{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:X37CITNJS7VGEBMPJ2GQUZVD66","short_pith_number":"pith:X37CITNJ","schema_version":"1.0","canonical_sha256":"befe244da997ea62058f4e8d0a66a3f78709245469dcebb43c401efc50b8695d","source":{"kind":"arxiv","id":"1610.01858","version":1},"attestation_state":"computed","paper":{"title":"A Robust Framework for Classifying Evolving Document Streams in an Expert-Machine-Crowd Setting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Carlos Castillo, Muhammad Imran, Sanjay Chawla","submitted_at":"2016-10-06T13:20:07Z","abstract_excerpt":"An emerging challenge in the online classification of social media data streams is to keep the categories used for classification up-to-date. In this paper, we propose an innovative framework based on an Expert-Machine-Crowd (EMC) triad to help categorize items by continuously identifying novel concepts in heterogeneous data streams often riddled with outliers. We unify constrained clustering and outlier detection by formulating a novel optimization problem: COD-Means. We design an algorithm to solve the COD-Means problem and show that COD-Means will not only help detect novel categories but a"},"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":"1610.01858","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-10-06T13:20:07Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"c1bd2161f1bc952589ef5256e66ce8811f97dc986cc76694d42260920e726af8","abstract_canon_sha256":"8117d69cf2445e7692ae65300015556f97d72afc06023610d5cf929b2f302646"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:03:04.705280Z","signature_b64":"dXjpludY8KpvO5nSHgbB3ntjmCjYVrS4RfjyqkU/tJeHPRmlA0+9FCezJ6MZZJO1sd4D5wq41zTaWsS36Oj7AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"befe244da997ea62058f4e8d0a66a3f78709245469dcebb43c401efc50b8695d","last_reissued_at":"2026-05-18T01:03:04.704688Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:03:04.704688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Robust Framework for Classifying Evolving Document Streams in an Expert-Machine-Crowd Setting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Carlos Castillo, Muhammad Imran, Sanjay Chawla","submitted_at":"2016-10-06T13:20:07Z","abstract_excerpt":"An emerging challenge in the online classification of social media data streams is to keep the categories used for classification up-to-date. In this paper, we propose an innovative framework based on an Expert-Machine-Crowd (EMC) triad to help categorize items by continuously identifying novel concepts in heterogeneous data streams often riddled with outliers. We unify constrained clustering and outlier detection by formulating a novel optimization problem: COD-Means. We design an algorithm to solve the COD-Means problem and show that COD-Means will not only help detect novel categories but a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.01858","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1610.01858","created_at":"2026-05-18T01:03:04.704798+00:00"},{"alias_kind":"arxiv_version","alias_value":"1610.01858v1","created_at":"2026-05-18T01:03:04.704798+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.01858","created_at":"2026-05-18T01:03:04.704798+00:00"},{"alias_kind":"pith_short_12","alias_value":"X37CITNJS7VG","created_at":"2026-05-18T12:30:51.357362+00:00"},{"alias_kind":"pith_short_16","alias_value":"X37CITNJS7VGEBMP","created_at":"2026-05-18T12:30:51.357362+00:00"},{"alias_kind":"pith_short_8","alias_value":"X37CITNJ","created_at":"2026-05-18T12:30:51.357362+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/X37CITNJS7VGEBMPJ2GQUZVD66","json":"https://pith.science/pith/X37CITNJS7VGEBMPJ2GQUZVD66.json","graph_json":"https://pith.science/api/pith-number/X37CITNJS7VGEBMPJ2GQUZVD66/graph.json","events_json":"https://pith.science/api/pith-number/X37CITNJS7VGEBMPJ2GQUZVD66/events.json","paper":"https://pith.science/paper/X37CITNJ"},"agent_actions":{"view_html":"https://pith.science/pith/X37CITNJS7VGEBMPJ2GQUZVD66","download_json":"https://pith.science/pith/X37CITNJS7VGEBMPJ2GQUZVD66.json","view_paper":"https://pith.science/paper/X37CITNJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1610.01858&json=true","fetch_graph":"https://pith.science/api/pith-number/X37CITNJS7VGEBMPJ2GQUZVD66/graph.json","fetch_events":"https://pith.science/api/pith-number/X37CITNJS7VGEBMPJ2GQUZVD66/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X37CITNJS7VGEBMPJ2GQUZVD66/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X37CITNJS7VGEBMPJ2GQUZVD66/action/storage_attestation","attest_author":"https://pith.science/pith/X37CITNJS7VGEBMPJ2GQUZVD66/action/author_attestation","sign_citation":"https://pith.science/pith/X37CITNJS7VGEBMPJ2GQUZVD66/action/citation_signature","submit_replication":"https://pith.science/pith/X37CITNJS7VGEBMPJ2GQUZVD66/action/replication_record"}},"created_at":"2026-05-18T01:03:04.704798+00:00","updated_at":"2026-05-18T01:03:04.704798+00:00"}