{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7K6BBF67PL2RD2WXLCPN4GMDI7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"78fa12f1f4f7b0b927c938bb57c5ab897ec0cbbe77626463e7b13f256b9b20e3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-21T04:32:35Z","title_canon_sha256":"5dce2ec204da98cab023dc80d96004fe6dbffa43e09fe411c2e337744dcc0d46"},"schema_version":"1.0","source":{"id":"2505.15859","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.15859","created_at":"2026-07-05T11:07:26Z"},{"alias_kind":"arxiv_version","alias_value":"2505.15859v1","created_at":"2026-07-05T11:07:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15859","created_at":"2026-07-05T11:07:26Z"},{"alias_kind":"pith_short_12","alias_value":"7K6BBF67PL2R","created_at":"2026-07-05T11:07:26Z"},{"alias_kind":"pith_short_16","alias_value":"7K6BBF67PL2RD2WX","created_at":"2026-07-05T11:07:26Z"},{"alias_kind":"pith_short_8","alias_value":"7K6BBF67","created_at":"2026-07-05T11:07:26Z"}],"graph_snapshots":[{"event_id":"sha256:e288ab760b3d41ac40875b091e9b44b6257c3521bdf3c94074f7a70b336dd337","target":"graph","created_at":"2026-07-05T11:07:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.15859/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-21T04:32:35Z","title":"AutoData: A Multi-Agent System for Open Web Data Collection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15859","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a18ab4b4fd8173cd46db4ea63dec3a828f691ca09eb966ede19b85c508223a61","target":"record","created_at":"2026-07-05T11:07:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"78fa12f1f4f7b0b927c938bb57c5ab897ec0cbbe77626463e7b13f256b9b20e3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-21T04:32:35Z","title_canon_sha256":"5dce2ec204da98cab023dc80d96004fe6dbffa43e09fe411c2e337744dcc0d46"},"schema_version":"1.0","source":{"id":"2505.15859","kind":"arxiv","version":1}},"canonical_sha256":"fabc1097df7af511ead7589ede198347d6ace6b16dce50b1c3dde76e78f259d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fabc1097df7af511ead7589ede198347d6ace6b16dce50b1c3dde76e78f259d6","first_computed_at":"2026-07-05T11:07:26.465154Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:26.465154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hk01G+R/g63qE0rCaWKssSgAQVcgeGPOvYdyArNfoVBViyqPK4JG9t0U8449UQNuPH+7PZ7Qu2C4/tctco9/Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:26.465642Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.15859","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a18ab4b4fd8173cd46db4ea63dec3a828f691ca09eb966ede19b85c508223a61","sha256:e288ab760b3d41ac40875b091e9b44b6257c3521bdf3c94074f7a70b336dd337"],"state_sha256":"ff02d9b522e28aeb5024e126329048da0ec85d6997f67b9779deaa2d4c1a5286"}