{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3JE34T23FLEDS3S2S7TZZX42QV","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":"982b28cb33018da5c8345ad47bf2b312a068e1157a16798c42fd9ed4dd8c9ad6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-25T14:05:37Z","title_canon_sha256":"33cfd2583b0c34ab7a15d1755992bbd9803ac71255a70729ba14a37ec3261c63"},"schema_version":"1.0","source":{"id":"2607.00035","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.00035","created_at":"2026-07-02T00:18:32Z"},{"alias_kind":"arxiv_version","alias_value":"2607.00035v1","created_at":"2026-07-02T00:18:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00035","created_at":"2026-07-02T00:18:32Z"},{"alias_kind":"pith_short_12","alias_value":"3JE34T23FLED","created_at":"2026-07-02T00:18:32Z"},{"alias_kind":"pith_short_16","alias_value":"3JE34T23FLEDS3S2","created_at":"2026-07-02T00:18:32Z"},{"alias_kind":"pith_short_8","alias_value":"3JE34T23","created_at":"2026-07-02T00:18:32Z"}],"graph_snapshots":[{"event_id":"sha256:452f40a15c41971859b2ea1319eb888d807505d6fca13c3415bf9b4157c50daa","target":"graph","created_at":"2026-07-02T00:18:32Z","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/2607.00035/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLMs and agents can generate web scrapers from natural-language requirements, but direct generation remains unreliable because of dependency errors, broken selectors, schema mismatches, and heterogeneous page structures. We propose a constrained, verifiable agent framework that shifts LLM output from free-form code to typed JSON collector configurations, combining a six-type collector taxonomy, template and utility-function constraints, static Airflow DAG execution, rule-based quality checking, and structured feedback correction. Experiments on 138 tasks show that the taxonomy supports descrip","authors_text":"Bo Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-25T14:05:37Z","title":"Making Failure Safe: A Constrained, Verifiable Agent Framework for Open-Web Data Collection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00035","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":"sha256:0d65cc79e62e4b9653c7386df89edca9c25360ed592ea35349fe83deb7e2a07c","target":"record","created_at":"2026-07-02T00:18:32Z","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":"982b28cb33018da5c8345ad47bf2b312a068e1157a16798c42fd9ed4dd8c9ad6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-25T14:05:37Z","title_canon_sha256":"33cfd2583b0c34ab7a15d1755992bbd9803ac71255a70729ba14a37ec3261c63"},"schema_version":"1.0","source":{"id":"2607.00035","kind":"arxiv","version":1}},"canonical_sha256":"da49be4f5b2ac8396e5a97e79cdf9a85783c1a836eae2190aabe3fd3d723ad16","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da49be4f5b2ac8396e5a97e79cdf9a85783c1a836eae2190aabe3fd3d723ad16","first_computed_at":"2026-07-02T00:18:32.055545Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-02T00:18:32.055545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8MZlZmQd5YDnenV+DzRfzSB0S1zbVkvCJgaWDPlvBxNS5jgvl+mI0Hy3nYUu7Y5kvH08tQBj6YcneNRmIxMaCA==","signature_status":"signed_v1","signed_at":"2026-07-02T00:18:32.056243Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.00035","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0d65cc79e62e4b9653c7386df89edca9c25360ed592ea35349fe83deb7e2a07c","sha256:452f40a15c41971859b2ea1319eb888d807505d6fca13c3415bf9b4157c50daa"],"state_sha256":"1f7fa65c4027db2e28d7ee74ca9a7cc8c17b02fa3e8461e19ef17e6b0b82a1bf"}