{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TTXYS4U5VWTOEIQUONP2QBHM6O","short_pith_number":"pith:TTXYS4U5","schema_version":"1.0","canonical_sha256":"9cef89729dada6e22214735fa804ecf3b80183cf62eff47370cefb56ba2f5eec","source":{"kind":"arxiv","id":"2607.14447","version":1},"attestation_state":"computed","paper":{"title":"Do Generative AI Assistants Respect robots.txt? Tracing Web Access Beyond Visible Answers","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CY","authors_text":"David Rodriguez, Gabriel Lopez-Fonseca, Jose M. del Alamo, Stefan Bechtold","submitted_at":"2026-07-16T00:45:06Z","abstract_excerpt":"AI assistants increasingly retrieve web content at inference time to provide fresh and grounded answers, yet it remains unclear whether these search-augmented capabilities respect website-owner restrictions expressed through robots.txt. We present a controlled empirical study of ten widely used AI assistants with advertised web-search capabilities. For each assistant, we first identify a configuration that actually produces observable web-browsing behavior and record the user-agent exposed during retrieval. We then evaluate compliance with controlled robots.txt rules across four complementary "},"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":"2607.14447","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CY","submitted_at":"2026-07-16T00:45:06Z","cross_cats_sorted":[],"title_canon_sha256":"ec98d5c31dfcc4a41e2b228ec6a5ad983a6258078ffcc82c2861d6b1ff262ef4","abstract_canon_sha256":"80de6ec84ec53a24a714a375a17c20db52ce7cf636ae9ebce781fab2938cddda"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T00:21:12.879676Z","signature_b64":"vBZXjUcTnr6n7YeXGGfleYe6JHJ9+oGCwZgZgmCgRQm0XqeamyBfQVllzBSUsisbERt5vaZ8hkwR+cvEztflCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9cef89729dada6e22214735fa804ecf3b80183cf62eff47370cefb56ba2f5eec","last_reissued_at":"2026-07-17T00:21:12.878844Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T00:21:12.878844Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do Generative AI Assistants Respect robots.txt? Tracing Web Access Beyond Visible Answers","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CY","authors_text":"David Rodriguez, Gabriel Lopez-Fonseca, Jose M. del Alamo, Stefan Bechtold","submitted_at":"2026-07-16T00:45:06Z","abstract_excerpt":"AI assistants increasingly retrieve web content at inference time to provide fresh and grounded answers, yet it remains unclear whether these search-augmented capabilities respect website-owner restrictions expressed through robots.txt. We present a controlled empirical study of ten widely used AI assistants with advertised web-search capabilities. For each assistant, we first identify a configuration that actually produces observable web-browsing behavior and record the user-agent exposed during retrieval. We then evaluate compliance with controlled robots.txt rules across four complementary "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14447","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/2607.14447/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":"2607.14447","created_at":"2026-07-17T00:21:12.879274+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.14447v1","created_at":"2026-07-17T00:21:12.879274+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14447","created_at":"2026-07-17T00:21:12.879274+00:00"},{"alias_kind":"pith_short_12","alias_value":"TTXYS4U5VWTO","created_at":"2026-07-17T00:21:12.879274+00:00"},{"alias_kind":"pith_short_16","alias_value":"TTXYS4U5VWTOEIQU","created_at":"2026-07-17T00:21:12.879274+00:00"},{"alias_kind":"pith_short_8","alias_value":"TTXYS4U5","created_at":"2026-07-17T00:21:12.879274+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/TTXYS4U5VWTOEIQUONP2QBHM6O","json":"https://pith.science/pith/TTXYS4U5VWTOEIQUONP2QBHM6O.json","graph_json":"https://pith.science/api/pith-number/TTXYS4U5VWTOEIQUONP2QBHM6O/graph.json","events_json":"https://pith.science/api/pith-number/TTXYS4U5VWTOEIQUONP2QBHM6O/events.json","paper":"https://pith.science/paper/TTXYS4U5"},"agent_actions":{"view_html":"https://pith.science/pith/TTXYS4U5VWTOEIQUONP2QBHM6O","download_json":"https://pith.science/pith/TTXYS4U5VWTOEIQUONP2QBHM6O.json","view_paper":"https://pith.science/paper/TTXYS4U5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.14447&json=true","fetch_graph":"https://pith.science/api/pith-number/TTXYS4U5VWTOEIQUONP2QBHM6O/graph.json","fetch_events":"https://pith.science/api/pith-number/TTXYS4U5VWTOEIQUONP2QBHM6O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TTXYS4U5VWTOEIQUONP2QBHM6O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TTXYS4U5VWTOEIQUONP2QBHM6O/action/storage_attestation","attest_author":"https://pith.science/pith/TTXYS4U5VWTOEIQUONP2QBHM6O/action/author_attestation","sign_citation":"https://pith.science/pith/TTXYS4U5VWTOEIQUONP2QBHM6O/action/citation_signature","submit_replication":"https://pith.science/pith/TTXYS4U5VWTOEIQUONP2QBHM6O/action/replication_record"}},"created_at":"2026-07-17T00:21:12.879274+00:00","updated_at":"2026-07-17T00:21:12.879274+00:00"}