{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:QXHDQJN2IJ3LWPKUGOSY5ETOJM","short_pith_number":"pith:QXHDQJN2","canonical_record":{"source":{"id":"1709.08524","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2017-09-25T14:43:53Z","cross_cats_sorted":["cs.CV","cs.NE","stat.ML"],"title_canon_sha256":"4694aaee1e780b96b239a77c0137ff95e4218da76a10c72333a92a41d6a2d476","abstract_canon_sha256":"896dc203deb769d3d7216f75f8fe41fcb1a383550396a5a43c092c2fd177d234"},"schema_version":"1.0"},"canonical_sha256":"85ce3825ba4276bb3d5433a58e926e4b007851eced7d7159924ff0dff86240b4","source":{"kind":"arxiv","id":"1709.08524","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.08524","created_at":"2026-05-18T00:34:25Z"},{"alias_kind":"arxiv_version","alias_value":"1709.08524v1","created_at":"2026-05-18T00:34:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.08524","created_at":"2026-05-18T00:34:25Z"},{"alias_kind":"pith_short_12","alias_value":"QXHDQJN2IJ3L","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"QXHDQJN2IJ3LWPKU","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"QXHDQJN2","created_at":"2026-05-18T12:31:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:QXHDQJN2IJ3LWPKUGOSY5ETOJM","target":"record","payload":{"canonical_record":{"source":{"id":"1709.08524","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2017-09-25T14:43:53Z","cross_cats_sorted":["cs.CV","cs.NE","stat.ML"],"title_canon_sha256":"4694aaee1e780b96b239a77c0137ff95e4218da76a10c72333a92a41d6a2d476","abstract_canon_sha256":"896dc203deb769d3d7216f75f8fe41fcb1a383550396a5a43c092c2fd177d234"},"schema_version":"1.0"},"canonical_sha256":"85ce3825ba4276bb3d5433a58e926e4b007851eced7d7159924ff0dff86240b4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:34:25.396973Z","signature_b64":"ZQpTKmv0BX9R4VSmMwZEJ8cmjnvlKMvFOawMsZvvdoZx6HzHjsQiGL48Mx4357+6ORYUG/8dEgQ40zukCD90AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85ce3825ba4276bb3d5433a58e926e4b007851eced7d7159924ff0dff86240b4","last_reissued_at":"2026-05-18T00:34:25.396409Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:34:25.396409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.08524","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":"2026-05-18T00:34:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OE4kGFtGDiXadkXrXpXmxwYF8CTqoDnIXREy8oWFRsWJ+KfYXPhk1LFfY/CpdJJ1Pin0dOp3TjyD5476ocemDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T21:36:42.005799Z"},"content_sha256":"de16ab05ec7078a9cc712cc53c303258b0d9d187109f7cea340013544e5fd45b","schema_version":"1.0","event_id":"sha256:de16ab05ec7078a9cc712cc53c303258b0d9d187109f7cea340013544e5fd45b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:QXHDQJN2IJ3LWPKUGOSY5ETOJM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generative learning for deep networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Shekhovtsov, Boris Flach, Ondrej Fikar","submitted_at":"2017-09-25T14:43:53Z","abstract_excerpt":"Learning, taking into account full distribution of the data, referred to as generative, is not feasible with deep neural networks (DNNs) because they model only the conditional distribution of the outputs given the inputs. Current solutions are either based on joint probability models facing difficult estimation problems or learn two separate networks, mapping inputs to outputs (recognition) and vice-versa (generation). We propose an intermediate approach. First, we show that forward computation in DNNs with logistic sigmoid activations corresponds to a simplified approximate Bayesian inferenc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.08524","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":"2026-05-18T00:34:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rpNYFt6hjx+zzIDMl6MsXXhBjH6kywqvUn7hvhKrqMrFbaAqiKiacnksaQj1cautfAya4LeAy/DzuoN8NNbNDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T21:36:42.006151Z"},"content_sha256":"648d209373617f70b115e7f34d536d3ca471488410a400211c317a956d915a79","schema_version":"1.0","event_id":"sha256:648d209373617f70b115e7f34d536d3ca471488410a400211c317a956d915a79"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QXHDQJN2IJ3LWPKUGOSY5ETOJM/bundle.json","state_url":"https://pith.science/pith/QXHDQJN2IJ3LWPKUGOSY5ETOJM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QXHDQJN2IJ3LWPKUGOSY5ETOJM/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":"2026-06-02T21:36:42Z","links":{"resolver":"https://pith.science/pith/QXHDQJN2IJ3LWPKUGOSY5ETOJM","bundle":"https://pith.science/pith/QXHDQJN2IJ3LWPKUGOSY5ETOJM/bundle.json","state":"https://pith.science/pith/QXHDQJN2IJ3LWPKUGOSY5ETOJM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QXHDQJN2IJ3LWPKUGOSY5ETOJM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:QXHDQJN2IJ3LWPKUGOSY5ETOJM","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":"896dc203deb769d3d7216f75f8fe41fcb1a383550396a5a43c092c2fd177d234","cross_cats_sorted":["cs.CV","cs.NE","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2017-09-25T14:43:53Z","title_canon_sha256":"4694aaee1e780b96b239a77c0137ff95e4218da76a10c72333a92a41d6a2d476"},"schema_version":"1.0","source":{"id":"1709.08524","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.08524","created_at":"2026-05-18T00:34:25Z"},{"alias_kind":"arxiv_version","alias_value":"1709.08524v1","created_at":"2026-05-18T00:34:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.08524","created_at":"2026-05-18T00:34:25Z"},{"alias_kind":"pith_short_12","alias_value":"QXHDQJN2IJ3L","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"QXHDQJN2IJ3LWPKU","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"QXHDQJN2","created_at":"2026-05-18T12:31:39Z"}],"graph_snapshots":[{"event_id":"sha256:648d209373617f70b115e7f34d536d3ca471488410a400211c317a956d915a79","target":"graph","created_at":"2026-05-18T00:34:25Z","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":"Learning, taking into account full distribution of the data, referred to as generative, is not feasible with deep neural networks (DNNs) because they model only the conditional distribution of the outputs given the inputs. Current solutions are either based on joint probability models facing difficult estimation problems or learn two separate networks, mapping inputs to outputs (recognition) and vice-versa (generation). We propose an intermediate approach. First, we show that forward computation in DNNs with logistic sigmoid activations corresponds to a simplified approximate Bayesian inferenc","authors_text":"Alexander Shekhovtsov, Boris Flach, Ondrej Fikar","cross_cats":["cs.CV","cs.NE","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2017-09-25T14:43:53Z","title":"Generative learning for deep networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.08524","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:de16ab05ec7078a9cc712cc53c303258b0d9d187109f7cea340013544e5fd45b","target":"record","created_at":"2026-05-18T00:34:25Z","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":"896dc203deb769d3d7216f75f8fe41fcb1a383550396a5a43c092c2fd177d234","cross_cats_sorted":["cs.CV","cs.NE","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2017-09-25T14:43:53Z","title_canon_sha256":"4694aaee1e780b96b239a77c0137ff95e4218da76a10c72333a92a41d6a2d476"},"schema_version":"1.0","source":{"id":"1709.08524","kind":"arxiv","version":1}},"canonical_sha256":"85ce3825ba4276bb3d5433a58e926e4b007851eced7d7159924ff0dff86240b4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"85ce3825ba4276bb3d5433a58e926e4b007851eced7d7159924ff0dff86240b4","first_computed_at":"2026-05-18T00:34:25.396409Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:34:25.396409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZQpTKmv0BX9R4VSmMwZEJ8cmjnvlKMvFOawMsZvvdoZx6HzHjsQiGL48Mx4357+6ORYUG/8dEgQ40zukCD90AA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:34:25.396973Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.08524","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de16ab05ec7078a9cc712cc53c303258b0d9d187109f7cea340013544e5fd45b","sha256:648d209373617f70b115e7f34d536d3ca471488410a400211c317a956d915a79"],"state_sha256":"2dcf74e7d9b2aee278964f78b1c87ff53355e74d085227baa3d8d5d0048b9b10"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kzwxZcLYia/sIf2HNO26wSVtiQXSd270ZyBJsLecKDp6027Ml9VWZuLTMKTj9FPCmYzD3Sn9SFM3S4AzulzWCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T21:36:42.008087Z","bundle_sha256":"5db915e1bca205f3c70d2bd9d49d6a03480e14f88b92b3fb9ca76bc9d4df8cda"}}