{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:Z5DQZJES6ACL24MMEIG4YGGJEO","short_pith_number":"pith:Z5DQZJES","canonical_record":{"source":{"id":"2504.11011","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-04-15T09:32:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fc8bf6acbdf9eff570b2ff0eaca2bff75872e3d8748b1d2e5c9b9a339b25ca20","abstract_canon_sha256":"6fd38820d3d5e737dcd4972f60f2433a1d46dd2422bb3538b8ea0fa01e8f7b89"},"schema_version":"1.0"},"canonical_sha256":"cf470ca492f004bd718c220dcc18c923bb82ebc451968d58e779cd9deec345d0","source":{"kind":"arxiv","id":"2504.11011","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.11011","created_at":"2026-07-05T10:49:27Z"},{"alias_kind":"arxiv_version","alias_value":"2504.11011v1","created_at":"2026-07-05T10:49:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.11011","created_at":"2026-07-05T10:49:27Z"},{"alias_kind":"pith_short_12","alias_value":"Z5DQZJES6ACL","created_at":"2026-07-05T10:49:27Z"},{"alias_kind":"pith_short_16","alias_value":"Z5DQZJES6ACL24MM","created_at":"2026-07-05T10:49:27Z"},{"alias_kind":"pith_short_8","alias_value":"Z5DQZJES","created_at":"2026-07-05T10:49:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:Z5DQZJES6ACL24MMEIG4YGGJEO","target":"record","payload":{"canonical_record":{"source":{"id":"2504.11011","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-04-15T09:32:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fc8bf6acbdf9eff570b2ff0eaca2bff75872e3d8748b1d2e5c9b9a339b25ca20","abstract_canon_sha256":"6fd38820d3d5e737dcd4972f60f2433a1d46dd2422bb3538b8ea0fa01e8f7b89"},"schema_version":"1.0"},"canonical_sha256":"cf470ca492f004bd718c220dcc18c923bb82ebc451968d58e779cd9deec345d0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:27.850483Z","signature_b64":"rgjO8MTE8JAcHEbgx98pQvK53MHbQXTfk8fuWwEwVeLf74mC1JVBCSC+Xg/0v8vTbqzP8xIBGaZHswowWjudAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf470ca492f004bd718c220dcc18c923bb82ebc451968d58e779cd9deec345d0","last_reissued_at":"2026-07-05T10:49:27.849878Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:27.849878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.11011","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:49:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SZz/BAuIAS6TLx9YGtJhFiD02XS5ruVuv1np2sBjxYeqVfnpfWlr2g/rwL4QngLWAJDEH4NjtucSHrepxVDNAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T08:42:41.238047Z"},"content_sha256":"653a527646083721b0291b00d2152e9300ad8a4d8f9d9efc2cb1e416609fd23a","schema_version":"1.0","event_id":"sha256:653a527646083721b0291b00d2152e9300ad8a4d8f9d9efc2cb1e416609fd23a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:Z5DQZJES6ACL24MMEIG4YGGJEO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Document Quality Scoring for Web Crawling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Ariane Mueller, Francesca Pezzuti, Nicola Tonellotto, Sean MacAvaney","submitted_at":"2025-04-15T09:32:57Z","abstract_excerpt":"The internet contains large amounts of low-quality content, yet users expect web search engines to deliver high-quality, relevant results. The abundant presence of low-quality pages can negatively impact retrieval and crawling processes by wasting resources on these documents. Therefore, search engines can greatly benefit from techniques that leverage efficient quality estimation methods to mitigate these negative impacts. Quality scoring methods for web pages are useful for many processes typical for web search systems, including static index pruning, index tiering, and crawling. Building on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.11011","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/2504.11011/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":"2026-07-05T10:49:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rfvW/GXe0cJShPLGSq7sss7b28U45xdmY76X6ONPfftmqnWTs1eHbzW0l8H3Stw/4rd9lUMdsA+XiDXCbZgSDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T08:42:41.238563Z"},"content_sha256":"d2bacf8d2af1d3122710ed9d2a70cd9dd795b035b9be2a76a6bc55e10ec56f72","schema_version":"1.0","event_id":"sha256:d2bacf8d2af1d3122710ed9d2a70cd9dd795b035b9be2a76a6bc55e10ec56f72"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z5DQZJES6ACL24MMEIG4YGGJEO/bundle.json","state_url":"https://pith.science/pith/Z5DQZJES6ACL24MMEIG4YGGJEO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z5DQZJES6ACL24MMEIG4YGGJEO/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":"2026-08-10T08:42:41Z","links":{"resolver":"https://pith.science/pith/Z5DQZJES6ACL24MMEIG4YGGJEO","bundle":"https://pith.science/pith/Z5DQZJES6ACL24MMEIG4YGGJEO/bundle.json","state":"https://pith.science/pith/Z5DQZJES6ACL24MMEIG4YGGJEO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z5DQZJES6ACL24MMEIG4YGGJEO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Z5DQZJES6ACL24MMEIG4YGGJEO","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":"6fd38820d3d5e737dcd4972f60f2433a1d46dd2422bb3538b8ea0fa01e8f7b89","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-04-15T09:32:57Z","title_canon_sha256":"fc8bf6acbdf9eff570b2ff0eaca2bff75872e3d8748b1d2e5c9b9a339b25ca20"},"schema_version":"1.0","source":{"id":"2504.11011","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.11011","created_at":"2026-07-05T10:49:27Z"},{"alias_kind":"arxiv_version","alias_value":"2504.11011v1","created_at":"2026-07-05T10:49:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.11011","created_at":"2026-07-05T10:49:27Z"},{"alias_kind":"pith_short_12","alias_value":"Z5DQZJES6ACL","created_at":"2026-07-05T10:49:27Z"},{"alias_kind":"pith_short_16","alias_value":"Z5DQZJES6ACL24MM","created_at":"2026-07-05T10:49:27Z"},{"alias_kind":"pith_short_8","alias_value":"Z5DQZJES","created_at":"2026-07-05T10:49:27Z"}],"graph_snapshots":[{"event_id":"sha256:d2bacf8d2af1d3122710ed9d2a70cd9dd795b035b9be2a76a6bc55e10ec56f72","target":"graph","created_at":"2026-07-05T10:49:27Z","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/2504.11011/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The internet contains large amounts of low-quality content, yet users expect web search engines to deliver high-quality, relevant results. The abundant presence of low-quality pages can negatively impact retrieval and crawling processes by wasting resources on these documents. Therefore, search engines can greatly benefit from techniques that leverage efficient quality estimation methods to mitigate these negative impacts. Quality scoring methods for web pages are useful for many processes typical for web search systems, including static index pruning, index tiering, and crawling. Building on ","authors_text":"Ariane Mueller, Francesca Pezzuti, Nicola Tonellotto, Sean MacAvaney","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-04-15T09:32:57Z","title":"Document Quality Scoring for Web Crawling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.11011","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":"sha256:653a527646083721b0291b00d2152e9300ad8a4d8f9d9efc2cb1e416609fd23a","target":"record","created_at":"2026-07-05T10:49:27Z","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":"6fd38820d3d5e737dcd4972f60f2433a1d46dd2422bb3538b8ea0fa01e8f7b89","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-04-15T09:32:57Z","title_canon_sha256":"fc8bf6acbdf9eff570b2ff0eaca2bff75872e3d8748b1d2e5c9b9a339b25ca20"},"schema_version":"1.0","source":{"id":"2504.11011","kind":"arxiv","version":1}},"canonical_sha256":"cf470ca492f004bd718c220dcc18c923bb82ebc451968d58e779cd9deec345d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf470ca492f004bd718c220dcc18c923bb82ebc451968d58e779cd9deec345d0","first_computed_at":"2026-07-05T10:49:27.849878Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:49:27.849878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rgjO8MTE8JAcHEbgx98pQvK53MHbQXTfk8fuWwEwVeLf74mC1JVBCSC+Xg/0v8vTbqzP8xIBGaZHswowWjudAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:49:27.850483Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.11011","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:653a527646083721b0291b00d2152e9300ad8a4d8f9d9efc2cb1e416609fd23a","sha256:d2bacf8d2af1d3122710ed9d2a70cd9dd795b035b9be2a76a6bc55e10ec56f72"],"state_sha256":"7ef647ce0992890a0731a50a9bccdcac3b91bc69a9a5e819ee67aa387f70eed1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yIMWHRX6eR8Ias44nAW9XRjPlfViijizPsygIPMO0umIb/F/Xrs+iSzrFsdHdJdyvfBH2l8MJ6oPriWs3hy3Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T08:42:41.242285Z","bundle_sha256":"3e736aad3d839ea60041daba3db0be2bad34cbbf3512216d6d9756e1cd4b13b8"}}