{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:X37CITNJS7VGEBMPJ2GQUZVD66","short_pith_number":"pith:X37CITNJ","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"},"canonical_sha256":"befe244da997ea62058f4e8d0a66a3f78709245469dcebb43c401efc50b8695d","source":{"kind":"arxiv","id":"1610.01858","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.01858","created_at":"2026-05-18T01:03:04Z"},{"alias_kind":"arxiv_version","alias_value":"1610.01858v1","created_at":"2026-05-18T01:03:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.01858","created_at":"2026-05-18T01:03:04Z"},{"alias_kind":"pith_short_12","alias_value":"X37CITNJS7VG","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_16","alias_value":"X37CITNJS7VGEBMP","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_8","alias_value":"X37CITNJ","created_at":"2026-05-18T12:30:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:X37CITNJS7VGEBMPJ2GQUZVD66","target":"record","payload":{"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"},"canonical_sha256":"befe244da997ea62058f4e8d0a66a3f78709245469dcebb43c401efc50b8695d","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"},"source_kind":"arxiv","source_id":"1610.01858","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":"2026-05-18T01:03:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wMkNCznKEKhSB2px6lU3VgZhKm5kspD1xoT39hwIh8JoLg9kzsLEhsBvuRV/caU99gzbhUE2nemW3JlaQIMTAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T04:37:25.868225Z"},"content_sha256":"5af9609555e303a03986e19bbba8fcbdefefb9fc5ca2eaf09f4db1e8c781af6d","schema_version":"1.0","event_id":"sha256:5af9609555e303a03986e19bbba8fcbdefefb9fc5ca2eaf09f4db1e8c781af6d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:X37CITNJS7VGEBMPJ2GQUZVD66","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:03:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PCOb79+JNDBlpilqEYBoxHG7LYFXx6k/Y9f9QQ8Qvy+LeJXzlb/cpfOtdVzrC03iCS7L+J3QrArlDuMMBoLmBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T04:37:25.868585Z"},"content_sha256":"c0afc18e07b1db820e4b4ec7215436a669016a5d4036f84d07c875b6575fc826","schema_version":"1.0","event_id":"sha256:c0afc18e07b1db820e4b4ec7215436a669016a5d4036f84d07c875b6575fc826"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X37CITNJS7VGEBMPJ2GQUZVD66/bundle.json","state_url":"https://pith.science/pith/X37CITNJS7VGEBMPJ2GQUZVD66/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X37CITNJS7VGEBMPJ2GQUZVD66/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":"2026-06-07T04:37:25Z","links":{"resolver":"https://pith.science/pith/X37CITNJS7VGEBMPJ2GQUZVD66","bundle":"https://pith.science/pith/X37CITNJS7VGEBMPJ2GQUZVD66/bundle.json","state":"https://pith.science/pith/X37CITNJS7VGEBMPJ2GQUZVD66/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X37CITNJS7VGEBMPJ2GQUZVD66/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:X37CITNJS7VGEBMPJ2GQUZVD66","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":"8117d69cf2445e7692ae65300015556f97d72afc06023610d5cf929b2f302646","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-10-06T13:20:07Z","title_canon_sha256":"c1bd2161f1bc952589ef5256e66ce8811f97dc986cc76694d42260920e726af8"},"schema_version":"1.0","source":{"id":"1610.01858","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.01858","created_at":"2026-05-18T01:03:04Z"},{"alias_kind":"arxiv_version","alias_value":"1610.01858v1","created_at":"2026-05-18T01:03:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.01858","created_at":"2026-05-18T01:03:04Z"},{"alias_kind":"pith_short_12","alias_value":"X37CITNJS7VG","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_16","alias_value":"X37CITNJS7VGEBMP","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_8","alias_value":"X37CITNJ","created_at":"2026-05-18T12:30:51Z"}],"graph_snapshots":[{"event_id":"sha256:c0afc18e07b1db820e4b4ec7215436a669016a5d4036f84d07c875b6575fc826","target":"graph","created_at":"2026-05-18T01:03:04Z","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":"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","authors_text":"Carlos Castillo, Muhammad Imran, Sanjay Chawla","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-10-06T13:20:07Z","title":"A Robust Framework for Classifying Evolving Document Streams in an Expert-Machine-Crowd Setting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.01858","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":"sha256:5af9609555e303a03986e19bbba8fcbdefefb9fc5ca2eaf09f4db1e8c781af6d","target":"record","created_at":"2026-05-18T01:03:04Z","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":"8117d69cf2445e7692ae65300015556f97d72afc06023610d5cf929b2f302646","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-10-06T13:20:07Z","title_canon_sha256":"c1bd2161f1bc952589ef5256e66ce8811f97dc986cc76694d42260920e726af8"},"schema_version":"1.0","source":{"id":"1610.01858","kind":"arxiv","version":1}},"canonical_sha256":"befe244da997ea62058f4e8d0a66a3f78709245469dcebb43c401efc50b8695d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"befe244da997ea62058f4e8d0a66a3f78709245469dcebb43c401efc50b8695d","first_computed_at":"2026-05-18T01:03:04.704688Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:03:04.704688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dXjpludY8KpvO5nSHgbB3ntjmCjYVrS4RfjyqkU/tJeHPRmlA0+9FCezJ6MZZJO1sd4D5wq41zTaWsS36Oj7AA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:03:04.705280Z","signed_message":"canonical_sha256_bytes"},"source_id":"1610.01858","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5af9609555e303a03986e19bbba8fcbdefefb9fc5ca2eaf09f4db1e8c781af6d","sha256:c0afc18e07b1db820e4b4ec7215436a669016a5d4036f84d07c875b6575fc826"],"state_sha256":"3ffc13d986a17aa5c35eb8709d30eded186e5e3d787bf5f1d19867dab791e894"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"090WfrDZnV+zMzot4bZnNPzTL5pWaaj7AGndFdUHrzuyFON00MWGTn2BJ5z+h5abLUaGBYtXGQsV/njI3FC6BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T04:37:25.870427Z","bundle_sha256":"96653a25d099dca13b621808afa3b5fe754b5b7a3ec4c3e8eabcfba39595d042"}}