{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:JYC2Z74BQGJK2WLLKVEA4YODZ4","short_pith_number":"pith:JYC2Z74B","canonical_record":{"source":{"id":"1602.07416","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-24T06:57:14Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"8652d7d9ab48104cc0e7e11932770bfc8f291eee8fbbc14dbab8d8e118092c00","abstract_canon_sha256":"4367e857b51ae054cf47ac8d93463d20b465f834d9e1b082d98277ca0151aac4"},"schema_version":"1.0"},"canonical_sha256":"4e05acff818192ad596b55480e61c3cf12753f371105a17dacc4259523713b7e","source":{"kind":"arxiv","id":"1602.07416","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.07416","created_at":"2026-05-18T01:13:23Z"},{"alias_kind":"arxiv_version","alias_value":"1602.07416v2","created_at":"2026-05-18T01:13:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.07416","created_at":"2026-05-18T01:13:23Z"},{"alias_kind":"pith_short_12","alias_value":"JYC2Z74BQGJK","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_16","alias_value":"JYC2Z74BQGJK2WLL","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_8","alias_value":"JYC2Z74B","created_at":"2026-05-18T12:30:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:JYC2Z74BQGJK2WLLKVEA4YODZ4","target":"record","payload":{"canonical_record":{"source":{"id":"1602.07416","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-24T06:57:14Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"8652d7d9ab48104cc0e7e11932770bfc8f291eee8fbbc14dbab8d8e118092c00","abstract_canon_sha256":"4367e857b51ae054cf47ac8d93463d20b465f834d9e1b082d98277ca0151aac4"},"schema_version":"1.0"},"canonical_sha256":"4e05acff818192ad596b55480e61c3cf12753f371105a17dacc4259523713b7e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:13:23.614764Z","signature_b64":"Wehy6hKHkcibvtf+NekZVMzL4ppYqWERucUX58n+t4hdSTxe9/ENK0j20uhgvBSrUQQZNMJtDKDCEJ9kxEkoCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e05acff818192ad596b55480e61c3cf12753f371105a17dacc4259523713b7e","last_reissued_at":"2026-05-18T01:13:23.614168Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:13:23.614168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1602.07416","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":"2026-05-18T01:13:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EYNw4WdGYRhvJ86WioOT1X392iJqMCZMifU7cdcBG+VzNskrkiPdV51LeeVMofYyCXtOa7c5oJgk1JApdfzQAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T17:49:01.317444Z"},"content_sha256":"c12db7d9b2f423683bb78fd58c6f4da3627dd857cc465db42ac3a8568e6baf18","schema_version":"1.0","event_id":"sha256:c12db7d9b2f423683bb78fd58c6f4da3627dd857cc465db42ac3a8568e6baf18"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:JYC2Z74BQGJK2WLLKVEA4YODZ4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Generate with Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Bo Zhang, Chongxuan Li, Jun Zhu","submitted_at":"2016-02-24T06:57:14Z","abstract_excerpt":"Memory units have been widely used to enrich the capabilities of deep networks on capturing long-term dependencies in reasoning and prediction tasks, but little investigation exists on deep generative models (DGMs) which are good at inferring high-level invariant representations from unlabeled data. This paper presents a deep generative model with a possibly large external memory and an attention mechanism to capture the local detail information that is often lost in the bottom-up abstraction process in representation learning. By adopting a smooth attention model, the whole network is trained"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.07416","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":"2026-05-18T01:13:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PsAHkkH9YkaoYq627RA5PMgsMRXoGaUWnP/afqmGz56PGOJFZicD8zcOQmovfwi2om9DTAR3snfRuO44zEfXAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T17:49:01.317801Z"},"content_sha256":"cabfea573a23d25bc189499a25b9219f34a5e47f8519cff18028f36a4376f4b2","schema_version":"1.0","event_id":"sha256:cabfea573a23d25bc189499a25b9219f34a5e47f8519cff18028f36a4376f4b2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JYC2Z74BQGJK2WLLKVEA4YODZ4/bundle.json","state_url":"https://pith.science/pith/JYC2Z74BQGJK2WLLKVEA4YODZ4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JYC2Z74BQGJK2WLLKVEA4YODZ4/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":"2026-05-30T17:49:01Z","links":{"resolver":"https://pith.science/pith/JYC2Z74BQGJK2WLLKVEA4YODZ4","bundle":"https://pith.science/pith/JYC2Z74BQGJK2WLLKVEA4YODZ4/bundle.json","state":"https://pith.science/pith/JYC2Z74BQGJK2WLLKVEA4YODZ4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JYC2Z74BQGJK2WLLKVEA4YODZ4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:JYC2Z74BQGJK2WLLKVEA4YODZ4","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":"4367e857b51ae054cf47ac8d93463d20b465f834d9e1b082d98277ca0151aac4","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-24T06:57:14Z","title_canon_sha256":"8652d7d9ab48104cc0e7e11932770bfc8f291eee8fbbc14dbab8d8e118092c00"},"schema_version":"1.0","source":{"id":"1602.07416","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.07416","created_at":"2026-05-18T01:13:23Z"},{"alias_kind":"arxiv_version","alias_value":"1602.07416v2","created_at":"2026-05-18T01:13:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.07416","created_at":"2026-05-18T01:13:23Z"},{"alias_kind":"pith_short_12","alias_value":"JYC2Z74BQGJK","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_16","alias_value":"JYC2Z74BQGJK2WLL","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_8","alias_value":"JYC2Z74B","created_at":"2026-05-18T12:30:25Z"}],"graph_snapshots":[{"event_id":"sha256:cabfea573a23d25bc189499a25b9219f34a5e47f8519cff18028f36a4376f4b2","target":"graph","created_at":"2026-05-18T01:13:23Z","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":"Memory units have been widely used to enrich the capabilities of deep networks on capturing long-term dependencies in reasoning and prediction tasks, but little investigation exists on deep generative models (DGMs) which are good at inferring high-level invariant representations from unlabeled data. This paper presents a deep generative model with a possibly large external memory and an attention mechanism to capture the local detail information that is often lost in the bottom-up abstraction process in representation learning. By adopting a smooth attention model, the whole network is trained","authors_text":"Bo Zhang, Chongxuan Li, Jun Zhu","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-24T06:57:14Z","title":"Learning to Generate with Memory"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.07416","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:c12db7d9b2f423683bb78fd58c6f4da3627dd857cc465db42ac3a8568e6baf18","target":"record","created_at":"2026-05-18T01:13:23Z","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":"4367e857b51ae054cf47ac8d93463d20b465f834d9e1b082d98277ca0151aac4","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-24T06:57:14Z","title_canon_sha256":"8652d7d9ab48104cc0e7e11932770bfc8f291eee8fbbc14dbab8d8e118092c00"},"schema_version":"1.0","source":{"id":"1602.07416","kind":"arxiv","version":2}},"canonical_sha256":"4e05acff818192ad596b55480e61c3cf12753f371105a17dacc4259523713b7e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4e05acff818192ad596b55480e61c3cf12753f371105a17dacc4259523713b7e","first_computed_at":"2026-05-18T01:13:23.614168Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:13:23.614168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Wehy6hKHkcibvtf+NekZVMzL4ppYqWERucUX58n+t4hdSTxe9/ENK0j20uhgvBSrUQQZNMJtDKDCEJ9kxEkoCw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:13:23.614764Z","signed_message":"canonical_sha256_bytes"},"source_id":"1602.07416","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c12db7d9b2f423683bb78fd58c6f4da3627dd857cc465db42ac3a8568e6baf18","sha256:cabfea573a23d25bc189499a25b9219f34a5e47f8519cff18028f36a4376f4b2"],"state_sha256":"3db6e15637d285ff87ed8faab9a9571a5af001d9d31f821110ad5c528ad30547"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wHmvQ0GgxDyIGx2Bgy4VFRphWB5GCRojZMQfEhSiubkG++dTIcBo/dNK8r3WH4qU/D+qTmG/QiI8ICxhv7QqBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T17:49:01.319942Z","bundle_sha256":"235e685fdfcb4549e7e2daab4156f900993208bd2984038c96e56ce3f74e60c2"}}