{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:VL2PP3JKHRQGIDEC5ITW3UKNCK","short_pith_number":"pith:VL2PP3JK","canonical_record":{"source":{"id":"1706.00359","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-06-01T15:55:42Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"6db4098804f44e533344ab10315043c453afbace9074aaa59dfd66fc9689117b","abstract_canon_sha256":"5c2ac0b140610cdbfc6b74606550615d211da7f9af01d1c1914a598b1acdbdfd"},"schema_version":"1.0"},"canonical_sha256":"aaf4f7ed2a3c60640c82ea276dd14d12ab0e92620c84dea0a56ee5f9cc2c1d74","source":{"kind":"arxiv","id":"1706.00359","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.00359","created_at":"2026-05-18T00:15:30Z"},{"alias_kind":"arxiv_version","alias_value":"1706.00359v2","created_at":"2026-05-18T00:15:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.00359","created_at":"2026-05-18T00:15:30Z"},{"alias_kind":"pith_short_12","alias_value":"VL2PP3JKHRQG","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"VL2PP3JKHRQGIDEC","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"VL2PP3JK","created_at":"2026-05-18T12:31:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:VL2PP3JKHRQGIDEC5ITW3UKNCK","target":"record","payload":{"canonical_record":{"source":{"id":"1706.00359","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-06-01T15:55:42Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"6db4098804f44e533344ab10315043c453afbace9074aaa59dfd66fc9689117b","abstract_canon_sha256":"5c2ac0b140610cdbfc6b74606550615d211da7f9af01d1c1914a598b1acdbdfd"},"schema_version":"1.0"},"canonical_sha256":"aaf4f7ed2a3c60640c82ea276dd14d12ab0e92620c84dea0a56ee5f9cc2c1d74","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:30.727748Z","signature_b64":"1UceP8RGOIghA7HScdXBBZ9cHfXJNtb3rNUCmAFvYcQD9gaQ2BW9eJq2sfNOiUHnE8i/XKEZ7hDLjk3F13g2Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aaf4f7ed2a3c60640c82ea276dd14d12ab0e92620c84dea0a56ee5f9cc2c1d74","last_reissued_at":"2026-05-18T00:15:30.727227Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:30.727227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1706.00359","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:15:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rTjh/FV0XYQyiC8TRz1jfd1KDt8t9aJRpwU67dkOv3zndrOE3xgHv60hpeVWumdjG/cJGFrDSJ/3wCpZqIzMAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T15:39:30.916372Z"},"content_sha256":"086b9636a08074a7a7ee617e4a02763ddb538948eb7dbb5132061d2d18e1ae96","schema_version":"1.0","event_id":"sha256:086b9636a08074a7a7ee617e4a02763ddb538948eb7dbb5132061d2d18e1ae96"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:VL2PP3JKHRQGIDEC5ITW3UKNCK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Discovering Discrete Latent Topics with Neural Variational Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Edward Grefenstette, Phil Blunsom, Yishu Miao","submitted_at":"2017-06-01T15:55:42Z","abstract_excerpt":"Topic models have been widely explored as probabilistic generative models of documents. Traditional inference methods have sought closed-form derivations for updating the models, however as the expressiveness of these models grows, so does the difficulty of performing fast and accurate inference over their parameters. This paper presents alternative neural approaches to topic modelling by providing parameterisable distributions over topics which permit training by backpropagation in the framework of neural variational inference. In addition, with the help of a stick-breaking construction, we p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.00359","kind":"arxiv","version":2},"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":"2026-05-18T00:15:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bxtlxq8boBc3ktGl7qAVw0HAyz8pfIOMhGTVivyXGJY3mgaIV4nY4IJ2ZxtWq4JhMlFaASLww9snmB78GcUcBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T15:39:30.916754Z"},"content_sha256":"a4c7b57c4d33e594b6b80e25acf12e2da69213c76807482678e89fa983614de0","schema_version":"1.0","event_id":"sha256:a4c7b57c4d33e594b6b80e25acf12e2da69213c76807482678e89fa983614de0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VL2PP3JKHRQGIDEC5ITW3UKNCK/bundle.json","state_url":"https://pith.science/pith/VL2PP3JKHRQGIDEC5ITW3UKNCK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VL2PP3JKHRQGIDEC5ITW3UKNCK/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":"2026-05-27T15:39:30Z","links":{"resolver":"https://pith.science/pith/VL2PP3JKHRQGIDEC5ITW3UKNCK","bundle":"https://pith.science/pith/VL2PP3JKHRQGIDEC5ITW3UKNCK/bundle.json","state":"https://pith.science/pith/VL2PP3JKHRQGIDEC5ITW3UKNCK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VL2PP3JKHRQGIDEC5ITW3UKNCK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:VL2PP3JKHRQGIDEC5ITW3UKNCK","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":"5c2ac0b140610cdbfc6b74606550615d211da7f9af01d1c1914a598b1acdbdfd","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-06-01T15:55:42Z","title_canon_sha256":"6db4098804f44e533344ab10315043c453afbace9074aaa59dfd66fc9689117b"},"schema_version":"1.0","source":{"id":"1706.00359","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.00359","created_at":"2026-05-18T00:15:30Z"},{"alias_kind":"arxiv_version","alias_value":"1706.00359v2","created_at":"2026-05-18T00:15:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.00359","created_at":"2026-05-18T00:15:30Z"},{"alias_kind":"pith_short_12","alias_value":"VL2PP3JKHRQG","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"VL2PP3JKHRQGIDEC","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"VL2PP3JK","created_at":"2026-05-18T12:31:49Z"}],"graph_snapshots":[{"event_id":"sha256:a4c7b57c4d33e594b6b80e25acf12e2da69213c76807482678e89fa983614de0","target":"graph","created_at":"2026-05-18T00:15:30Z","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":"Topic models have been widely explored as probabilistic generative models of documents. Traditional inference methods have sought closed-form derivations for updating the models, however as the expressiveness of these models grows, so does the difficulty of performing fast and accurate inference over their parameters. This paper presents alternative neural approaches to topic modelling by providing parameterisable distributions over topics which permit training by backpropagation in the framework of neural variational inference. In addition, with the help of a stick-breaking construction, we p","authors_text":"Edward Grefenstette, Phil Blunsom, Yishu Miao","cross_cats":["cs.AI","cs.IR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-06-01T15:55:42Z","title":"Discovering Discrete Latent Topics with Neural Variational Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.00359","kind":"arxiv","version":2},"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":"sha256:086b9636a08074a7a7ee617e4a02763ddb538948eb7dbb5132061d2d18e1ae96","target":"record","created_at":"2026-05-18T00:15:30Z","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":"5c2ac0b140610cdbfc6b74606550615d211da7f9af01d1c1914a598b1acdbdfd","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-06-01T15:55:42Z","title_canon_sha256":"6db4098804f44e533344ab10315043c453afbace9074aaa59dfd66fc9689117b"},"schema_version":"1.0","source":{"id":"1706.00359","kind":"arxiv","version":2}},"canonical_sha256":"aaf4f7ed2a3c60640c82ea276dd14d12ab0e92620c84dea0a56ee5f9cc2c1d74","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aaf4f7ed2a3c60640c82ea276dd14d12ab0e92620c84dea0a56ee5f9cc2c1d74","first_computed_at":"2026-05-18T00:15:30.727227Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:15:30.727227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1UceP8RGOIghA7HScdXBBZ9cHfXJNtb3rNUCmAFvYcQD9gaQ2BW9eJq2sfNOiUHnE8i/XKEZ7hDLjk3F13g2Cw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:15:30.727748Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.00359","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:086b9636a08074a7a7ee617e4a02763ddb538948eb7dbb5132061d2d18e1ae96","sha256:a4c7b57c4d33e594b6b80e25acf12e2da69213c76807482678e89fa983614de0"],"state_sha256":"63e0586c15261cc0f8824124ec012b33306ac6126bec7b3288d44a5eb50c74b5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1jO8oIg5PyqR7So/hNVnlSqyYoc06m7kNXfvZ423uIj1u1doiyZKgUF2Gtn3nv9ylHT1J5DSRZV769ZytizpCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T15:39:30.919200Z","bundle_sha256":"c53a44fcb1b366d76f2f97b89f63e7d31ac52e033528437f144bbce3cc1d199a"}}