b1c3dde76e78f259d6","last_reissued_at":"2026-07-05T11:07:26.465154Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:26.465154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AutoData: A Multi-Agent System for Open Web Data Collection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Chuxu Zhang, Feifan Bai, Keerthiram Murugesan, Shinan Zhang, Tianyi Ma, Xiaoye Qian, Xuwei Luo, Yanfang Ye, Yifan Ding, Yiyue Qian, Zehong Wang, Zheyuan Zhang","submitted_at":"2025-05-21T04:32:35Z","abstract_excerpt":"The exponential growth of data-driven systems and AI technologies has intensified the demand for high-quality web-sourced datasets. While existing datasets have proven valuable, conventional web data collection approaches face significant limitations in terms of human effort and scalability. Current data-collecting solutions fall into two categories: wrapper-based methods that struggle with adaptability and reproducibility, and large language model (LLM)-based approaches that incur substantial computational and financial costs. To address these challenges, we propose AutoData, a novel multi-ag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15859","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/2505.15859/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":"2505.15859","created_at":"2026-07-05T11:07:26.465203+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.15859v1","created_at":"2026-07-05T11:07:26.465203+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15859","created_at":"2026-07-05T11:07:26.465203+00:00"},{"alias_kind":"pith_short_12","alias_value":"7K6BBF67PL2R","created_at":"2026-07-05T11:07:26.465203+00:00"},{"alias_kind":"pith_short_16","alias_value":"7K6BBF67PL2RD2WX","created_at":"2026-07-05T11:07:26.465203+00:00"},{"alias_kind":"pith_short_8","alias_value":"7K6BBF67","created_at":"2026-07-05T11:07:26.465203+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.23452","citing_title":"CiteAudit: You Cited It, But Did You Read It? A Benchmark for Verifying Scientific References in the LLM Era","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08583","citing_title":"Source or It Didn't Happen: A Multi-Agent Framework for Citation Hallucination Detection","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7K6BBF67PL2RD2WXLCPN4GMDI7","json":"https://pith.science/pith/7K6BBF67PL2RD2WXLCPN4GMDI7.json","graph_json":"https://pith.science/api/pith-number/7K6BBF67PL2RD2WXLCPN4GMDI7/graph.json","events_json":"https://pith.science/api/pith-number/7K6BBF67PL2RD2WXLCPN4GMDI7/events.json","paper":"https://pith.science/paper/7K6BBF67"},"agent_actions":{"view_html":"https://pith.science/pith/7K6BBF67PL2RD2WXLCPN4GMDI7","download_json":"https://pith.science/pith/7K6BBF67PL2RD2WXLCPN4GMDI7.json","view_paper":"https://pith.science/paper/7K6BBF67","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.15859&json=true","fetch_graph":"https://pith.science/api/pith-number/7K6BBF67PL2RD2WXLCPN4GMDI7/graph.json","fetch_events":"https://pith.science/api/pith-number/7K6BBF67PL2RD2WXLCPN4GMDI7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7K6BBF67PL2RD2WXLCPN4GMDI7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7K6BBF67PL2RD2WXLCPN4GMDI7/action/storage_attestation","attest_author":"https://pith.science/pith/7K6BBF67PL2RD2WXLCPN4GMDI7/action/author_attestation","sign_citation":"https://pith.science/pith/7K6BBF67PL2RD2WXLCPN4GMDI7/action/citation_signature","submit_replication":"https://pith.science/pith/7K6BBF67PL2RD2WXLCPN4GMDI7/action/replication_record"}},"created_at":"2026-07-05T11:07:26.465203+00:00","updated_at":"2026-07-05T11:07:26.465203+00:00"}