{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:FDL3XFBYZETKLQQPSAW5VU6ZTX","short_pith_number":"pith:FDL3XFBY","canonical_record":{"source":{"id":"1612.00377","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-12-01T18:49:23Z","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"title_canon_sha256":"36cbd4ef6866f30916d6f8100807a9aa66cf05203c98ed82481b6957a1feab72","abstract_canon_sha256":"ab7697170b48ad89861c655d8a02e385cfe57127ba9bcfed039bec3dc64b7661"},"schema_version":"1.0"},"canonical_sha256":"28d7bb9438c926a5c20f902ddad3d99dd843d9278b7670dc93d892ac06332b04","source":{"kind":"arxiv","id":"1612.00377","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.00377","created_at":"2026-05-18T00:34:31Z"},{"alias_kind":"arxiv_version","alias_value":"1612.00377v4","created_at":"2026-05-18T00:34:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.00377","created_at":"2026-05-18T00:34:31Z"},{"alias_kind":"pith_short_12","alias_value":"FDL3XFBYZETK","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_16","alias_value":"FDL3XFBYZETKLQQP","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_8","alias_value":"FDL3XFBY","created_at":"2026-05-18T12:30:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:FDL3XFBYZETKLQQPSAW5VU6ZTX","target":"record","payload":{"canonical_record":{"source":{"id":"1612.00377","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-12-01T18:49:23Z","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"title_canon_sha256":"36cbd4ef6866f30916d6f8100807a9aa66cf05203c98ed82481b6957a1feab72","abstract_canon_sha256":"ab7697170b48ad89861c655d8a02e385cfe57127ba9bcfed039bec3dc64b7661"},"schema_version":"1.0"},"canonical_sha256":"28d7bb9438c926a5c20f902ddad3d99dd843d9278b7670dc93d892ac06332b04","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:34:31.385180Z","signature_b64":"wLc/8S4iqTSX6ri981mYJgR5HyOT7EjewYHdNq4ygYTXXbFPy/MlGHneslpntD2JhdCkG8f2ocoBG7XAaYviDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28d7bb9438c926a5c20f902ddad3d99dd843d9278b7670dc93d892ac06332b04","last_reissued_at":"2026-05-18T00:34:31.384803Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:34:31.384803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1612.00377","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:34:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kSo2Hks/4gSFYsBAlOAaZZbk9RE7m8RHTykkLPgu7OVq7mvF/eeZiAJX/QqEa6oMXSadPPPiEKZBL3SPy2ysDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T01:38:23.422337Z"},"content_sha256":"283839463c8056768e211deb014f139283c6998d4734c369fee18cf09bf8b5c5","schema_version":"1.0","event_id":"sha256:283839463c8056768e211deb014f139283c6998d4734c369fee18cf09bf8b5c5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:FDL3XFBYZETKLQQPSAW5VU6ZTX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Piecewise Latent Variables for Neural Variational Text Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Aaron Courville, Alexander G. Ororbia II, Iulian V. Serban, Joelle Pineau","submitted_at":"2016-12-01T18:49:23Z","abstract_excerpt":"Advances in neural variational inference have facilitated the learning of powerful directed graphical models with continuous latent variables, such as variational autoencoders. The hope is that such models will learn to represent rich, multi-modal latent factors in real-world data, such as natural language text. However, current models often assume simplistic priors on the latent variables - such as the uni-modal Gaussian distribution - which are incapable of representing complex latent factors efficiently. To overcome this restriction, we propose the simple, but highly flexible, piecewise con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.00377","kind":"arxiv","version":4},"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":"2026-05-18T00:34:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U0wBU/NSW+Dl9zwi+YMm9le37hY8bqjpG/d/7W1bbiqQtEQLb3nE3tizF+eB+p0tvSmAqr+AhzTxEKSrDEr2CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T01:38:23.422949Z"},"content_sha256":"6c82ff193f4968836e80e7a3d4fdb7fd8f59fe450c128ff40e24e2045542eb79","schema_version":"1.0","event_id":"sha256:6c82ff193f4968836e80e7a3d4fdb7fd8f59fe450c128ff40e24e2045542eb79"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FDL3XFBYZETKLQQPSAW5VU6ZTX/bundle.json","state_url":"https://pith.science/pith/FDL3XFBYZETKLQQPSAW5VU6ZTX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FDL3XFBYZETKLQQPSAW5VU6ZTX/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":"2026-06-08T01:38:23Z","links":{"resolver":"https://pith.science/pith/FDL3XFBYZETKLQQPSAW5VU6ZTX","bundle":"https://pith.science/pith/FDL3XFBYZETKLQQPSAW5VU6ZTX/bundle.json","state":"https://pith.science/pith/FDL3XFBYZETKLQQPSAW5VU6ZTX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FDL3XFBYZETKLQQPSAW5VU6ZTX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:FDL3XFBYZETKLQQPSAW5VU6ZTX","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":"ab7697170b48ad89861c655d8a02e385cfe57127ba9bcfed039bec3dc64b7661","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-12-01T18:49:23Z","title_canon_sha256":"36cbd4ef6866f30916d6f8100807a9aa66cf05203c98ed82481b6957a1feab72"},"schema_version":"1.0","source":{"id":"1612.00377","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.00377","created_at":"2026-05-18T00:34:31Z"},{"alias_kind":"arxiv_version","alias_value":"1612.00377v4","created_at":"2026-05-18T00:34:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.00377","created_at":"2026-05-18T00:34:31Z"},{"alias_kind":"pith_short_12","alias_value":"FDL3XFBYZETK","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_16","alias_value":"FDL3XFBYZETKLQQP","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_8","alias_value":"FDL3XFBY","created_at":"2026-05-18T12:30:15Z"}],"graph_snapshots":[{"event_id":"sha256:6c82ff193f4968836e80e7a3d4fdb7fd8f59fe450c128ff40e24e2045542eb79","target":"graph","created_at":"2026-05-18T00:34:31Z","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":"Advances in neural variational inference have facilitated the learning of powerful directed graphical models with continuous latent variables, such as variational autoencoders. The hope is that such models will learn to represent rich, multi-modal latent factors in real-world data, such as natural language text. However, current models often assume simplistic priors on the latent variables - such as the uni-modal Gaussian distribution - which are incapable of representing complex latent factors efficiently. To overcome this restriction, we propose the simple, but highly flexible, piecewise con","authors_text":"Aaron Courville, Alexander G. Ororbia II, Iulian V. Serban, Joelle Pineau","cross_cats":["cs.AI","cs.LG","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-12-01T18:49:23Z","title":"Piecewise Latent Variables for Neural Variational Text Processing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.00377","kind":"arxiv","version":4},"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":"sha256:283839463c8056768e211deb014f139283c6998d4734c369fee18cf09bf8b5c5","target":"record","created_at":"2026-05-18T00:34:31Z","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":"ab7697170b48ad89861c655d8a02e385cfe57127ba9bcfed039bec3dc64b7661","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-12-01T18:49:23Z","title_canon_sha256":"36cbd4ef6866f30916d6f8100807a9aa66cf05203c98ed82481b6957a1feab72"},"schema_version":"1.0","source":{"id":"1612.00377","kind":"arxiv","version":4}},"canonical_sha256":"28d7bb9438c926a5c20f902ddad3d99dd843d9278b7670dc93d892ac06332b04","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28d7bb9438c926a5c20f902ddad3d99dd843d9278b7670dc93d892ac06332b04","first_computed_at":"2026-05-18T00:34:31.384803Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:34:31.384803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wLc/8S4iqTSX6ri981mYJgR5HyOT7EjewYHdNq4ygYTXXbFPy/MlGHneslpntD2JhdCkG8f2ocoBG7XAaYviDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:34:31.385180Z","signed_message":"canonical_sha256_bytes"},"source_id":"1612.00377","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:283839463c8056768e211deb014f139283c6998d4734c369fee18cf09bf8b5c5","sha256:6c82ff193f4968836e80e7a3d4fdb7fd8f59fe450c128ff40e24e2045542eb79"],"state_sha256":"38b9a7dbcaf08c0dca017bb4bbc29dd961aca5a079c1da8f07c5da240ef6b070"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"//VG9Pzy8hR+Abr54bGKtgkvv3LEFI4PUVFgXZS8A89E2qH1fct7C+9DSKG16pwYX1UP5cPyBJYQOVmtF5LNBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T01:38:23.426188Z","bundle_sha256":"62b453d00d39b7d079e26309a521ebc06f5fbcd4182d7df5e5c7b4c59902884c"}}