{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CLU7EPMCBJJ647UCBQI7OEMRT5","short_pith_number":"pith:CLU7EPMC","canonical_record":{"source":{"id":"2510.10315","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2025-10-11T18:47:14Z","cross_cats_sorted":[],"title_canon_sha256":"6e4d904dcb587badfab58b49fdd6decf851377a9cf92345333df617223738660","abstract_canon_sha256":"0708585bcbe0a152d19f25453d7fcebb75dd395958215bd4c5a5af374854daa6"},"schema_version":"1.0"},"canonical_sha256":"12e9f23d820a53ee7e820c11f711919f66eb2d7470b313ccda5f5d19abe30841","source":{"kind":"arxiv","id":"2510.10315","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.10315","created_at":"2026-07-29T01:25:29Z"},{"alias_kind":"arxiv_version","alias_value":"2510.10315v3","created_at":"2026-07-29T01:25:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.10315","created_at":"2026-07-29T01:25:29Z"},{"alias_kind":"pith_short_12","alias_value":"CLU7EPMCBJJ6","created_at":"2026-07-29T01:25:29Z"},{"alias_kind":"pith_short_16","alias_value":"CLU7EPMCBJJ647UC","created_at":"2026-07-29T01:25:29Z"},{"alias_kind":"pith_short_8","alias_value":"CLU7EPMC","created_at":"2026-07-29T01:25:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CLU7EPMCBJJ647UCBQI7OEMRT5","target":"record","payload":{"canonical_record":{"source":{"id":"2510.10315","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2025-10-11T18:47:14Z","cross_cats_sorted":[],"title_canon_sha256":"6e4d904dcb587badfab58b49fdd6decf851377a9cf92345333df617223738660","abstract_canon_sha256":"0708585bcbe0a152d19f25453d7fcebb75dd395958215bd4c5a5af374854daa6"},"schema_version":"1.0"},"canonical_sha256":"12e9f23d820a53ee7e820c11f711919f66eb2d7470b313ccda5f5d19abe30841","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T01:25:29.710241Z","signature_b64":"J7tIEMgzeMR6W4C0yDXibrElHJprK1rPdvLuD7+gZfyPZx5z/Q3qVYRoEVzD9k1vEER7GMgO/Npk/SewVDk7DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12e9f23d820a53ee7e820c11f711919f66eb2d7470b313ccda5f5d19abe30841","last_reissued_at":"2026-07-29T01:25:29.709347Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T01:25:29.709347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2510.10315","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-29T01:25:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5VVKkTDs9GCB160B2AqPFt4uQL3QsoA3NL8FpsfKVpjc7eRx76csAwldXNCKbhk8sLAVevMCa6xaPuaHtBlaDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T15:22:44.713286Z"},"content_sha256":"16f93a56070423ed6255c3e58e9cb584caef81094db41531d11b0f9bebfa7380","schema_version":"1.0","event_id":"sha256:16f93a56070423ed6255c3e58e9cb584caef81094db41531d11b0f9bebfa7380"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CLU7EPMCBJJ647UCBQI7OEMRT5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Is Misinformation More Open? A Study of robots.txt Gatekeeping on the Web","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CY","authors_text":"Devashish Gosain, Ha Dao, Nicolas Steinacker-Olsztyn","submitted_at":"2025-10-11T18:47:14Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly relying on web crawling to stay up to date and accurately answer user queries. These crawlers are expected to honor robots.txt files, which govern automated access. In this study, for the first time, we investigate whether reputable news websites and misinformation sites differ in how they configure these files, particularly in relation to AI crawlers. Analyzing a curated dataset, we find a stark contrast: 60.0% of reputable sites disallow at least one AI crawler, compared to just 9.1% of misinformation sites in their robots.txt files. Reputable si"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.10315","kind":"arxiv","version":3},"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/2510.10315/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-29T01:25:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aH+9IR8HQvthP072gJwJgwnLRDQs6ssRfSlGQ2bEmXQW5lAJdTt7Is+ApbnmDzWl6ySIM1st115HA2J+xtQpCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T15:22:44.713784Z"},"content_sha256":"8930a1aad14f9d35f5ede12c1323db59e453be278200cdf98fa69329a9c011b3","schema_version":"1.0","event_id":"sha256:8930a1aad14f9d35f5ede12c1323db59e453be278200cdf98fa69329a9c011b3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CLU7EPMCBJJ647UCBQI7OEMRT5/bundle.json","state_url":"https://pith.science/pith/CLU7EPMCBJJ647UCBQI7OEMRT5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CLU7EPMCBJJ647UCBQI7OEMRT5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T15:22:44Z","links":{"resolver":"https://pith.science/pith/CLU7EPMCBJJ647UCBQI7OEMRT5","bundle":"https://pith.science/pith/CLU7EPMCBJJ647UCBQI7OEMRT5/bundle.json","state":"https://pith.science/pith/CLU7EPMCBJJ647UCBQI7OEMRT5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CLU7EPMCBJJ647UCBQI7OEMRT5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CLU7EPMCBJJ647UCBQI7OEMRT5","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":"0708585bcbe0a152d19f25453d7fcebb75dd395958215bd4c5a5af374854daa6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2025-10-11T18:47:14Z","title_canon_sha256":"6e4d904dcb587badfab58b49fdd6decf851377a9cf92345333df617223738660"},"schema_version":"1.0","source":{"id":"2510.10315","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.10315","created_at":"2026-07-29T01:25:29Z"},{"alias_kind":"arxiv_version","alias_value":"2510.10315v3","created_at":"2026-07-29T01:25:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.10315","created_at":"2026-07-29T01:25:29Z"},{"alias_kind":"pith_short_12","alias_value":"CLU7EPMCBJJ6","created_at":"2026-07-29T01:25:29Z"},{"alias_kind":"pith_short_16","alias_value":"CLU7EPMCBJJ647UC","created_at":"2026-07-29T01:25:29Z"},{"alias_kind":"pith_short_8","alias_value":"CLU7EPMC","created_at":"2026-07-29T01:25:29Z"}],"graph_snapshots":[{"event_id":"sha256:8930a1aad14f9d35f5ede12c1323db59e453be278200cdf98fa69329a9c011b3","target":"graph","created_at":"2026-07-29T01:25:29Z","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/2510.10315/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) are increasingly relying on web crawling to stay up to date and accurately answer user queries. These crawlers are expected to honor robots.txt files, which govern automated access. In this study, for the first time, we investigate whether reputable news websites and misinformation sites differ in how they configure these files, particularly in relation to AI crawlers. Analyzing a curated dataset, we find a stark contrast: 60.0% of reputable sites disallow at least one AI crawler, compared to just 9.1% of misinformation sites in their robots.txt files. Reputable si","authors_text":"Devashish Gosain, Ha Dao, Nicolas Steinacker-Olsztyn","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2025-10-11T18:47:14Z","title":"Is Misinformation More Open? A Study of robots.txt Gatekeeping on the Web"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.10315","kind":"arxiv","version":3},"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":"sha256:16f93a56070423ed6255c3e58e9cb584caef81094db41531d11b0f9bebfa7380","target":"record","created_at":"2026-07-29T01:25:29Z","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":"0708585bcbe0a152d19f25453d7fcebb75dd395958215bd4c5a5af374854daa6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2025-10-11T18:47:14Z","title_canon_sha256":"6e4d904dcb587badfab58b49fdd6decf851377a9cf92345333df617223738660"},"schema_version":"1.0","source":{"id":"2510.10315","kind":"arxiv","version":3}},"canonical_sha256":"12e9f23d820a53ee7e820c11f711919f66eb2d7470b313ccda5f5d19abe30841","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"12e9f23d820a53ee7e820c11f711919f66eb2d7470b313ccda5f5d19abe30841","first_computed_at":"2026-07-29T01:25:29.709347Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-29T01:25:29.709347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J7tIEMgzeMR6W4C0yDXibrElHJprK1rPdvLuD7+gZfyPZx5z/Q3qVYRoEVzD9k1vEER7GMgO/Npk/SewVDk7DA==","signature_status":"signed_v1","signed_at":"2026-07-29T01:25:29.710241Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.10315","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16f93a56070423ed6255c3e58e9cb584caef81094db41531d11b0f9bebfa7380","sha256:8930a1aad14f9d35f5ede12c1323db59e453be278200cdf98fa69329a9c011b3"],"state_sha256":"36f5a9c5bd4f7234d4e1288aa0cb70ecc747e8bb9d3b429ca7054bdeac1623b0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zq12Nypvt7Lj3dW5P79fKVpAVRpsBQC3/RAY+H/2MybMKj8d/3WHyt38k1Dnz2uwNERw8Kg5AGknGBnPsB3ZDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T15:22:44.719528Z","bundle_sha256":"dd5a9b4b408a9dd1d5ce64d0d3629b927edf30fa195a16e68f7664b00ed3f6f6"}}