{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ENJ2HTEDRDBVSMRXYTSZI4TQUB","short_pith_number":"pith:ENJ2HTED","schema_version":"1.0","canonical_sha256":"2353a3cc8388c3593237c4e5947270a040417c8c7bcb46ef8bb0c33c03e288bd","source":{"kind":"arxiv","id":"2102.10252","version":3},"attestation_state":"computed","paper":{"title":"nTreeClus: a Tree-based Sequence Encoder for Clustering Categorical Series","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hadi Jahanshahi, Mustafa Gokce Baydogan","submitted_at":"2021-02-20T03:58:17Z","abstract_excerpt":"The overwhelming presence of categorical/sequential data in diverse domains emphasizes the importance of sequence mining. The challenging nature of sequences proves the need for continuing research to find a more accurate and faster approach providing a better understanding of their (dis)similarities. This paper proposes a new Model-based approach for clustering sequence data, namely nTreeClus. The proposed method deploys Tree-based Learners, k-mers, and autoregressive models for categorical time series, culminating with a novel numerical representation of the categorical sequences. Adopting t"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2102.10252","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-20T03:58:17Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"953aa9b05e344267bcfc1fe082d7a2b43e800a4999a190c4fc30804169c6f78b","abstract_canon_sha256":"16aff8c9095208f6bb4f1c07a6702dce16b4bd9da86e2ca0a0ef5a51ffed38cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:17:02.600589Z","signature_b64":"uDOfT/7pdk/HxustQVKwFKUjURaGP+t4IbGR8ZWHdz0PKeILY9MfsK1rynVGUPPSZrMswzB7JzgvbZFJW5XoDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2353a3cc8388c3593237c4e5947270a040417c8c7bcb46ef8bb0c33c03e288bd","last_reissued_at":"2026-07-05T04:17:02.600142Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:17:02.600142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"nTreeClus: a Tree-based Sequence Encoder for Clustering Categorical Series","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hadi Jahanshahi, Mustafa Gokce Baydogan","submitted_at":"2021-02-20T03:58:17Z","abstract_excerpt":"The overwhelming presence of categorical/sequential data in diverse domains emphasizes the importance of sequence mining. The challenging nature of sequences proves the need for continuing research to find a more accurate and faster approach providing a better understanding of their (dis)similarities. This paper proposes a new Model-based approach for clustering sequence data, namely nTreeClus. The proposed method deploys Tree-based Learners, k-mers, and autoregressive models for categorical time series, culminating with a novel numerical representation of the categorical sequences. Adopting t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.10252","kind":"arxiv","version":3},"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/2102.10252/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2102.10252","created_at":"2026-07-05T04:17:02.600198+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.10252v3","created_at":"2026-07-05T04:17:02.600198+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.10252","created_at":"2026-07-05T04:17:02.600198+00:00"},{"alias_kind":"pith_short_12","alias_value":"ENJ2HTEDRDBV","created_at":"2026-07-05T04:17:02.600198+00:00"},{"alias_kind":"pith_short_16","alias_value":"ENJ2HTEDRDBVSMRX","created_at":"2026-07-05T04:17:02.600198+00:00"},{"alias_kind":"pith_short_8","alias_value":"ENJ2HTED","created_at":"2026-07-05T04:17:02.600198+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ENJ2HTEDRDBVSMRXYTSZI4TQUB","json":"https://pith.science/pith/ENJ2HTEDRDBVSMRXYTSZI4TQUB.json","graph_json":"https://pith.science/api/pith-number/ENJ2HTEDRDBVSMRXYTSZI4TQUB/graph.json","events_json":"https://pith.science/api/pith-number/ENJ2HTEDRDBVSMRXYTSZI4TQUB/events.json","paper":"https://pith.science/paper/ENJ2HTED"},"agent_actions":{"view_html":"https://pith.science/pith/ENJ2HTEDRDBVSMRXYTSZI4TQUB","download_json":"https://pith.science/pith/ENJ2HTEDRDBVSMRXYTSZI4TQUB.json","view_paper":"https://pith.science/paper/ENJ2HTED","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.10252&json=true","fetch_graph":"https://pith.science/api/pith-number/ENJ2HTEDRDBVSMRXYTSZI4TQUB/graph.json","fetch_events":"https://pith.science/api/pith-number/ENJ2HTEDRDBVSMRXYTSZI4TQUB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ENJ2HTEDRDBVSMRXYTSZI4TQUB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ENJ2HTEDRDBVSMRXYTSZI4TQUB/action/storage_attestation","attest_author":"https://pith.science/pith/ENJ2HTEDRDBVSMRXYTSZI4TQUB/action/author_attestation","sign_citation":"https://pith.science/pith/ENJ2HTEDRDBVSMRXYTSZI4TQUB/action/citation_signature","submit_replication":"https://pith.science/pith/ENJ2HTEDRDBVSMRXYTSZI4TQUB/action/replication_record"}},"created_at":"2026-07-05T04:17:02.600198+00:00","updated_at":"2026-07-05T04:17:02.600198+00:00"}