{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2011:IUM3SKSMF7UYSGEFHM2TLHPB7T","short_pith_number":"pith:IUM3SKSM","canonical_record":{"source":{"id":"1107.3765","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-07-19T16:32:22Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"347c16a48beffc7b2e9435231480599cf453fd7e66c7259a0226a27ee7511631","abstract_canon_sha256":"a81fe3af9005b3aa5e699d5770397eba286666a261da9903e25c4522c29495bd"},"schema_version":"1.0"},"canonical_sha256":"4519b92a4c2fe98918853b35359de1fcc49693aec1ecba4383ca69ad9b0e6d36","source":{"kind":"arxiv","id":"1107.3765","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1107.3765","created_at":"2026-05-18T04:17:16Z"},{"alias_kind":"arxiv_version","alias_value":"1107.3765v1","created_at":"2026-05-18T04:17:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1107.3765","created_at":"2026-05-18T04:17:16Z"},{"alias_kind":"pith_short_12","alias_value":"IUM3SKSMF7UY","created_at":"2026-05-18T12:26:32Z"},{"alias_kind":"pith_short_16","alias_value":"IUM3SKSMF7UYSGEF","created_at":"2026-05-18T12:26:32Z"},{"alias_kind":"pith_short_8","alias_value":"IUM3SKSM","created_at":"2026-05-18T12:26:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2011:IUM3SKSMF7UYSGEFHM2TLHPB7T","target":"record","payload":{"canonical_record":{"source":{"id":"1107.3765","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-07-19T16:32:22Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"347c16a48beffc7b2e9435231480599cf453fd7e66c7259a0226a27ee7511631","abstract_canon_sha256":"a81fe3af9005b3aa5e699d5770397eba286666a261da9903e25c4522c29495bd"},"schema_version":"1.0"},"canonical_sha256":"4519b92a4c2fe98918853b35359de1fcc49693aec1ecba4383ca69ad9b0e6d36","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:17:16.033275Z","signature_b64":"zLR2DJvOvqORurR8I0R9CsX3WNparuHP2H22x+xqaZWzkcH9e/SgoeJyzRCMzd5+VkSB4gakCuuswcMWs4rHDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4519b92a4c2fe98918853b35359de1fcc49693aec1ecba4383ca69ad9b0e6d36","last_reissued_at":"2026-05-18T04:17:16.032620Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:17:16.032620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1107.3765","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":"2026-05-18T04:17:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WHE4JzuinxqrYQz4uqL36M2G3Q5maXDueUlM0CSnm2IoTPXaIFu9CdEIFHbX/iyZ7kc1VMN55uGk9EZSu+yQCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T00:58:35.793375Z"},"content_sha256":"30ae1fc2c10df6bf621dfc7fcc52150008ba8a7421339802891f31f1a269fde3","schema_version":"1.0","event_id":"sha256:30ae1fc2c10df6bf621dfc7fcc52150008ba8a7421339802891f31f1a269fde3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2011:IUM3SKSMF7UYSGEFHM2TLHPB7T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Using Variational Inference and MapReduce to Scale Topic Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.AI","authors_text":"Jordan Boyd-Graber, Ke Zhai, Nima Asadi","submitted_at":"2011-07-19T16:32:22Z","abstract_excerpt":"Latent Dirichlet Allocation (LDA) is a popular topic modeling technique for exploring document collections. Because of the increasing prevalence of large datasets, there is a need to improve the scalability of inference of LDA. In this paper, we propose a technique called ~\\emph{MapReduce LDA} (Mr. LDA) to accommodate very large corpus collections in the MapReduce framework. In contrast to other techniques to scale inference for LDA, which use Gibbs sampling, we use variational inference. Our solution efficiently distributes computation and is relatively simple to implement. More importantly, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1107.3765","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":"2026-05-18T04:17:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wxgj1kDDkFpN3tSq2/UvlahydfOQ1b6YUMHkKhw4AX6cSRH4lmbbQitYToONWDsyJldfG4reRN2m1i8NbOnLDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T00:58:35.793735Z"},"content_sha256":"9e183b1c7cccc1c2c9c4bfcc4fec41ac8ce1f3588211a3d41ae51db06e330a2c","schema_version":"1.0","event_id":"sha256:9e183b1c7cccc1c2c9c4bfcc4fec41ac8ce1f3588211a3d41ae51db06e330a2c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IUM3SKSMF7UYSGEFHM2TLHPB7T/bundle.json","state_url":"https://pith.science/pith/IUM3SKSMF7UYSGEFHM2TLHPB7T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IUM3SKSMF7UYSGEFHM2TLHPB7T/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":"2026-06-03T00:58:35Z","links":{"resolver":"https://pith.science/pith/IUM3SKSMF7UYSGEFHM2TLHPB7T","bundle":"https://pith.science/pith/IUM3SKSMF7UYSGEFHM2TLHPB7T/bundle.json","state":"https://pith.science/pith/IUM3SKSMF7UYSGEFHM2TLHPB7T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IUM3SKSMF7UYSGEFHM2TLHPB7T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2011:IUM3SKSMF7UYSGEFHM2TLHPB7T","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":"a81fe3af9005b3aa5e699d5770397eba286666a261da9903e25c4522c29495bd","cross_cats_sorted":["cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-07-19T16:32:22Z","title_canon_sha256":"347c16a48beffc7b2e9435231480599cf453fd7e66c7259a0226a27ee7511631"},"schema_version":"1.0","source":{"id":"1107.3765","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1107.3765","created_at":"2026-05-18T04:17:16Z"},{"alias_kind":"arxiv_version","alias_value":"1107.3765v1","created_at":"2026-05-18T04:17:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1107.3765","created_at":"2026-05-18T04:17:16Z"},{"alias_kind":"pith_short_12","alias_value":"IUM3SKSMF7UY","created_at":"2026-05-18T12:26:32Z"},{"alias_kind":"pith_short_16","alias_value":"IUM3SKSMF7UYSGEF","created_at":"2026-05-18T12:26:32Z"},{"alias_kind":"pith_short_8","alias_value":"IUM3SKSM","created_at":"2026-05-18T12:26:32Z"}],"graph_snapshots":[{"event_id":"sha256:9e183b1c7cccc1c2c9c4bfcc4fec41ac8ce1f3588211a3d41ae51db06e330a2c","target":"graph","created_at":"2026-05-18T04:17:16Z","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":"Latent Dirichlet Allocation (LDA) is a popular topic modeling technique for exploring document collections. Because of the increasing prevalence of large datasets, there is a need to improve the scalability of inference of LDA. In this paper, we propose a technique called ~\\emph{MapReduce LDA} (Mr. LDA) to accommodate very large corpus collections in the MapReduce framework. In contrast to other techniques to scale inference for LDA, which use Gibbs sampling, we use variational inference. Our solution efficiently distributes computation and is relatively simple to implement. More importantly, ","authors_text":"Jordan Boyd-Graber, Ke Zhai, Nima Asadi","cross_cats":["cs.DC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-07-19T16:32:22Z","title":"Using Variational Inference and MapReduce to Scale Topic Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1107.3765","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":"sha256:30ae1fc2c10df6bf621dfc7fcc52150008ba8a7421339802891f31f1a269fde3","target":"record","created_at":"2026-05-18T04:17:16Z","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":"a81fe3af9005b3aa5e699d5770397eba286666a261da9903e25c4522c29495bd","cross_cats_sorted":["cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-07-19T16:32:22Z","title_canon_sha256":"347c16a48beffc7b2e9435231480599cf453fd7e66c7259a0226a27ee7511631"},"schema_version":"1.0","source":{"id":"1107.3765","kind":"arxiv","version":1}},"canonical_sha256":"4519b92a4c2fe98918853b35359de1fcc49693aec1ecba4383ca69ad9b0e6d36","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4519b92a4c2fe98918853b35359de1fcc49693aec1ecba4383ca69ad9b0e6d36","first_computed_at":"2026-05-18T04:17:16.032620Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:17:16.032620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zLR2DJvOvqORurR8I0R9CsX3WNparuHP2H22x+xqaZWzkcH9e/SgoeJyzRCMzd5+VkSB4gakCuuswcMWs4rHDw==","signature_status":"signed_v1","signed_at":"2026-05-18T04:17:16.033275Z","signed_message":"canonical_sha256_bytes"},"source_id":"1107.3765","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:30ae1fc2c10df6bf621dfc7fcc52150008ba8a7421339802891f31f1a269fde3","sha256:9e183b1c7cccc1c2c9c4bfcc4fec41ac8ce1f3588211a3d41ae51db06e330a2c"],"state_sha256":"edf864c298714b87746eaa3a5e5118059f68d111ed3a7acda9ecc84736769eda"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H7eFgBhl5Sm+NnyqgSRk70fKCxCurEsPRyYq16pcANb+ps3V6jmOZTDPwlqAUCQydstrMIYMu9t8dBnWFiTSCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T00:58:35.795619Z","bundle_sha256":"df1a5ee6247ee19fa4ea15ff41864b4221179dbed94b8eadca2cde878dd05219"}}