{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:6DWMN2SRMKKMZELODRMKKILTZY","short_pith_number":"pith:6DWMN2SR","canonical_record":{"source":{"id":"1711.08797","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-23T18:27:37Z","cross_cats_sorted":["cs.DS","cs.LG"],"title_canon_sha256":"fa39a2fc81350510ae7e693c3affda2cfa2584a3a5b16ec654659b17733ee624","abstract_canon_sha256":"a51a9fb2a8bd867231cdca1b7d18589f0e012f3167080745b5936d12f530820c"},"schema_version":"1.0"},"canonical_sha256":"f0ecc6ea516294cc916e1c58a52173ce19f28fe5d29d02b54ade06d963dd59a3","source":{"kind":"arxiv","id":"1711.08797","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.08797","created_at":"2026-05-18T00:29:44Z"},{"alias_kind":"arxiv_version","alias_value":"1711.08797v1","created_at":"2026-05-18T00:29:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.08797","created_at":"2026-05-18T00:29:44Z"},{"alias_kind":"pith_short_12","alias_value":"6DWMN2SRMKKM","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"6DWMN2SRMKKMZELO","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"6DWMN2SR","created_at":"2026-05-18T12:31:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:6DWMN2SRMKKMZELODRMKKILTZY","target":"record","payload":{"canonical_record":{"source":{"id":"1711.08797","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-23T18:27:37Z","cross_cats_sorted":["cs.DS","cs.LG"],"title_canon_sha256":"fa39a2fc81350510ae7e693c3affda2cfa2584a3a5b16ec654659b17733ee624","abstract_canon_sha256":"a51a9fb2a8bd867231cdca1b7d18589f0e012f3167080745b5936d12f530820c"},"schema_version":"1.0"},"canonical_sha256":"f0ecc6ea516294cc916e1c58a52173ce19f28fe5d29d02b54ade06d963dd59a3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:44.066689Z","signature_b64":"SrExzIoYgbdfeYHxmvnME4NdeR0j7YUZw7kXKTCVgw2VM9VPdLGTOYHlwcrbNSn6aXLZDuUSgZGK+jsu8AvoBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0ecc6ea516294cc916e1c58a52173ce19f28fe5d29d02b54ade06d963dd59a3","last_reissued_at":"2026-05-18T00:29:44.066256Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:44.066256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1711.08797","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":"2026-05-18T00:29:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wFyV0lHkm/EJkBwm798QVZA2VOjrFCwoljys3YBicuBGmotW9zkP4KT3CwcJPDJlUiK4rw5O2ewaR2OhT3hWCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T05:08:53.228821Z"},"content_sha256":"f071da5afd5032de335a2ee9612729a5480e1704a4b9ca6ade6340b7525b7ce7","schema_version":"1.0","event_id":"sha256:f071da5afd5032de335a2ee9612729a5480e1704a4b9ca6ade6340b7525b7ce7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:6DWMN2SRMKKMZELODRMKKILTZY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Practical Hash Functions for Similarity Estimation and Dimensionality Reduction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","cs.LG"],"primary_cat":"stat.ML","authors_text":"Mathias B{\\ae}k Tejs Knudsen, Mikkel Thorup, S{\\o}ren Dahlgaard","submitted_at":"2017-11-23T18:27:37Z","abstract_excerpt":"Hashing is a basic tool for dimensionality reduction employed in several aspects of machine learning. However, the perfomance analysis is often carried out under the abstract assumption that a truly random unit cost hash function is used, without concern for which concrete hash function is employed. The concrete hash function may work fine on sufficiently random input. The question is if it can be trusted in the real world when faced with more structured input.\n  In this paper we focus on two prominent applications of hashing, namely similarity estimation with the one permutation hashing (OPH)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.08797","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":"2026-05-18T00:29:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rHK6tvSH4sP4Un6zHnd+ip3Acf5Nc3YwHRrmSgHVt2QbtK1erx0CIVkTZ8mGODtj/7N152IWMclcqOxVXw1IDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T05:08:53.229162Z"},"content_sha256":"12361e9cada46a14777a128e2e4110cf32fc456dc9b4f2ab1d4f42e6988969f1","schema_version":"1.0","event_id":"sha256:12361e9cada46a14777a128e2e4110cf32fc456dc9b4f2ab1d4f42e6988969f1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6DWMN2SRMKKMZELODRMKKILTZY/bundle.json","state_url":"https://pith.science/pith/6DWMN2SRMKKMZELODRMKKILTZY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6DWMN2SRMKKMZELODRMKKILTZY/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":"2026-06-27T05:08:53Z","links":{"resolver":"https://pith.science/pith/6DWMN2SRMKKMZELODRMKKILTZY","bundle":"https://pith.science/pith/6DWMN2SRMKKMZELODRMKKILTZY/bundle.json","state":"https://pith.science/pith/6DWMN2SRMKKMZELODRMKKILTZY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6DWMN2SRMKKMZELODRMKKILTZY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:6DWMN2SRMKKMZELODRMKKILTZY","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":"a51a9fb2a8bd867231cdca1b7d18589f0e012f3167080745b5936d12f530820c","cross_cats_sorted":["cs.DS","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-23T18:27:37Z","title_canon_sha256":"fa39a2fc81350510ae7e693c3affda2cfa2584a3a5b16ec654659b17733ee624"},"schema_version":"1.0","source":{"id":"1711.08797","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.08797","created_at":"2026-05-18T00:29:44Z"},{"alias_kind":"arxiv_version","alias_value":"1711.08797v1","created_at":"2026-05-18T00:29:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.08797","created_at":"2026-05-18T00:29:44Z"},{"alias_kind":"pith_short_12","alias_value":"6DWMN2SRMKKM","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"6DWMN2SRMKKMZELO","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"6DWMN2SR","created_at":"2026-05-18T12:31:03Z"}],"graph_snapshots":[{"event_id":"sha256:12361e9cada46a14777a128e2e4110cf32fc456dc9b4f2ab1d4f42e6988969f1","target":"graph","created_at":"2026-05-18T00:29:44Z","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":"Hashing is a basic tool for dimensionality reduction employed in several aspects of machine learning. However, the perfomance analysis is often carried out under the abstract assumption that a truly random unit cost hash function is used, without concern for which concrete hash function is employed. The concrete hash function may work fine on sufficiently random input. The question is if it can be trusted in the real world when faced with more structured input.\n  In this paper we focus on two prominent applications of hashing, namely similarity estimation with the one permutation hashing (OPH)","authors_text":"Mathias B{\\ae}k Tejs Knudsen, Mikkel Thorup, S{\\o}ren Dahlgaard","cross_cats":["cs.DS","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-23T18:27:37Z","title":"Practical Hash Functions for Similarity Estimation and Dimensionality Reduction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.08797","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:f071da5afd5032de335a2ee9612729a5480e1704a4b9ca6ade6340b7525b7ce7","target":"record","created_at":"2026-05-18T00:29:44Z","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":"a51a9fb2a8bd867231cdca1b7d18589f0e012f3167080745b5936d12f530820c","cross_cats_sorted":["cs.DS","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-23T18:27:37Z","title_canon_sha256":"fa39a2fc81350510ae7e693c3affda2cfa2584a3a5b16ec654659b17733ee624"},"schema_version":"1.0","source":{"id":"1711.08797","kind":"arxiv","version":1}},"canonical_sha256":"f0ecc6ea516294cc916e1c58a52173ce19f28fe5d29d02b54ade06d963dd59a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f0ecc6ea516294cc916e1c58a52173ce19f28fe5d29d02b54ade06d963dd59a3","first_computed_at":"2026-05-18T00:29:44.066256Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:29:44.066256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SrExzIoYgbdfeYHxmvnME4NdeR0j7YUZw7kXKTCVgw2VM9VPdLGTOYHlwcrbNSn6aXLZDuUSgZGK+jsu8AvoBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:29:44.066689Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.08797","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f071da5afd5032de335a2ee9612729a5480e1704a4b9ca6ade6340b7525b7ce7","sha256:12361e9cada46a14777a128e2e4110cf32fc456dc9b4f2ab1d4f42e6988969f1"],"state_sha256":"958e03c2cc6c5275cadcbee71fb0c1e93ec81834de2d6c8a111dfe22918e55f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PN3v+wZ68L2iWI0SNkuWxJWvYOsZv8IzeZdVoDhq7dfnmqDSDrXEzsh0vCCfE23+BNH3SBOCxmetgLCo1r37CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T05:08:53.231005Z","bundle_sha256":"7a2cac1b6c6f191604b60bc471adec5daeaee160fea02f61cd32e30d25e604c2"}}