{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ENJ2HTEDRDBVSMRXYTSZI4TQUB","short_pith_number":"pith:ENJ2HTED","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"},"canonical_sha256":"2353a3cc8388c3593237c4e5947270a040417c8c7bcb46ef8bb0c33c03e288bd","source":{"kind":"arxiv","id":"2102.10252","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.10252","created_at":"2026-07-05T04:17:02Z"},{"alias_kind":"arxiv_version","alias_value":"2102.10252v3","created_at":"2026-07-05T04:17:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.10252","created_at":"2026-07-05T04:17:02Z"},{"alias_kind":"pith_short_12","alias_value":"ENJ2HTEDRDBV","created_at":"2026-07-05T04:17:02Z"},{"alias_kind":"pith_short_16","alias_value":"ENJ2HTEDRDBVSMRX","created_at":"2026-07-05T04:17:02Z"},{"alias_kind":"pith_short_8","alias_value":"ENJ2HTED","created_at":"2026-07-05T04:17:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ENJ2HTEDRDBVSMRXYTSZI4TQUB","target":"record","payload":{"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"},"canonical_sha256":"2353a3cc8388c3593237c4e5947270a040417c8c7bcb46ef8bb0c33c03e288bd","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"},"source_kind":"arxiv","source_id":"2102.10252","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:17:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Fjfy12EZQ43pmFD0EQqlAg9Bty6ridbq/6TM8Dkte4Ue/ekUa+38MzpWUAn2OLlxSga6k0H/epC0AqIda5dDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T15:47:48.776292Z"},"content_sha256":"3fec46ccb21990b250431f004f5aa40bcaf6de14540ddfefe1da84ca6388b3cd","schema_version":"1.0","event_id":"sha256:3fec46ccb21990b250431f004f5aa40bcaf6de14540ddfefe1da84ca6388b3cd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ENJ2HTEDRDBVSMRXYTSZI4TQUB","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:17:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f4zkN53Gz63ekm7Tpvp6nHgbu1mTdGhxknEOFaVmfMEzz0bzaZhH1st673zYZ1dZTpSUOVYgY3aHV9jGJZHCAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T15:47:48.776988Z"},"content_sha256":"46943235c498c3fa3312fa81bfac0d7c8060005ee82d2928f98902dc489f01ed","schema_version":"1.0","event_id":"sha256:46943235c498c3fa3312fa81bfac0d7c8060005ee82d2928f98902dc489f01ed"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ENJ2HTEDRDBVSMRXYTSZI4TQUB/bundle.json","state_url":"https://pith.science/pith/ENJ2HTEDRDBVSMRXYTSZI4TQUB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ENJ2HTEDRDBVSMRXYTSZI4TQUB/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":"2026-07-05T15:47:48Z","links":{"resolver":"https://pith.science/pith/ENJ2HTEDRDBVSMRXYTSZI4TQUB","bundle":"https://pith.science/pith/ENJ2HTEDRDBVSMRXYTSZI4TQUB/bundle.json","state":"https://pith.science/pith/ENJ2HTEDRDBVSMRXYTSZI4TQUB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ENJ2HTEDRDBVSMRXYTSZI4TQUB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ENJ2HTEDRDBVSMRXYTSZI4TQUB","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":"16aff8c9095208f6bb4f1c07a6702dce16b4bd9da86e2ca0a0ef5a51ffed38cc","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-20T03:58:17Z","title_canon_sha256":"953aa9b05e344267bcfc1fe082d7a2b43e800a4999a190c4fc30804169c6f78b"},"schema_version":"1.0","source":{"id":"2102.10252","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.10252","created_at":"2026-07-05T04:17:02Z"},{"alias_kind":"arxiv_version","alias_value":"2102.10252v3","created_at":"2026-07-05T04:17:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.10252","created_at":"2026-07-05T04:17:02Z"},{"alias_kind":"pith_short_12","alias_value":"ENJ2HTEDRDBV","created_at":"2026-07-05T04:17:02Z"},{"alias_kind":"pith_short_16","alias_value":"ENJ2HTEDRDBVSMRX","created_at":"2026-07-05T04:17:02Z"},{"alias_kind":"pith_short_8","alias_value":"ENJ2HTED","created_at":"2026-07-05T04:17:02Z"}],"graph_snapshots":[{"event_id":"sha256:46943235c498c3fa3312fa81bfac0d7c8060005ee82d2928f98902dc489f01ed","target":"graph","created_at":"2026-07-05T04:17:02Z","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/2102.10252/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hadi Jahanshahi, Mustafa Gokce Baydogan","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-20T03:58:17Z","title":"nTreeClus: a Tree-based Sequence Encoder for Clustering Categorical Series"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.10252","kind":"arxiv","version":3},"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":"sha256:3fec46ccb21990b250431f004f5aa40bcaf6de14540ddfefe1da84ca6388b3cd","target":"record","created_at":"2026-07-05T04:17:02Z","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":"16aff8c9095208f6bb4f1c07a6702dce16b4bd9da86e2ca0a0ef5a51ffed38cc","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-20T03:58:17Z","title_canon_sha256":"953aa9b05e344267bcfc1fe082d7a2b43e800a4999a190c4fc30804169c6f78b"},"schema_version":"1.0","source":{"id":"2102.10252","kind":"arxiv","version":3}},"canonical_sha256":"2353a3cc8388c3593237c4e5947270a040417c8c7bcb46ef8bb0c33c03e288bd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2353a3cc8388c3593237c4e5947270a040417c8c7bcb46ef8bb0c33c03e288bd","first_computed_at":"2026-07-05T04:17:02.600142Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:17:02.600142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uDOfT/7pdk/HxustQVKwFKUjURaGP+t4IbGR8ZWHdz0PKeILY9MfsK1rynVGUPPSZrMswzB7JzgvbZFJW5XoDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:17:02.600589Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.10252","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3fec46ccb21990b250431f004f5aa40bcaf6de14540ddfefe1da84ca6388b3cd","sha256:46943235c498c3fa3312fa81bfac0d7c8060005ee82d2928f98902dc489f01ed"],"state_sha256":"e5f44a36967e23fc504400b32be544b77e256bb3099833bd11b4060802e31bdf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K7L9AXAqMQ+QnwwP7Sai3Dubcy0SetND4NcBVKJ4n43PxLFfWKVGMtrsZCUuSKA3iYrLlsQIGZeJI+wRB7iMCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T15:47:48.780719Z","bundle_sha256":"1e5c305e7cdf060c9abd2fb9fad427bd53824c41d8c799405898c901810cf312"}}