{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:CSDYI7FRPB5JW56NQH3VUYJN2J","short_pith_number":"pith:CSDYI7FR","canonical_record":{"source":{"id":"1210.2179","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-10-08T08:17:18Z","cross_cats_sorted":[],"title_canon_sha256":"95cf162c9d710e6244eaddb262e71a3dc99fe102e49df9847200f995b729ec6f","abstract_canon_sha256":"5cabd2ce213525b04f9eee0d8c516d4a6159261370b2aef55218da274babc323"},"schema_version":"1.0"},"canonical_sha256":"1487847cb1787a9b77cd81f75a612dd242454a72873a2f2b9c7ed8830d4d7524","source":{"kind":"arxiv","id":"1210.2179","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1210.2179","created_at":"2026-05-18T01:25:16Z"},{"alias_kind":"arxiv_version","alias_value":"1210.2179v3","created_at":"2026-05-18T01:25:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1210.2179","created_at":"2026-05-18T01:25:16Z"},{"alias_kind":"pith_short_12","alias_value":"CSDYI7FRPB5J","created_at":"2026-05-18T12:27:01Z"},{"alias_kind":"pith_short_16","alias_value":"CSDYI7FRPB5JW56N","created_at":"2026-05-18T12:27:01Z"},{"alias_kind":"pith_short_8","alias_value":"CSDYI7FR","created_at":"2026-05-18T12:27:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:CSDYI7FRPB5JW56NQH3VUYJN2J","target":"record","payload":{"canonical_record":{"source":{"id":"1210.2179","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-10-08T08:17:18Z","cross_cats_sorted":[],"title_canon_sha256":"95cf162c9d710e6244eaddb262e71a3dc99fe102e49df9847200f995b729ec6f","abstract_canon_sha256":"5cabd2ce213525b04f9eee0d8c516d4a6159261370b2aef55218da274babc323"},"schema_version":"1.0"},"canonical_sha256":"1487847cb1787a9b77cd81f75a612dd242454a72873a2f2b9c7ed8830d4d7524","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:25:16.495926Z","signature_b64":"fXz72zEP+JpuY5COoySwPQdgWh/dzwpIyO/jjP1j8kiEJC9lSWHVNggwRziYlaRpQqxPT0iWeIQtm1BuVtg8Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1487847cb1787a9b77cd81f75a612dd242454a72873a2f2b9c7ed8830d4d7524","last_reissued_at":"2026-05-18T01:25:16.495392Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:25:16.495392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1210.2179","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":"2026-05-18T01:25:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qdg9e8NFI9EhgCSzSOX1bl0xD5vWYBmFQ4zKIaeejCBgzTzPHHvSDv+2wr3I9LcOht/cNcYahJG6gHUdijtcDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T20:20:31.719658Z"},"content_sha256":"13f5ffb547dea9ddae53e89e6864ceb9a2434315c01538b805e7730e1f5af3fe","schema_version":"1.0","event_id":"sha256:13f5ffb547dea9ddae53e89e6864ceb9a2434315c01538b805e7730e1f5af3fe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:CSDYI7FRPB5JW56NQH3VUYJN2J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fast Online EM for Big Topic Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jia Zeng, Xiao-Qin Cao, Zhi-Qiang Liu","submitted_at":"2012-10-08T08:17:18Z","abstract_excerpt":"The expectation-maximization (EM) algorithm can compute the maximum-likelihood (ML) or maximum a posterior (MAP) point estimate of the mixture models or latent variable models such as latent Dirichlet allocation (LDA), which has been one of the most popular probabilistic topic modeling methods in the past decade. However, batch EM has high time and space complexities to learn big LDA models from big data streams. In this paper, we present a fast online EM (FOEM) algorithm that infers the topic distribution from the previously unseen documents incrementally with constant memory requirements. Wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1210.2179","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":""},"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":"2026-05-18T01:25:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ub3MQZ+EhzZJzfiLbRNQJwe8ZLls6DjkUuXrcNK76PCXZu+ZRLWZVzkvx6i6rgn1+BaRdrZ8Sn+SJn3/JQNjCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T20:20:31.720418Z"},"content_sha256":"9f45225a12db2564995016b1be95a8fa9eec9e20254af7314f887ee3608b954f","schema_version":"1.0","event_id":"sha256:9f45225a12db2564995016b1be95a8fa9eec9e20254af7314f887ee3608b954f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CSDYI7FRPB5JW56NQH3VUYJN2J/bundle.json","state_url":"https://pith.science/pith/CSDYI7FRPB5JW56NQH3VUYJN2J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CSDYI7FRPB5JW56NQH3VUYJN2J/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":"2026-06-07T20:20:31Z","links":{"resolver":"https://pith.science/pith/CSDYI7FRPB5JW56NQH3VUYJN2J","bundle":"https://pith.science/pith/CSDYI7FRPB5JW56NQH3VUYJN2J/bundle.json","state":"https://pith.science/pith/CSDYI7FRPB5JW56NQH3VUYJN2J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CSDYI7FRPB5JW56NQH3VUYJN2J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:CSDYI7FRPB5JW56NQH3VUYJN2J","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":"5cabd2ce213525b04f9eee0d8c516d4a6159261370b2aef55218da274babc323","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-10-08T08:17:18Z","title_canon_sha256":"95cf162c9d710e6244eaddb262e71a3dc99fe102e49df9847200f995b729ec6f"},"schema_version":"1.0","source":{"id":"1210.2179","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1210.2179","created_at":"2026-05-18T01:25:16Z"},{"alias_kind":"arxiv_version","alias_value":"1210.2179v3","created_at":"2026-05-18T01:25:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1210.2179","created_at":"2026-05-18T01:25:16Z"},{"alias_kind":"pith_short_12","alias_value":"CSDYI7FRPB5J","created_at":"2026-05-18T12:27:01Z"},{"alias_kind":"pith_short_16","alias_value":"CSDYI7FRPB5JW56N","created_at":"2026-05-18T12:27:01Z"},{"alias_kind":"pith_short_8","alias_value":"CSDYI7FR","created_at":"2026-05-18T12:27:01Z"}],"graph_snapshots":[{"event_id":"sha256:9f45225a12db2564995016b1be95a8fa9eec9e20254af7314f887ee3608b954f","target":"graph","created_at":"2026-05-18T01:25:16Z","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":"The expectation-maximization (EM) algorithm can compute the maximum-likelihood (ML) or maximum a posterior (MAP) point estimate of the mixture models or latent variable models such as latent Dirichlet allocation (LDA), which has been one of the most popular probabilistic topic modeling methods in the past decade. However, batch EM has high time and space complexities to learn big LDA models from big data streams. In this paper, we present a fast online EM (FOEM) algorithm that infers the topic distribution from the previously unseen documents incrementally with constant memory requirements. Wi","authors_text":"Jia Zeng, Xiao-Qin Cao, Zhi-Qiang Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-10-08T08:17:18Z","title":"Fast Online EM for Big Topic Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1210.2179","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":"sha256:13f5ffb547dea9ddae53e89e6864ceb9a2434315c01538b805e7730e1f5af3fe","target":"record","created_at":"2026-05-18T01:25:16Z","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":"5cabd2ce213525b04f9eee0d8c516d4a6159261370b2aef55218da274babc323","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-10-08T08:17:18Z","title_canon_sha256":"95cf162c9d710e6244eaddb262e71a3dc99fe102e49df9847200f995b729ec6f"},"schema_version":"1.0","source":{"id":"1210.2179","kind":"arxiv","version":3}},"canonical_sha256":"1487847cb1787a9b77cd81f75a612dd242454a72873a2f2b9c7ed8830d4d7524","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1487847cb1787a9b77cd81f75a612dd242454a72873a2f2b9c7ed8830d4d7524","first_computed_at":"2026-05-18T01:25:16.495392Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:25:16.495392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fXz72zEP+JpuY5COoySwPQdgWh/dzwpIyO/jjP1j8kiEJC9lSWHVNggwRziYlaRpQqxPT0iWeIQtm1BuVtg8Bg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:25:16.495926Z","signed_message":"canonical_sha256_bytes"},"source_id":"1210.2179","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:13f5ffb547dea9ddae53e89e6864ceb9a2434315c01538b805e7730e1f5af3fe","sha256:9f45225a12db2564995016b1be95a8fa9eec9e20254af7314f887ee3608b954f"],"state_sha256":"0d968c511ebbf62f6a07a0188c496a429639c4b81a4970ecb9c6fbd2e69af4ea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YSGkhvXun35/xEwOW1UIzEa20v9o5z+cCRVLhCvnmOyE2Z0sIl4r6dByHz4MbTtfSrY3zYwk0pvixymtxdYoBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T20:20:31.724112Z","bundle_sha256":"708d04f46390310decc1f8a1cf57e6cd4259cdd2a7335d2cc9c6bd9b27888289"}}