{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2013:SDA6U6QR656KJSA37GJHM6EF4E","short_pith_number":"pith:SDA6U6QR","canonical_record":{"source":{"id":"1305.3814","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2013-05-16T14:11:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0855c8c9982a7c3d11a5096c14ccab2c99c1211e6219bc117c79ec1268eae127","abstract_canon_sha256":"956133d473a206fe0675c73a2982637e2fb3d4c64e9502ec30389724b7d6b0c5"},"schema_version":"1.0"},"canonical_sha256":"90c1ea7a11f77ca4c81bf992767885e10ec253edc9ace57f2272bff0c395638c","source":{"kind":"arxiv","id":"1305.3814","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1305.3814","created_at":"2026-05-18T03:17:44Z"},{"alias_kind":"arxiv_version","alias_value":"1305.3814v2","created_at":"2026-05-18T03:17:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1305.3814","created_at":"2026-05-18T03:17:44Z"},{"alias_kind":"pith_short_12","alias_value":"SDA6U6QR656K","created_at":"2026-05-18T12:27:59Z"},{"alias_kind":"pith_short_16","alias_value":"SDA6U6QR656KJSA3","created_at":"2026-05-18T12:27:59Z"},{"alias_kind":"pith_short_8","alias_value":"SDA6U6QR","created_at":"2026-05-18T12:27:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2013:SDA6U6QR656KJSA37GJHM6EF4E","target":"record","payload":{"canonical_record":{"source":{"id":"1305.3814","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2013-05-16T14:11:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0855c8c9982a7c3d11a5096c14ccab2c99c1211e6219bc117c79ec1268eae127","abstract_canon_sha256":"956133d473a206fe0675c73a2982637e2fb3d4c64e9502ec30389724b7d6b0c5"},"schema_version":"1.0"},"canonical_sha256":"90c1ea7a11f77ca4c81bf992767885e10ec253edc9ace57f2272bff0c395638c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:17:44.167668Z","signature_b64":"EnEJdgmSC5Oa3dZU9899zrGGU8nhlLQvvfDvhQ88i1O8ipu/RpkZImIbDyWskc/vfq/raH3Eo9L5Y5pQ3fqyBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90c1ea7a11f77ca4c81bf992767885e10ec253edc9ace57f2272bff0c395638c","last_reissued_at":"2026-05-18T03:17:44.166998Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:17:44.166998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1305.3814","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":"2026-05-18T03:17:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X0y+z38kzbx2VwtAX9Sk8tdbtIn7OW9KhvmJebKLHRw4JiI/4TYjEciUTyqfTLHE9V20CYiIsZ6Yb+4wtyYcCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T12:40:28.759725Z"},"content_sha256":"432c360282c66c280dcbfae760d8955b52cf986607e9f4f940e80f11133bb2bf","schema_version":"1.0","event_id":"sha256:432c360282c66c280dcbfae760d8955b52cf986607e9f4f940e80f11133bb2bf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2013:SDA6U6QR656KJSA37GJHM6EF4E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-View Learning for Web Spam Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Ali Hadian, Behrouz Minaei-Bidgoli","submitted_at":"2013-05-16T14:11:02Z","abstract_excerpt":"Spam pages are designed to maliciously appear among the top search results by excessive usage of popular terms. Therefore, spam pages should be removed using an effective and efficient spam detection system. Previous methods for web spam classification used several features from various information sources (page contents, web graph, access logs, etc.) to detect web spam. In this paper, we follow page-level classification approach to build fast and scalable spam filters. We show that each web page can be classified with satisfiable accuracy using only its own HTML content. In order to design a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1305.3814","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":""},"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":"2026-05-18T03:17:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vv8QXck369eQKyS88l0CUiUuIqjdhWqS1Stqj2XrV8YaEoEwVPSAcRB65mZwPrQEWLBjrD0w+RAGgX/MM+IZBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T12:40:28.760076Z"},"content_sha256":"427447ecb445b89eb4ba0eb7c358093bdc215a44c2e36104de911e1e1a2c8180","schema_version":"1.0","event_id":"sha256:427447ecb445b89eb4ba0eb7c358093bdc215a44c2e36104de911e1e1a2c8180"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SDA6U6QR656KJSA37GJHM6EF4E/bundle.json","state_url":"https://pith.science/pith/SDA6U6QR656KJSA37GJHM6EF4E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SDA6U6QR656KJSA37GJHM6EF4E/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":"2026-07-01T12:40:28Z","links":{"resolver":"https://pith.science/pith/SDA6U6QR656KJSA37GJHM6EF4E","bundle":"https://pith.science/pith/SDA6U6QR656KJSA37GJHM6EF4E/bundle.json","state":"https://pith.science/pith/SDA6U6QR656KJSA37GJHM6EF4E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SDA6U6QR656KJSA37GJHM6EF4E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:SDA6U6QR656KJSA37GJHM6EF4E","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":"956133d473a206fe0675c73a2982637e2fb3d4c64e9502ec30389724b7d6b0c5","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2013-05-16T14:11:02Z","title_canon_sha256":"0855c8c9982a7c3d11a5096c14ccab2c99c1211e6219bc117c79ec1268eae127"},"schema_version":"1.0","source":{"id":"1305.3814","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1305.3814","created_at":"2026-05-18T03:17:44Z"},{"alias_kind":"arxiv_version","alias_value":"1305.3814v2","created_at":"2026-05-18T03:17:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1305.3814","created_at":"2026-05-18T03:17:44Z"},{"alias_kind":"pith_short_12","alias_value":"SDA6U6QR656K","created_at":"2026-05-18T12:27:59Z"},{"alias_kind":"pith_short_16","alias_value":"SDA6U6QR656KJSA3","created_at":"2026-05-18T12:27:59Z"},{"alias_kind":"pith_short_8","alias_value":"SDA6U6QR","created_at":"2026-05-18T12:27:59Z"}],"graph_snapshots":[{"event_id":"sha256:427447ecb445b89eb4ba0eb7c358093bdc215a44c2e36104de911e1e1a2c8180","target":"graph","created_at":"2026-05-18T03:17:44Z","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"},"paper":{"abstract_excerpt":"Spam pages are designed to maliciously appear among the top search results by excessive usage of popular terms. Therefore, spam pages should be removed using an effective and efficient spam detection system. Previous methods for web spam classification used several features from various information sources (page contents, web graph, access logs, etc.) to detect web spam. In this paper, we follow page-level classification approach to build fast and scalable spam filters. We show that each web page can be classified with satisfiable accuracy using only its own HTML content. In order to design a ","authors_text":"Ali Hadian, Behrouz Minaei-Bidgoli","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2013-05-16T14:11:02Z","title":"Multi-View Learning for Web Spam Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1305.3814","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":"sha256:432c360282c66c280dcbfae760d8955b52cf986607e9f4f940e80f11133bb2bf","target":"record","created_at":"2026-05-18T03:17:44Z","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":"956133d473a206fe0675c73a2982637e2fb3d4c64e9502ec30389724b7d6b0c5","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2013-05-16T14:11:02Z","title_canon_sha256":"0855c8c9982a7c3d11a5096c14ccab2c99c1211e6219bc117c79ec1268eae127"},"schema_version":"1.0","source":{"id":"1305.3814","kind":"arxiv","version":2}},"canonical_sha256":"90c1ea7a11f77ca4c81bf992767885e10ec253edc9ace57f2272bff0c395638c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"90c1ea7a11f77ca4c81bf992767885e10ec253edc9ace57f2272bff0c395638c","first_computed_at":"2026-05-18T03:17:44.166998Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:17:44.166998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EnEJdgmSC5Oa3dZU9899zrGGU8nhlLQvvfDvhQ88i1O8ipu/RpkZImIbDyWskc/vfq/raH3Eo9L5Y5pQ3fqyBA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:17:44.167668Z","signed_message":"canonical_sha256_bytes"},"source_id":"1305.3814","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:432c360282c66c280dcbfae760d8955b52cf986607e9f4f940e80f11133bb2bf","sha256:427447ecb445b89eb4ba0eb7c358093bdc215a44c2e36104de911e1e1a2c8180"],"state_sha256":"73fd7331054df475f35a8b71ef2042bd4e58558e6dc702f0e4509879645dda5a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NcyYp+al9N4s/BZLzMhLQgy/7DJXiS2QGd9Sl1SsGimZkUmjnjr2QFgrIkcHkhndAUFahbWiTzXLQIrIurPhCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-01T12:40:28.761975Z","bundle_sha256":"914beee15365e2e46b7ba6ffaeb5b4d5909165e8fd3a432a3a6e4f2356bd1025"}}