{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ZZ2RJJTE6SCSHZZYBLUN7BDPMS","short_pith_number":"pith:ZZ2RJJTE","canonical_record":{"source":{"id":"2111.10864","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2021-11-21T17:34:39Z","cross_cats_sorted":[],"title_canon_sha256":"c2dad03edbe0bf2f6a4ade78934cdb88f7c30e5844375c396a64901b3246320d","abstract_canon_sha256":"173c362e9e7e2e66a4656aaa04c962c6ce213e110c7766b358b47b07fcc20f4d"},"schema_version":"1.0"},"canonical_sha256":"ce7514a664f48523e7380ae8df846f64836f9658820d4d251f86b7171f87387d","source":{"kind":"arxiv","id":"2111.10864","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.10864","created_at":"2026-07-05T03:33:57Z"},{"alias_kind":"arxiv_version","alias_value":"2111.10864v1","created_at":"2026-07-05T03:33:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.10864","created_at":"2026-07-05T03:33:57Z"},{"alias_kind":"pith_short_12","alias_value":"ZZ2RJJTE6SCS","created_at":"2026-07-05T03:33:57Z"},{"alias_kind":"pith_short_16","alias_value":"ZZ2RJJTE6SCSHZZY","created_at":"2026-07-05T03:33:57Z"},{"alias_kind":"pith_short_8","alias_value":"ZZ2RJJTE","created_at":"2026-07-05T03:33:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ZZ2RJJTE6SCSHZZYBLUN7BDPMS","target":"record","payload":{"canonical_record":{"source":{"id":"2111.10864","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2021-11-21T17:34:39Z","cross_cats_sorted":[],"title_canon_sha256":"c2dad03edbe0bf2f6a4ade78934cdb88f7c30e5844375c396a64901b3246320d","abstract_canon_sha256":"173c362e9e7e2e66a4656aaa04c962c6ce213e110c7766b358b47b07fcc20f4d"},"schema_version":"1.0"},"canonical_sha256":"ce7514a664f48523e7380ae8df846f64836f9658820d4d251f86b7171f87387d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:33:57.593698Z","signature_b64":"cg3gHUlbLWOmVZWtXOYp0iIWfLurGekfuG7kOozekxXfqRenN/seXalfXP8lMEc0PGOA9pYv9+Wbo3Bb+BmbAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce7514a664f48523e7380ae8df846f64836f9658820d4d251f86b7171f87387d","last_reissued_at":"2026-07-05T03:33:57.593245Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:33:57.593245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.10864","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":"2026-07-05T03:33:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ubx0SW/2lHpi/cELA8Iq+pSHboBsS4vGsqWJe+b9tWzEzIY5AQAwrOh16J1WUme3/pp5mqqa1BnGp7dUJraTDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:15:59.206496Z"},"content_sha256":"6aa349049c47aef5115bafedff851855e175a16d9883f3ebe554ff6e6737ea1f","schema_version":"1.0","event_id":"sha256:6aa349049c47aef5115bafedff851855e175a16d9883f3ebe554ff6e6737ea1f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ZZ2RJJTE6SCSHZZYBLUN7BDPMS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Impact of Main Content Extraction on Near-Duplicate Detection","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Benno Stein, Christopher Schr\\\"oder, Janek Bevendorff, Lukas Gienapp, Maik Fr\\\"obe, Martin Potthast, Matthias Hagen, Michael V\\\"olske, Robby Wagner","submitted_at":"2021-11-21T17:34:39Z","abstract_excerpt":"Commercial web search engines employ near-duplicate detection to ensure that users see each relevant result only once, albeit the underlying web crawls typically include (near-)duplicates of many web pages. We revisit the risks and potential of near-duplicates with an information retrieval focus, motivating that current efforts toward an open and independent European web search infrastructure should maintain metadata on duplicate and near-duplicate documents in its index.\n  Near-duplicate detection implemented in an open web search infrastructure should provide a suitable similarity threshold,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.10864","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/2111.10864/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":"2026-07-05T03:33:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3tMjZSgbNuGg4M0vD80GdqB3HG0wnfz+pxyromS1iwbIQBKXb+3Cdb6/ENbg8cO/8dSB8ro8AI94qOSyRuOjBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:15:59.207353Z"},"content_sha256":"0639e6218bfe703a179287cb4803160ff2b4b8a3729039f853a44c422f95443b","schema_version":"1.0","event_id":"sha256:0639e6218bfe703a179287cb4803160ff2b4b8a3729039f853a44c422f95443b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZZ2RJJTE6SCSHZZYBLUN7BDPMS/bundle.json","state_url":"https://pith.science/pith/ZZ2RJJTE6SCSHZZYBLUN7BDPMS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZZ2RJJTE6SCSHZZYBLUN7BDPMS/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":"2026-08-07T06:15:59Z","links":{"resolver":"https://pith.science/pith/ZZ2RJJTE6SCSHZZYBLUN7BDPMS","bundle":"https://pith.science/pith/ZZ2RJJTE6SCSHZZYBLUN7BDPMS/bundle.json","state":"https://pith.science/pith/ZZ2RJJTE6SCSHZZYBLUN7BDPMS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZZ2RJJTE6SCSHZZYBLUN7BDPMS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ZZ2RJJTE6SCSHZZYBLUN7BDPMS","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":"173c362e9e7e2e66a4656aaa04c962c6ce213e110c7766b358b47b07fcc20f4d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2021-11-21T17:34:39Z","title_canon_sha256":"c2dad03edbe0bf2f6a4ade78934cdb88f7c30e5844375c396a64901b3246320d"},"schema_version":"1.0","source":{"id":"2111.10864","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.10864","created_at":"2026-07-05T03:33:57Z"},{"alias_kind":"arxiv_version","alias_value":"2111.10864v1","created_at":"2026-07-05T03:33:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.10864","created_at":"2026-07-05T03:33:57Z"},{"alias_kind":"pith_short_12","alias_value":"ZZ2RJJTE6SCS","created_at":"2026-07-05T03:33:57Z"},{"alias_kind":"pith_short_16","alias_value":"ZZ2RJJTE6SCSHZZY","created_at":"2026-07-05T03:33:57Z"},{"alias_kind":"pith_short_8","alias_value":"ZZ2RJJTE","created_at":"2026-07-05T03:33:57Z"}],"graph_snapshots":[{"event_id":"sha256:0639e6218bfe703a179287cb4803160ff2b4b8a3729039f853a44c422f95443b","target":"graph","created_at":"2026-07-05T03:33:57Z","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/2111.10864/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Commercial web search engines employ near-duplicate detection to ensure that users see each relevant result only once, albeit the underlying web crawls typically include (near-)duplicates of many web pages. We revisit the risks and potential of near-duplicates with an information retrieval focus, motivating that current efforts toward an open and independent European web search infrastructure should maintain metadata on duplicate and near-duplicate documents in its index.\n  Near-duplicate detection implemented in an open web search infrastructure should provide a suitable similarity threshold,","authors_text":"Benno Stein, Christopher Schr\\\"oder, Janek Bevendorff, Lukas Gienapp, Maik Fr\\\"obe, Martin Potthast, Matthias Hagen, Michael V\\\"olske, Robby Wagner","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2021-11-21T17:34:39Z","title":"The Impact of Main Content Extraction on Near-Duplicate Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.10864","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":"sha256:6aa349049c47aef5115bafedff851855e175a16d9883f3ebe554ff6e6737ea1f","target":"record","created_at":"2026-07-05T03:33:57Z","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":"173c362e9e7e2e66a4656aaa04c962c6ce213e110c7766b358b47b07fcc20f4d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2021-11-21T17:34:39Z","title_canon_sha256":"c2dad03edbe0bf2f6a4ade78934cdb88f7c30e5844375c396a64901b3246320d"},"schema_version":"1.0","source":{"id":"2111.10864","kind":"arxiv","version":1}},"canonical_sha256":"ce7514a664f48523e7380ae8df846f64836f9658820d4d251f86b7171f87387d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce7514a664f48523e7380ae8df846f64836f9658820d4d251f86b7171f87387d","first_computed_at":"2026-07-05T03:33:57.593245Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:33:57.593245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cg3gHUlbLWOmVZWtXOYp0iIWfLurGekfuG7kOozekxXfqRenN/seXalfXP8lMEc0PGOA9pYv9+Wbo3Bb+BmbAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:33:57.593698Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.10864","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6aa349049c47aef5115bafedff851855e175a16d9883f3ebe554ff6e6737ea1f","sha256:0639e6218bfe703a179287cb4803160ff2b4b8a3729039f853a44c422f95443b"],"state_sha256":"f4605b3870d51e08ca6d1031ab069e3c6c9b06800b599c6d9ffad0469f6d7127"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z2pJYKMbZgAV4qxIfw284pHiXDQrKAx0CCUCouUXP+C9U4m+yyhlHl6v4EtA7BU13f0yumq48HDt367Chw7aBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T06:15:59.214305Z","bundle_sha256":"504030f6cd6e4358809ce28ed09be9e76e65826fe7012162b01cf488b6c95b35"}}