{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:5FQG23R7E5MVPWIDL2Q5LE7XAY","short_pith_number":"pith:5FQG23R7","canonical_record":{"source":{"id":"2011.09887","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-19T15:18:26Z","cross_cats_sorted":[],"title_canon_sha256":"38e3a6f17ad659cd1d4c19ba3de8624d3be21eee937cce06b203d4aeed78711e","abstract_canon_sha256":"be585e2047ffe67c4c979e3386d8ce4782fc0db754405a51bd8de06bd075d32f"},"schema_version":"1.0"},"canonical_sha256":"e9606d6e3f275957d9035ea1d593f7061cb383e9d46193af9865beee46aa111f","source":{"kind":"arxiv","id":"2011.09887","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.09887","created_at":"2026-07-05T01:53:02Z"},{"alias_kind":"arxiv_version","alias_value":"2011.09887v1","created_at":"2026-07-05T01:53:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.09887","created_at":"2026-07-05T01:53:02Z"},{"alias_kind":"pith_short_12","alias_value":"5FQG23R7E5MV","created_at":"2026-07-05T01:53:02Z"},{"alias_kind":"pith_short_16","alias_value":"5FQG23R7E5MVPWID","created_at":"2026-07-05T01:53:02Z"},{"alias_kind":"pith_short_8","alias_value":"5FQG23R7","created_at":"2026-07-05T01:53:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:5FQG23R7E5MVPWIDL2Q5LE7XAY","target":"record","payload":{"canonical_record":{"source":{"id":"2011.09887","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-19T15:18:26Z","cross_cats_sorted":[],"title_canon_sha256":"38e3a6f17ad659cd1d4c19ba3de8624d3be21eee937cce06b203d4aeed78711e","abstract_canon_sha256":"be585e2047ffe67c4c979e3386d8ce4782fc0db754405a51bd8de06bd075d32f"},"schema_version":"1.0"},"canonical_sha256":"e9606d6e3f275957d9035ea1d593f7061cb383e9d46193af9865beee46aa111f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:53:02.232593Z","signature_b64":"gZG/qNTCeLZhoOdZ1LNDlSKmmurIxMHDedXs+hy19B/GMCNXmgN82DlKmZcCYYQSRndLuCLPjir9949HXgoDCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9606d6e3f275957d9035ea1d593f7061cb383e9d46193af9865beee46aa111f","last_reissued_at":"2026-07-05T01:53:02.232120Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:53:02.232120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.09887","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":"2026-07-05T01:53:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1zOGCS9512M6XJ3pybxR3o1FDXYhovMEgeiFJrWCX6aRs7NRbrRa4NGdoJIA+UTlfvB7NsErbeLSA+RoV5qAAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:23:03.929334Z"},"content_sha256":"c72ca84581452ed988043c8526978093576e3f187cd8d2fd2539ca60eb781e88","schema_version":"1.0","event_id":"sha256:c72ca84581452ed988043c8526978093576e3f187cd8d2fd2539ca60eb781e88"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:5FQG23R7E5MVPWIDL2Q5LE7XAY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Similarity-based Distance for Categorical Clustering using Space Structure","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Rahul Katarya, Shikha Asrani, Utkarsh Nath","submitted_at":"2020-11-19T15:18:26Z","abstract_excerpt":"Clustering is spotting pattern in a group of objects and resultantly grouping the similar objects together. Objects have attributes which are not always numerical, sometimes attributes have domain or categories to which they could belong to. Such data is called categorical data. To group categorical data many clustering algorithms are used, among which k- modes algorithm has so far given the most significant results. Nevertheless, there is still a lot which could be improved. Algorithms like k-means, fuzzy-c-means or hierarchical have given far better accuracies with numerical data. In this pa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.09887","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/2011.09887/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":"2026-07-05T01:53:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HZfrkO7Og8YCiWsmyvXfhuGC+qo0ma6P92sVOmELILK1yYQoT9gKWmEK/oGrF8WfCimry19jYy3+p8NOS7zsDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:23:03.929842Z"},"content_sha256":"24f040a2a13df61c96497cf3188462a67bbcbaf33251e017283cdca9cdefc0d5","schema_version":"1.0","event_id":"sha256:24f040a2a13df61c96497cf3188462a67bbcbaf33251e017283cdca9cdefc0d5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5FQG23R7E5MVPWIDL2Q5LE7XAY/bundle.json","state_url":"https://pith.science/pith/5FQG23R7E5MVPWIDL2Q5LE7XAY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5FQG23R7E5MVPWIDL2Q5LE7XAY/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":"2026-08-10T18:23:03Z","links":{"resolver":"https://pith.science/pith/5FQG23R7E5MVPWIDL2Q5LE7XAY","bundle":"https://pith.science/pith/5FQG23R7E5MVPWIDL2Q5LE7XAY/bundle.json","state":"https://pith.science/pith/5FQG23R7E5MVPWIDL2Q5LE7XAY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5FQG23R7E5MVPWIDL2Q5LE7XAY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:5FQG23R7E5MVPWIDL2Q5LE7XAY","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":"be585e2047ffe67c4c979e3386d8ce4782fc0db754405a51bd8de06bd075d32f","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-19T15:18:26Z","title_canon_sha256":"38e3a6f17ad659cd1d4c19ba3de8624d3be21eee937cce06b203d4aeed78711e"},"schema_version":"1.0","source":{"id":"2011.09887","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.09887","created_at":"2026-07-05T01:53:02Z"},{"alias_kind":"arxiv_version","alias_value":"2011.09887v1","created_at":"2026-07-05T01:53:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.09887","created_at":"2026-07-05T01:53:02Z"},{"alias_kind":"pith_short_12","alias_value":"5FQG23R7E5MV","created_at":"2026-07-05T01:53:02Z"},{"alias_kind":"pith_short_16","alias_value":"5FQG23R7E5MVPWID","created_at":"2026-07-05T01:53:02Z"},{"alias_kind":"pith_short_8","alias_value":"5FQG23R7","created_at":"2026-07-05T01:53:02Z"}],"graph_snapshots":[{"event_id":"sha256:24f040a2a13df61c96497cf3188462a67bbcbaf33251e017283cdca9cdefc0d5","target":"graph","created_at":"2026-07-05T01:53:02Z","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/2011.09887/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Clustering is spotting pattern in a group of objects and resultantly grouping the similar objects together. Objects have attributes which are not always numerical, sometimes attributes have domain or categories to which they could belong to. Such data is called categorical data. To group categorical data many clustering algorithms are used, among which k- modes algorithm has so far given the most significant results. Nevertheless, there is still a lot which could be improved. Algorithms like k-means, fuzzy-c-means or hierarchical have given far better accuracies with numerical data. In this pa","authors_text":"Rahul Katarya, Shikha Asrani, Utkarsh Nath","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-19T15:18:26Z","title":"Similarity-based Distance for Categorical Clustering using Space Structure"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.09887","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:c72ca84581452ed988043c8526978093576e3f187cd8d2fd2539ca60eb781e88","target":"record","created_at":"2026-07-05T01:53:02Z","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":"be585e2047ffe67c4c979e3386d8ce4782fc0db754405a51bd8de06bd075d32f","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-19T15:18:26Z","title_canon_sha256":"38e3a6f17ad659cd1d4c19ba3de8624d3be21eee937cce06b203d4aeed78711e"},"schema_version":"1.0","source":{"id":"2011.09887","kind":"arxiv","version":1}},"canonical_sha256":"e9606d6e3f275957d9035ea1d593f7061cb383e9d46193af9865beee46aa111f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e9606d6e3f275957d9035ea1d593f7061cb383e9d46193af9865beee46aa111f","first_computed_at":"2026-07-05T01:53:02.232120Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:53:02.232120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gZG/qNTCeLZhoOdZ1LNDlSKmmurIxMHDedXs+hy19B/GMCNXmgN82DlKmZcCYYQSRndLuCLPjir9949HXgoDCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:53:02.232593Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.09887","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c72ca84581452ed988043c8526978093576e3f187cd8d2fd2539ca60eb781e88","sha256:24f040a2a13df61c96497cf3188462a67bbcbaf33251e017283cdca9cdefc0d5"],"state_sha256":"3b308907b2c742dbd0f8f1839c8d3d71df158d66e87b2c61ab0ad0120c73216f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yos46f0QOIWWniWP81LYymFgYUcDcdzRK53tpB6Zpb0KYtWrDDbHWaKZbfGDccC2xbbYfMz9SIKJAsEl/EIcCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T18:23:03.934880Z","bundle_sha256":"7bbd6a73a44ac5b2e794d89a450c4b0efd0d536944d8f6dc850dc35fa5728212"}}