{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:5BI3FN3MGG2NAD4UHQMYIMJQWR","short_pith_number":"pith:5BI3FN3M","canonical_record":{"source":{"id":"1810.03099","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-10-07T08:04:18Z","cross_cats_sorted":[],"title_canon_sha256":"dee77027d55ce9e92aca1aca4abb9aa5c5a2f8e388af3519f388ae26d7fdc9c3","abstract_canon_sha256":"7693c4497b254ffd1ce67eab510c9b3bba9373f4178f335b8e0759dd2fcde37c"},"schema_version":"1.0"},"canonical_sha256":"e851b2b76c31b4d00f943c19843130b46ca06f04fd0731dd11908a4a580493cf","source":{"kind":"arxiv","id":"1810.03099","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.03099","created_at":"2026-05-18T00:03:54Z"},{"alias_kind":"arxiv_version","alias_value":"1810.03099v1","created_at":"2026-05-18T00:03:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.03099","created_at":"2026-05-18T00:03:54Z"},{"alias_kind":"pith_short_12","alias_value":"5BI3FN3MGG2N","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5BI3FN3MGG2NAD4U","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5BI3FN3M","created_at":"2026-05-18T12:32:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:5BI3FN3MGG2NAD4UHQMYIMJQWR","target":"record","payload":{"canonical_record":{"source":{"id":"1810.03099","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-10-07T08:04:18Z","cross_cats_sorted":[],"title_canon_sha256":"dee77027d55ce9e92aca1aca4abb9aa5c5a2f8e388af3519f388ae26d7fdc9c3","abstract_canon_sha256":"7693c4497b254ffd1ce67eab510c9b3bba9373f4178f335b8e0759dd2fcde37c"},"schema_version":"1.0"},"canonical_sha256":"e851b2b76c31b4d00f943c19843130b46ca06f04fd0731dd11908a4a580493cf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:54.522689Z","signature_b64":"L/erTI3GKKj4xfh3oJm1aR9saNpHmMH7IQXF+ZPlPllCzpgkVQ5PSI5UQgr7taBrDenhYM2lM6QHblwKt1wyBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e851b2b76c31b4d00f943c19843130b46ca06f04fd0731dd11908a4a580493cf","last_reissued_at":"2026-05-18T00:03:54.522068Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:54.522068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.03099","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":"2026-05-18T00:03:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uhonOpf9d8hKsi71affcvdgeyedKgdE8HKA2CsWDzr/dtzS7evbihUSb9AFpfyJ4R9juqGCxfBntXqwLPiEMCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T09:39:29.348953Z"},"content_sha256":"7a99cf08d3911bf4e3d22f056f9e6ab721083d780ff1d094efac30815518b1f3","schema_version":"1.0","event_id":"sha256:7a99cf08d3911bf4e3d22f056f9e6ab721083d780ff1d094efac30815518b1f3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:5BI3FN3MGG2NAD4UHQMYIMJQWR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-reference Cosine: A New Approach to Text Similarity Measurement in Large Collections","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Amin Nikoukaran, Hamid Mohammadi","submitted_at":"2018-10-07T08:04:18Z","abstract_excerpt":"The importance of an efficient and scalable document similarity detection system is undeniable nowadays. Search engines need batch text similarity measures to detect duplicated and near-duplicated web pages in their indexes in order to prevent indexing a web page multiple times. Furthermore, in the scoring phase, search engines need similarity measures to detect duplicated contents on web pages so as to increase the quality of their results. In this paper, a new approach to batch text similarity detection is proposed by combining some ideas from dimensionality reduction techniques and informat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.03099","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":""},"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":"2026-05-18T00:03:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"82K77XFYPH+YmssVOu0ERT/qyOA9UTCz7KoMQYU3ytX5JcbqRHg7fULIIQNRcIhm1F3KpAPy6eCiX6bIcxj6DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T09:39:29.349299Z"},"content_sha256":"c28df0c9ba8f6068f0e885428f38663b371802f99c2939711b6158f32319ba14","schema_version":"1.0","event_id":"sha256:c28df0c9ba8f6068f0e885428f38663b371802f99c2939711b6158f32319ba14"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5BI3FN3MGG2NAD4UHQMYIMJQWR/bundle.json","state_url":"https://pith.science/pith/5BI3FN3MGG2NAD4UHQMYIMJQWR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5BI3FN3MGG2NAD4UHQMYIMJQWR/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":"2026-07-18T09:39:29Z","links":{"resolver":"https://pith.science/pith/5BI3FN3MGG2NAD4UHQMYIMJQWR","bundle":"https://pith.science/pith/5BI3FN3MGG2NAD4UHQMYIMJQWR/bundle.json","state":"https://pith.science/pith/5BI3FN3MGG2NAD4UHQMYIMJQWR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5BI3FN3MGG2NAD4UHQMYIMJQWR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:5BI3FN3MGG2NAD4UHQMYIMJQWR","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":"7693c4497b254ffd1ce67eab510c9b3bba9373f4178f335b8e0759dd2fcde37c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-10-07T08:04:18Z","title_canon_sha256":"dee77027d55ce9e92aca1aca4abb9aa5c5a2f8e388af3519f388ae26d7fdc9c3"},"schema_version":"1.0","source":{"id":"1810.03099","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.03099","created_at":"2026-05-18T00:03:54Z"},{"alias_kind":"arxiv_version","alias_value":"1810.03099v1","created_at":"2026-05-18T00:03:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.03099","created_at":"2026-05-18T00:03:54Z"},{"alias_kind":"pith_short_12","alias_value":"5BI3FN3MGG2N","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5BI3FN3MGG2NAD4U","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5BI3FN3M","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:c28df0c9ba8f6068f0e885428f38663b371802f99c2939711b6158f32319ba14","target":"graph","created_at":"2026-05-18T00:03:54Z","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":"The importance of an efficient and scalable document similarity detection system is undeniable nowadays. Search engines need batch text similarity measures to detect duplicated and near-duplicated web pages in their indexes in order to prevent indexing a web page multiple times. Furthermore, in the scoring phase, search engines need similarity measures to detect duplicated contents on web pages so as to increase the quality of their results. In this paper, a new approach to batch text similarity detection is proposed by combining some ideas from dimensionality reduction techniques and informat","authors_text":"Amin Nikoukaran, Hamid Mohammadi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-10-07T08:04:18Z","title":"Multi-reference Cosine: A New Approach to Text Similarity Measurement in Large Collections"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.03099","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":"sha256:7a99cf08d3911bf4e3d22f056f9e6ab721083d780ff1d094efac30815518b1f3","target":"record","created_at":"2026-05-18T00:03:54Z","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":"7693c4497b254ffd1ce67eab510c9b3bba9373f4178f335b8e0759dd2fcde37c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-10-07T08:04:18Z","title_canon_sha256":"dee77027d55ce9e92aca1aca4abb9aa5c5a2f8e388af3519f388ae26d7fdc9c3"},"schema_version":"1.0","source":{"id":"1810.03099","kind":"arxiv","version":1}},"canonical_sha256":"e851b2b76c31b4d00f943c19843130b46ca06f04fd0731dd11908a4a580493cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e851b2b76c31b4d00f943c19843130b46ca06f04fd0731dd11908a4a580493cf","first_computed_at":"2026-05-18T00:03:54.522068Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:03:54.522068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L/erTI3GKKj4xfh3oJm1aR9saNpHmMH7IQXF+ZPlPllCzpgkVQ5PSI5UQgr7taBrDenhYM2lM6QHblwKt1wyBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:03:54.522689Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.03099","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a99cf08d3911bf4e3d22f056f9e6ab721083d780ff1d094efac30815518b1f3","sha256:c28df0c9ba8f6068f0e885428f38663b371802f99c2939711b6158f32319ba14"],"state_sha256":"32540d5d5a48cf5711cfa2a031363cfaec5d6f6936654c46676a7d0f16530912"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dOxnTLWiUn0/npKFNDxEgiKmrZ5Ax101AetiJEbvju9AOV/tRxWDjKcAX8TbgJw47nEIAK2pdmAm9YW6WHPsCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-18T09:39:29.351825Z","bundle_sha256":"a4c5680a6231ea616c66e42985ebc07d1a85e28d024eb58d46e471bfb2424338"}}