{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2013:56EKEZB5KUJW4EYTWQYTFEC3HF","short_pith_number":"pith:56EKEZB5","canonical_record":{"source":{"id":"1306.1091","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-06-05T13:01:14Z","cross_cats_sorted":[],"title_canon_sha256":"dc12fc295c1174a22a4f4ae6a38d20f380c220de6766e850c04a14cb15cc48a6","abstract_canon_sha256":"73afd14edee39ecdbbd2c3b6780f2782e581c76380075c44cd3b9e61a3ae97ab"},"schema_version":"1.0"},"canonical_sha256":"ef88a2643d55136e1313b43132905b3941b4f4eb2d7f9fa9b020a8551e3a8ab0","source":{"kind":"arxiv","id":"1306.1091","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1306.1091","created_at":"2026-05-18T02:51:08Z"},{"alias_kind":"arxiv_version","alias_value":"1306.1091v5","created_at":"2026-05-18T02:51:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1306.1091","created_at":"2026-05-18T02:51:08Z"},{"alias_kind":"pith_short_12","alias_value":"56EKEZB5KUJW","created_at":"2026-05-18T12:27:34Z"},{"alias_kind":"pith_short_16","alias_value":"56EKEZB5KUJW4EYT","created_at":"2026-05-18T12:27:34Z"},{"alias_kind":"pith_short_8","alias_value":"56EKEZB5","created_at":"2026-05-18T12:27:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2013:56EKEZB5KUJW4EYTWQYTFEC3HF","target":"record","payload":{"canonical_record":{"source":{"id":"1306.1091","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-06-05T13:01:14Z","cross_cats_sorted":[],"title_canon_sha256":"dc12fc295c1174a22a4f4ae6a38d20f380c220de6766e850c04a14cb15cc48a6","abstract_canon_sha256":"73afd14edee39ecdbbd2c3b6780f2782e581c76380075c44cd3b9e61a3ae97ab"},"schema_version":"1.0"},"canonical_sha256":"ef88a2643d55136e1313b43132905b3941b4f4eb2d7f9fa9b020a8551e3a8ab0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:51:08.560820Z","signature_b64":"9sxkUStO4HRnT+V9hhaqjnfZhEWBaEBDC6lxQZRAQr9DC3/v6J94YDgiJUyH4tP+d+BO7StMOJac+HtYAOZqBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef88a2643d55136e1313b43132905b3941b4f4eb2d7f9fa9b020a8551e3a8ab0","last_reissued_at":"2026-05-18T02:51:08.560385Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:51:08.560385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1306.1091","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:51:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C7LJqKW2HAJNXwTp+M95m2z2uJDG2NKU3EPmRMr6Y87DdHEpGRrSEt1YKFZ2tcLLZPzI+TQdwomitnZGlf+eCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T12:22:54.597138Z"},"content_sha256":"5df55422a545183bffa24dcdd22bba6d8e06c6defd3306d412028bce0163548a","schema_version":"1.0","event_id":"sha256:5df55422a545183bffa24dcdd22bba6d8e06c6defd3306d412028bce0163548a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2013:56EKEZB5KUJW4EYTWQYTFEC3HF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Generative Stochastic Networks Trainable by Backprop","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"\\'Eric Thibodeau-Laufer, Guillaume Alain, Jason Yosinski, Yoshua Bengio","submitted_at":"2013-06-05T13:01:14Z","abstract_excerpt":"We introduce a novel training principle for probabilistic models that is an alternative to maximum likelihood. The proposed Generative Stochastic Networks (GSN) framework is based on learning the transition operator of a Markov chain whose stationary distribution estimates the data distribution. The transition distribution of the Markov chain is conditional on the previous state, generally involving a small move, so this conditional distribution has fewer dominant modes, being unimodal in the limit of small moves. Thus, it is easier to learn because it is easier to approximate its partition fu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1306.1091","kind":"arxiv","version":5},"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":"2026-05-18T02:51:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LElDuMnI9vIu4dnY3KxQ4axeKt0K8IEp/+ulygVAP+4fQtZ7rCeS/Y4hP0IW5bZV7r2tu1IBED2MN81zDFgUDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T12:22:54.597657Z"},"content_sha256":"4435eea8aceb6e8671d6251f8f04d17d81b5a280c4bbe8e2679361af5a45ca99","schema_version":"1.0","event_id":"sha256:4435eea8aceb6e8671d6251f8f04d17d81b5a280c4bbe8e2679361af5a45ca99"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/56EKEZB5KUJW4EYTWQYTFEC3HF/bundle.json","state_url":"https://pith.science/pith/56EKEZB5KUJW4EYTWQYTFEC3HF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/56EKEZB5KUJW4EYTWQYTFEC3HF/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":"2026-05-30T12:22:54Z","links":{"resolver":"https://pith.science/pith/56EKEZB5KUJW4EYTWQYTFEC3HF","bundle":"https://pith.science/pith/56EKEZB5KUJW4EYTWQYTFEC3HF/bundle.json","state":"https://pith.science/pith/56EKEZB5KUJW4EYTWQYTFEC3HF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/56EKEZB5KUJW4EYTWQYTFEC3HF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:56EKEZB5KUJW4EYTWQYTFEC3HF","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":"73afd14edee39ecdbbd2c3b6780f2782e581c76380075c44cd3b9e61a3ae97ab","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-06-05T13:01:14Z","title_canon_sha256":"dc12fc295c1174a22a4f4ae6a38d20f380c220de6766e850c04a14cb15cc48a6"},"schema_version":"1.0","source":{"id":"1306.1091","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1306.1091","created_at":"2026-05-18T02:51:08Z"},{"alias_kind":"arxiv_version","alias_value":"1306.1091v5","created_at":"2026-05-18T02:51:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1306.1091","created_at":"2026-05-18T02:51:08Z"},{"alias_kind":"pith_short_12","alias_value":"56EKEZB5KUJW","created_at":"2026-05-18T12:27:34Z"},{"alias_kind":"pith_short_16","alias_value":"56EKEZB5KUJW4EYT","created_at":"2026-05-18T12:27:34Z"},{"alias_kind":"pith_short_8","alias_value":"56EKEZB5","created_at":"2026-05-18T12:27:34Z"}],"graph_snapshots":[{"event_id":"sha256:4435eea8aceb6e8671d6251f8f04d17d81b5a280c4bbe8e2679361af5a45ca99","target":"graph","created_at":"2026-05-18T02:51:08Z","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":"We introduce a novel training principle for probabilistic models that is an alternative to maximum likelihood. The proposed Generative Stochastic Networks (GSN) framework is based on learning the transition operator of a Markov chain whose stationary distribution estimates the data distribution. The transition distribution of the Markov chain is conditional on the previous state, generally involving a small move, so this conditional distribution has fewer dominant modes, being unimodal in the limit of small moves. Thus, it is easier to learn because it is easier to approximate its partition fu","authors_text":"\\'Eric Thibodeau-Laufer, Guillaume Alain, Jason Yosinski, Yoshua Bengio","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-06-05T13:01:14Z","title":"Deep Generative Stochastic Networks Trainable by Backprop"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1306.1091","kind":"arxiv","version":5},"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":"sha256:5df55422a545183bffa24dcdd22bba6d8e06c6defd3306d412028bce0163548a","target":"record","created_at":"2026-05-18T02:51:08Z","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":"73afd14edee39ecdbbd2c3b6780f2782e581c76380075c44cd3b9e61a3ae97ab","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-06-05T13:01:14Z","title_canon_sha256":"dc12fc295c1174a22a4f4ae6a38d20f380c220de6766e850c04a14cb15cc48a6"},"schema_version":"1.0","source":{"id":"1306.1091","kind":"arxiv","version":5}},"canonical_sha256":"ef88a2643d55136e1313b43132905b3941b4f4eb2d7f9fa9b020a8551e3a8ab0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef88a2643d55136e1313b43132905b3941b4f4eb2d7f9fa9b020a8551e3a8ab0","first_computed_at":"2026-05-18T02:51:08.560385Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:51:08.560385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9sxkUStO4HRnT+V9hhaqjnfZhEWBaEBDC6lxQZRAQr9DC3/v6J94YDgiJUyH4tP+d+BO7StMOJac+HtYAOZqBw==","signature_status":"signed_v1","signed_at":"2026-05-18T02:51:08.560820Z","signed_message":"canonical_sha256_bytes"},"source_id":"1306.1091","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5df55422a545183bffa24dcdd22bba6d8e06c6defd3306d412028bce0163548a","sha256:4435eea8aceb6e8671d6251f8f04d17d81b5a280c4bbe8e2679361af5a45ca99"],"state_sha256":"26eccd23275d0d520ad520380a1dd92fa8bf3302a73fe209fb1ce14224ff33a8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8X7z2ieTil6NoaJNHKN19j0XLFNyZWaGnwkNTlIeJGMD9iGEkRNjdWh7bvkHKzGjDXsBUw4x85UN1NXVcnCfBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T12:22:54.600186Z","bundle_sha256":"fb04ef113ecafe52a10d0e2e3a71048089066c3ff279b964e11a183c19960ab9"}}