{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LA2OYGAVOA4NKP4VZZ4ET7YPAI","short_pith_number":"pith:LA2OYGAV","canonical_record":{"source":{"id":"2506.16146","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-06-19T08:59:21Z","cross_cats_sorted":[],"title_canon_sha256":"de7ae8711f7ed85cdb86feeac6f8ed7c3e51b65acc727f7d597d92207781088c","abstract_canon_sha256":"f3846fc6f2ebe4c2955699b1379ca2901dc1beaaf5b4bb90aca24c8e0658b404"},"schema_version":"1.0"},"canonical_sha256":"5834ec18157038d53f95ce7849ff0f0214cc379bf279e5cd88672d8101e8362c","source":{"kind":"arxiv","id":"2506.16146","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.16146","created_at":"2026-07-05T11:30:44Z"},{"alias_kind":"arxiv_version","alias_value":"2506.16146v2","created_at":"2026-07-05T11:30:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16146","created_at":"2026-07-05T11:30:44Z"},{"alias_kind":"pith_short_12","alias_value":"LA2OYGAVOA4N","created_at":"2026-07-05T11:30:44Z"},{"alias_kind":"pith_short_16","alias_value":"LA2OYGAVOA4NKP4V","created_at":"2026-07-05T11:30:44Z"},{"alias_kind":"pith_short_8","alias_value":"LA2OYGAV","created_at":"2026-07-05T11:30:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LA2OYGAVOA4NKP4VZZ4ET7YPAI","target":"record","payload":{"canonical_record":{"source":{"id":"2506.16146","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-06-19T08:59:21Z","cross_cats_sorted":[],"title_canon_sha256":"de7ae8711f7ed85cdb86feeac6f8ed7c3e51b65acc727f7d597d92207781088c","abstract_canon_sha256":"f3846fc6f2ebe4c2955699b1379ca2901dc1beaaf5b4bb90aca24c8e0658b404"},"schema_version":"1.0"},"canonical_sha256":"5834ec18157038d53f95ce7849ff0f0214cc379bf279e5cd88672d8101e8362c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:44.894795Z","signature_b64":"xKJNUdxpFlhwfHwZ+CrTxkoTwnatsSMXfoq+okfIyv/m4MDhgn/wubBt8DYzQDrBw89c4CA3cmBTaZBGfzozCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5834ec18157038d53f95ce7849ff0f0214cc379bf279e5cd88672d8101e8362c","last_reissued_at":"2026-07-05T11:30:44.894285Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:44.894285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.16146","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:30:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ASENJbYJ2siuPP4WE6ENEo+uONfa2xAGc+ywIM9wtibGgGwGYX4kSE7NheGJ+vn6EjdEIBTXLdqnfSU1dWQ7Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:34:53.242545Z"},"content_sha256":"7d909e0f687c587a2e57802e73ed3f9b04f18efe2c64fb6d855073c28dcd1dd6","schema_version":"1.0","event_id":"sha256:7d909e0f687c587a2e57802e73ed3f9b04f18efe2c64fb6d855073c28dcd1dd6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LA2OYGAVOA4NKP4VZZ4ET7YPAI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural Prioritisation for Web Crawling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Francesca Pezzuti, Nicola Tonellotto, Sean MacAvaney","submitted_at":"2025-06-19T08:59:21Z","abstract_excerpt":"Given the vast scale of the Web, crawling prioritisation techniques based on link graph traversal, popularity, link analysis, and textual content are frequently applied to surface documents that are most likely to be valuable. While existing techniques are effective for keyword-based search, both retrieval methods and user search behaviours are shifting from keyword-based matching to natural language semantic matching. The remarkable success of applying semantic matching and quality signals during ranking leads us to hypothesize that crawling could be improved by prioritizing Web pages with hi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16146","kind":"arxiv","version":2},"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/2506.16146/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":"2026-07-05T11:30:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lx0jHp97zyVULJyXQO8fI9AAMhyQKXd5jpKE8i0aoFXHfyyimLkUhinP07ldu4cBV87al9X1IL2un5X3W6DeAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:34:53.243072Z"},"content_sha256":"7ac913262c739fa7896fd11bc2100e7f4ab6308e42c9658c466239896d902044","schema_version":"1.0","event_id":"sha256:7ac913262c739fa7896fd11bc2100e7f4ab6308e42c9658c466239896d902044"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LA2OYGAVOA4NKP4VZZ4ET7YPAI/bundle.json","state_url":"https://pith.science/pith/LA2OYGAVOA4NKP4VZZ4ET7YPAI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LA2OYGAVOA4NKP4VZZ4ET7YPAI/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":"2026-08-08T21:34:53Z","links":{"resolver":"https://pith.science/pith/LA2OYGAVOA4NKP4VZZ4ET7YPAI","bundle":"https://pith.science/pith/LA2OYGAVOA4NKP4VZZ4ET7YPAI/bundle.json","state":"https://pith.science/pith/LA2OYGAVOA4NKP4VZZ4ET7YPAI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LA2OYGAVOA4NKP4VZZ4ET7YPAI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LA2OYGAVOA4NKP4VZZ4ET7YPAI","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":"f3846fc6f2ebe4c2955699b1379ca2901dc1beaaf5b4bb90aca24c8e0658b404","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-06-19T08:59:21Z","title_canon_sha256":"de7ae8711f7ed85cdb86feeac6f8ed7c3e51b65acc727f7d597d92207781088c"},"schema_version":"1.0","source":{"id":"2506.16146","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.16146","created_at":"2026-07-05T11:30:44Z"},{"alias_kind":"arxiv_version","alias_value":"2506.16146v2","created_at":"2026-07-05T11:30:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16146","created_at":"2026-07-05T11:30:44Z"},{"alias_kind":"pith_short_12","alias_value":"LA2OYGAVOA4N","created_at":"2026-07-05T11:30:44Z"},{"alias_kind":"pith_short_16","alias_value":"LA2OYGAVOA4NKP4V","created_at":"2026-07-05T11:30:44Z"},{"alias_kind":"pith_short_8","alias_value":"LA2OYGAV","created_at":"2026-07-05T11:30:44Z"}],"graph_snapshots":[{"event_id":"sha256:7ac913262c739fa7896fd11bc2100e7f4ab6308e42c9658c466239896d902044","target":"graph","created_at":"2026-07-05T11:30:44Z","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/2506.16146/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Given the vast scale of the Web, crawling prioritisation techniques based on link graph traversal, popularity, link analysis, and textual content are frequently applied to surface documents that are most likely to be valuable. While existing techniques are effective for keyword-based search, both retrieval methods and user search behaviours are shifting from keyword-based matching to natural language semantic matching. The remarkable success of applying semantic matching and quality signals during ranking leads us to hypothesize that crawling could be improved by prioritizing Web pages with hi","authors_text":"Francesca Pezzuti, Nicola Tonellotto, Sean MacAvaney","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-06-19T08:59:21Z","title":"Neural Prioritisation for Web Crawling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16146","kind":"arxiv","version":2},"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":"sha256:7d909e0f687c587a2e57802e73ed3f9b04f18efe2c64fb6d855073c28dcd1dd6","target":"record","created_at":"2026-07-05T11:30:44Z","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":"f3846fc6f2ebe4c2955699b1379ca2901dc1beaaf5b4bb90aca24c8e0658b404","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-06-19T08:59:21Z","title_canon_sha256":"de7ae8711f7ed85cdb86feeac6f8ed7c3e51b65acc727f7d597d92207781088c"},"schema_version":"1.0","source":{"id":"2506.16146","kind":"arxiv","version":2}},"canonical_sha256":"5834ec18157038d53f95ce7849ff0f0214cc379bf279e5cd88672d8101e8362c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5834ec18157038d53f95ce7849ff0f0214cc379bf279e5cd88672d8101e8362c","first_computed_at":"2026-07-05T11:30:44.894285Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:30:44.894285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xKJNUdxpFlhwfHwZ+CrTxkoTwnatsSMXfoq+okfIyv/m4MDhgn/wubBt8DYzQDrBw89c4CA3cmBTaZBGfzozCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:30:44.894795Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.16146","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7d909e0f687c587a2e57802e73ed3f9b04f18efe2c64fb6d855073c28dcd1dd6","sha256:7ac913262c739fa7896fd11bc2100e7f4ab6308e42c9658c466239896d902044"],"state_sha256":"89f7876264b3a1d6a4630cb1389df476bb33dab5e395e2d5e73006aa585a3414"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xiWXwHvg0ND8Yor506i/Lc9R/CNnqIm5g2ah+6JqG8f/bU0fnA8TL8pH+8UhtA0PFFy3nvNUqOMbDUIXf/D2AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T21:34:53.246638Z","bundle_sha256":"006d5af7703bf003a0c864deff7f03e600305ee64084111b212d8fa8537fae46"}}