{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:FPET6FR6ACI67N7TLBXPEDHSRW","short_pith_number":"pith:FPET6FR6","canonical_record":{"source":{"id":"1706.00400","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-01T17:23:07Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"678a2496ba86ef70f3a09cc7c52cc49bcac331f5f7d63ea614263da40bc2c609","abstract_canon_sha256":"1eaa7d868f7a52269b78fb764e13d7e7cd882b2eb845df80b9967117231327d6"},"schema_version":"1.0"},"canonical_sha256":"2bc93f163e0091efb7f3586ef20cf28da0ddad7b6646ab85172cfeb44fba66ab","source":{"kind":"arxiv","id":"1706.00400","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.00400","created_at":"2026-05-18T00:30:44Z"},{"alias_kind":"arxiv_version","alias_value":"1706.00400v2","created_at":"2026-05-18T00:30:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.00400","created_at":"2026-05-18T00:30:44Z"},{"alias_kind":"pith_short_12","alias_value":"FPET6FR6ACI6","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"FPET6FR6ACI67N7T","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"FPET6FR6","created_at":"2026-05-18T12:31:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:FPET6FR6ACI67N7TLBXPEDHSRW","target":"record","payload":{"canonical_record":{"source":{"id":"1706.00400","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-01T17:23:07Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"678a2496ba86ef70f3a09cc7c52cc49bcac331f5f7d63ea614263da40bc2c609","abstract_canon_sha256":"1eaa7d868f7a52269b78fb764e13d7e7cd882b2eb845df80b9967117231327d6"},"schema_version":"1.0"},"canonical_sha256":"2bc93f163e0091efb7f3586ef20cf28da0ddad7b6646ab85172cfeb44fba66ab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:44.570064Z","signature_b64":"62A/5OeHy1cpaZvY8zzR+2esISRX9CyZuGrESlv/V7kHcQ1aB5pKQGYa604x4nZG4H4HWI02nBeBSqKc/+ikDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bc93f163e0091efb7f3586ef20cf28da0ddad7b6646ab85172cfeb44fba66ab","last_reissued_at":"2026-05-18T00:30:44.569500Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:44.569500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1706.00400","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":"2026-05-18T00:30:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/sVju28tfdRZa6Un0K9X/s1VqDHevnEXgNp+SECbECpBcK37kjvHjHvItq6cGDICXX5qNEkMZb42lYiyjIFDCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T14:40:18.940556Z"},"content_sha256":"a09494e79933ad4404a025e726b2077da52049a76b758c2c941c1d23f75d9c57","schema_version":"1.0","event_id":"sha256:a09494e79933ad4404a025e726b2077da52049a76b758c2c941c1d23f75d9c57"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:FPET6FR6ACI67N7TLBXPEDHSRW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Disentangled Representations with Semi-Supervised Deep Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Alban Desmaison, Brooks Paige, Frank Wood, Jan-Willem van de Meent, Noah D. Goodman, N. Siddharth, Philip H.S. Torr, Pushmeet Kohli","submitted_at":"2017-06-01T17:23:07Z","abstract_excerpt":"Variational autoencoders (VAEs) learn representations of data by jointly training a probabilistic encoder and decoder network. Typically these models encode all features of the data into a single variable. Here we are interested in learning disentangled representations that encode distinct aspects of the data into separate variables. We propose to learn such representations using model architectures that generalise from standard VAEs, employing a general graphical model structure in the encoder and decoder. This allows us to train partially-specified models that make relatively strong assumpti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.00400","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":"2026-05-18T00:30:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"izDqTXjB7G2utUDaK3+Y9ws5TLKnRSWOg600CFbhXoPNnkdB83xVpHokdraA0OJtpyGf8uaeak3gAHcnvbxEDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T14:40:18.940922Z"},"content_sha256":"63b4a66092d70e6d7f1781055f1c4adb116cd5c3330fc11407c71c124a065273","schema_version":"1.0","event_id":"sha256:63b4a66092d70e6d7f1781055f1c4adb116cd5c3330fc11407c71c124a065273"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FPET6FR6ACI67N7TLBXPEDHSRW/bundle.json","state_url":"https://pith.science/pith/FPET6FR6ACI67N7TLBXPEDHSRW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FPET6FR6ACI67N7TLBXPEDHSRW/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":"2026-05-27T14:40:18Z","links":{"resolver":"https://pith.science/pith/FPET6FR6ACI67N7TLBXPEDHSRW","bundle":"https://pith.science/pith/FPET6FR6ACI67N7TLBXPEDHSRW/bundle.json","state":"https://pith.science/pith/FPET6FR6ACI67N7TLBXPEDHSRW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FPET6FR6ACI67N7TLBXPEDHSRW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:FPET6FR6ACI67N7TLBXPEDHSRW","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":"1eaa7d868f7a52269b78fb764e13d7e7cd882b2eb845df80b9967117231327d6","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-01T17:23:07Z","title_canon_sha256":"678a2496ba86ef70f3a09cc7c52cc49bcac331f5f7d63ea614263da40bc2c609"},"schema_version":"1.0","source":{"id":"1706.00400","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.00400","created_at":"2026-05-18T00:30:44Z"},{"alias_kind":"arxiv_version","alias_value":"1706.00400v2","created_at":"2026-05-18T00:30:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.00400","created_at":"2026-05-18T00:30:44Z"},{"alias_kind":"pith_short_12","alias_value":"FPET6FR6ACI6","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"FPET6FR6ACI67N7T","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"FPET6FR6","created_at":"2026-05-18T12:31:15Z"}],"graph_snapshots":[{"event_id":"sha256:63b4a66092d70e6d7f1781055f1c4adb116cd5c3330fc11407c71c124a065273","target":"graph","created_at":"2026-05-18T00:30:44Z","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":"Variational autoencoders (VAEs) learn representations of data by jointly training a probabilistic encoder and decoder network. Typically these models encode all features of the data into a single variable. Here we are interested in learning disentangled representations that encode distinct aspects of the data into separate variables. We propose to learn such representations using model architectures that generalise from standard VAEs, employing a general graphical model structure in the encoder and decoder. This allows us to train partially-specified models that make relatively strong assumpti","authors_text":"Alban Desmaison, Brooks Paige, Frank Wood, Jan-Willem van de Meent, Noah D. Goodman, N. Siddharth, Philip H.S. Torr, Pushmeet Kohli","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-01T17:23:07Z","title":"Learning Disentangled Representations with Semi-Supervised Deep Generative Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.00400","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:a09494e79933ad4404a025e726b2077da52049a76b758c2c941c1d23f75d9c57","target":"record","created_at":"2026-05-18T00:30:44Z","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":"1eaa7d868f7a52269b78fb764e13d7e7cd882b2eb845df80b9967117231327d6","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-01T17:23:07Z","title_canon_sha256":"678a2496ba86ef70f3a09cc7c52cc49bcac331f5f7d63ea614263da40bc2c609"},"schema_version":"1.0","source":{"id":"1706.00400","kind":"arxiv","version":2}},"canonical_sha256":"2bc93f163e0091efb7f3586ef20cf28da0ddad7b6646ab85172cfeb44fba66ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2bc93f163e0091efb7f3586ef20cf28da0ddad7b6646ab85172cfeb44fba66ab","first_computed_at":"2026-05-18T00:30:44.569500Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:30:44.569500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"62A/5OeHy1cpaZvY8zzR+2esISRX9CyZuGrESlv/V7kHcQ1aB5pKQGYa604x4nZG4H4HWI02nBeBSqKc/+ikDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:30:44.570064Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.00400","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a09494e79933ad4404a025e726b2077da52049a76b758c2c941c1d23f75d9c57","sha256:63b4a66092d70e6d7f1781055f1c4adb116cd5c3330fc11407c71c124a065273"],"state_sha256":"9434fa2f4783d42904cfd6bf561b485d8f0c4e4f170f5cead0943ce916f97b1a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tD3THm12Z3zByyKsIY33Mgm+9S3y7gq/qW3eto4Gjz7Hkz5V7COIZn/Y4fMUzIFL9dp7wZeM4LLbuPwG7puaBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T14:40:18.943766Z","bundle_sha256":"949314a1475336d30a3e5b13dbbab509548ff2018a96ad20fd174aa08a54c209"}}