{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:BKYAR7RGCFPOT3TWFJYJOUKBHL","short_pith_number":"pith:BKYAR7RG","canonical_record":{"source":{"id":"1605.02019","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-05-06T18:13:18Z","cross_cats_sorted":[],"title_canon_sha256":"879d3f489dd8f30db64f90012820e9da5b27bdf10638aeeba34565c3156242e8","abstract_canon_sha256":"aed6eef07c18217770effc053c82c15b85c4b6fc0517d7ec747995138585cc39"},"schema_version":"1.0"},"canonical_sha256":"0ab008fe26115ee9ee762a709751413ae72ae869fae480572512e170669a1ebb","source":{"kind":"arxiv","id":"1605.02019","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.02019","created_at":"2026-05-18T01:15:30Z"},{"alias_kind":"arxiv_version","alias_value":"1605.02019v1","created_at":"2026-05-18T01:15:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.02019","created_at":"2026-05-18T01:15:30Z"},{"alias_kind":"pith_short_12","alias_value":"BKYAR7RGCFPO","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_16","alias_value":"BKYAR7RGCFPOT3TW","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_8","alias_value":"BKYAR7RG","created_at":"2026-05-18T12:30:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:BKYAR7RGCFPOT3TWFJYJOUKBHL","target":"record","payload":{"canonical_record":{"source":{"id":"1605.02019","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-05-06T18:13:18Z","cross_cats_sorted":[],"title_canon_sha256":"879d3f489dd8f30db64f90012820e9da5b27bdf10638aeeba34565c3156242e8","abstract_canon_sha256":"aed6eef07c18217770effc053c82c15b85c4b6fc0517d7ec747995138585cc39"},"schema_version":"1.0"},"canonical_sha256":"0ab008fe26115ee9ee762a709751413ae72ae869fae480572512e170669a1ebb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:15:30.626443Z","signature_b64":"bjtJ90iDHRhDo49byHjJHmV0aeHaii+gZn49jM8HwE0KI1AvR3kgbJNOTz3qLT1BeSx0WcSeVWDNiJZ7s2SvDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ab008fe26115ee9ee762a709751413ae72ae869fae480572512e170669a1ebb","last_reissued_at":"2026-05-18T01:15:30.625755Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:15:30.625755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1605.02019","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":"2026-05-18T01:15:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0Zc2veA8yvV8Q8o4zpBAc7MZFlJcPS1fpBTNVYXxNIhcELGef/LgrL8fBwFiIQ7sdIVE3SDQC7GA+6EvujRiAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T16:04:29.002210Z"},"content_sha256":"b15111b5f7153ff7bbee9968346f820bb4efd641c9e1efd151e35ef2bf384e28","schema_version":"1.0","event_id":"sha256:b15111b5f7153ff7bbee9968346f820bb4efd641c9e1efd151e35ef2bf384e28"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:BKYAR7RGCFPOT3TWFJYJOUKBHL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mixing Dirichlet Topic Models and Word Embeddings to Make lda2vec","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christopher E Moody","submitted_at":"2016-05-06T18:13:18Z","abstract_excerpt":"Distributed dense word vectors have been shown to be effective at capturing token-level semantic and syntactic regularities in language, while topic models can form interpretable representations over documents. In this work, we describe lda2vec, a model that learns dense word vectors jointly with Dirichlet-distributed latent document-level mixtures of topic vectors. In contrast to continuous dense document representations, this formulation produces sparse, interpretable document mixtures through a non-negative simplex constraint. Our method is simple to incorporate into existing automatic diff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.02019","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":"2026-05-18T01:15:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IY8JMg7kGUoXIP/m8qojq5aLdjb9mfobamyM0nwQKTmFPLMkq8U/rFKVKjPkwz3kBQm1elBa8Qb8YO1YmdpiBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T16:04:29.002722Z"},"content_sha256":"e714696095aac5fad2883d37d27153bdcc7970e6eb54866b09eb5b9079277309","schema_version":"1.0","event_id":"sha256:e714696095aac5fad2883d37d27153bdcc7970e6eb54866b09eb5b9079277309"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BKYAR7RGCFPOT3TWFJYJOUKBHL/bundle.json","state_url":"https://pith.science/pith/BKYAR7RGCFPOT3TWFJYJOUKBHL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BKYAR7RGCFPOT3TWFJYJOUKBHL/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":"2026-05-25T16:04:29Z","links":{"resolver":"https://pith.science/pith/BKYAR7RGCFPOT3TWFJYJOUKBHL","bundle":"https://pith.science/pith/BKYAR7RGCFPOT3TWFJYJOUKBHL/bundle.json","state":"https://pith.science/pith/BKYAR7RGCFPOT3TWFJYJOUKBHL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BKYAR7RGCFPOT3TWFJYJOUKBHL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:BKYAR7RGCFPOT3TWFJYJOUKBHL","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":"aed6eef07c18217770effc053c82c15b85c4b6fc0517d7ec747995138585cc39","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-05-06T18:13:18Z","title_canon_sha256":"879d3f489dd8f30db64f90012820e9da5b27bdf10638aeeba34565c3156242e8"},"schema_version":"1.0","source":{"id":"1605.02019","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.02019","created_at":"2026-05-18T01:15:30Z"},{"alias_kind":"arxiv_version","alias_value":"1605.02019v1","created_at":"2026-05-18T01:15:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.02019","created_at":"2026-05-18T01:15:30Z"},{"alias_kind":"pith_short_12","alias_value":"BKYAR7RGCFPO","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_16","alias_value":"BKYAR7RGCFPOT3TW","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_8","alias_value":"BKYAR7RG","created_at":"2026-05-18T12:30:07Z"}],"graph_snapshots":[{"event_id":"sha256:e714696095aac5fad2883d37d27153bdcc7970e6eb54866b09eb5b9079277309","target":"graph","created_at":"2026-05-18T01:15:30Z","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":"Distributed dense word vectors have been shown to be effective at capturing token-level semantic and syntactic regularities in language, while topic models can form interpretable representations over documents. In this work, we describe lda2vec, a model that learns dense word vectors jointly with Dirichlet-distributed latent document-level mixtures of topic vectors. In contrast to continuous dense document representations, this formulation produces sparse, interpretable document mixtures through a non-negative simplex constraint. Our method is simple to incorporate into existing automatic diff","authors_text":"Christopher E Moody","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-05-06T18:13:18Z","title":"Mixing Dirichlet Topic Models and Word Embeddings to Make lda2vec"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.02019","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:b15111b5f7153ff7bbee9968346f820bb4efd641c9e1efd151e35ef2bf384e28","target":"record","created_at":"2026-05-18T01:15:30Z","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":"aed6eef07c18217770effc053c82c15b85c4b6fc0517d7ec747995138585cc39","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-05-06T18:13:18Z","title_canon_sha256":"879d3f489dd8f30db64f90012820e9da5b27bdf10638aeeba34565c3156242e8"},"schema_version":"1.0","source":{"id":"1605.02019","kind":"arxiv","version":1}},"canonical_sha256":"0ab008fe26115ee9ee762a709751413ae72ae869fae480572512e170669a1ebb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ab008fe26115ee9ee762a709751413ae72ae869fae480572512e170669a1ebb","first_computed_at":"2026-05-18T01:15:30.625755Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:15:30.625755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bjtJ90iDHRhDo49byHjJHmV0aeHaii+gZn49jM8HwE0KI1AvR3kgbJNOTz3qLT1BeSx0WcSeVWDNiJZ7s2SvDA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:15:30.626443Z","signed_message":"canonical_sha256_bytes"},"source_id":"1605.02019","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b15111b5f7153ff7bbee9968346f820bb4efd641c9e1efd151e35ef2bf384e28","sha256:e714696095aac5fad2883d37d27153bdcc7970e6eb54866b09eb5b9079277309"],"state_sha256":"2f1910e69c6ddb222220b3dcefe5646d274fedf036dc2d9918e600591d8b4e39"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"StrIzDmboVZDLWUBV5emBzAA2triNbXptPyDlTFGhnpg5cJ3zJnGcIh+xQnKlM16BoaHivXwFB8hopKtY5fVAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T16:04:29.006181Z","bundle_sha256":"3240137ebe29ada33a20426ea4f340188b0819a9bdb9319edadb658bc799ea47"}}