{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:7SMSLWTM6A7WAQM2OQPOAMKVPI","short_pith_number":"pith:7SMSLWTM","canonical_record":{"source":{"id":"2010.13476","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-26T10:43:28Z","cross_cats_sorted":[],"title_canon_sha256":"ae60004efc36a2d3b41b5a7e5d95d6ba2cbcf15ad67c6c7a717234f799115832","abstract_canon_sha256":"bdccea32da5a79d54d195882547515ded6374c47ce459689eb475c3c8b73b0c5"},"schema_version":"1.0"},"canonical_sha256":"fc9925da6cf03f60419a741ee031557a1e73e4f744928f6cf5398b6e8e35d64d","source":{"kind":"arxiv","id":"2010.13476","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.13476","created_at":"2026-07-05T02:37:06Z"},{"alias_kind":"arxiv_version","alias_value":"2010.13476v2","created_at":"2026-07-05T02:37:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.13476","created_at":"2026-07-05T02:37:06Z"},{"alias_kind":"pith_short_12","alias_value":"7SMSLWTM6A7W","created_at":"2026-07-05T02:37:06Z"},{"alias_kind":"pith_short_16","alias_value":"7SMSLWTM6A7WAQM2","created_at":"2026-07-05T02:37:06Z"},{"alias_kind":"pith_short_8","alias_value":"7SMSLWTM","created_at":"2026-07-05T02:37:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:7SMSLWTM6A7WAQM2OQPOAMKVPI","target":"record","payload":{"canonical_record":{"source":{"id":"2010.13476","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-26T10:43:28Z","cross_cats_sorted":[],"title_canon_sha256":"ae60004efc36a2d3b41b5a7e5d95d6ba2cbcf15ad67c6c7a717234f799115832","abstract_canon_sha256":"bdccea32da5a79d54d195882547515ded6374c47ce459689eb475c3c8b73b0c5"},"schema_version":"1.0"},"canonical_sha256":"fc9925da6cf03f60419a741ee031557a1e73e4f744928f6cf5398b6e8e35d64d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:37:06.606873Z","signature_b64":"Dz8VxXkkuqj5gXabgBDpDl5SFTLXGKbFzGPG+wJQx8P5abmxB7a6SQFGbZkElfRe3D23+kOhL6VRpXxBx81ODQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc9925da6cf03f60419a741ee031557a1e73e4f744928f6cf5398b6e8e35d64d","last_reissued_at":"2026-07-05T02:37:06.606390Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:37:06.606390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.13476","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":"2026-07-05T02:37:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GlZprExxHMIe2yWDALtRJ6H2UmaNpJw7tWpZre2EkkdKWprKNa5pAf11VaxEZ0ZApX8b0ZwlpCqh0aSi/sYgBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T03:31:47.383962Z"},"content_sha256":"998d0153e1cc02329b81a37d214be0995dec1b8799e377cebae9b4eeaa111b74","schema_version":"1.0","event_id":"sha256:998d0153e1cc02329b81a37d214be0995dec1b8799e377cebae9b4eeaa111b74"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:7SMSLWTM6A7WAQM2OQPOAMKVPI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reducing the Computational Cost of Deep Generative Models with Binary Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"David Barber, Friso H. Kingma, Thomas Bird","submitted_at":"2020-10-26T10:43:28Z","abstract_excerpt":"Deep generative models provide a powerful set of tools to understand real-world data. But as these models improve, they increase in size and complexity, so their computational cost in memory and execution time grows. Using binary weights in neural networks is one method which has shown promise in reducing this cost. However, whether binary neural networks can be used in generative models is an open problem. In this work we show, for the first time, that we can successfully train generative models which utilize binary neural networks. This reduces the computational cost of the models massively."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.13476","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2010.13476/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T02:37:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vrtrA3zfq/y/ye2rZ7x/ryI8eh+CS/UZzByr0eJ6b2MXeBF09d99L5pgVeZv5iyTviJfKjOD4HR8Tm/wHhrtAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T03:31:47.384896Z"},"content_sha256":"6e163a78cec3a65ab2468368587b0368faa3b9da5764a13e784c2fe2d0766c8d","schema_version":"1.0","event_id":"sha256:6e163a78cec3a65ab2468368587b0368faa3b9da5764a13e784c2fe2d0766c8d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7SMSLWTM6A7WAQM2OQPOAMKVPI/bundle.json","state_url":"https://pith.science/pith/7SMSLWTM6A7WAQM2OQPOAMKVPI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7SMSLWTM6A7WAQM2OQPOAMKVPI/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":"2026-08-18T03:31:47Z","links":{"resolver":"https://pith.science/pith/7SMSLWTM6A7WAQM2OQPOAMKVPI","bundle":"https://pith.science/pith/7SMSLWTM6A7WAQM2OQPOAMKVPI/bundle.json","state":"https://pith.science/pith/7SMSLWTM6A7WAQM2OQPOAMKVPI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7SMSLWTM6A7WAQM2OQPOAMKVPI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:7SMSLWTM6A7WAQM2OQPOAMKVPI","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":"bdccea32da5a79d54d195882547515ded6374c47ce459689eb475c3c8b73b0c5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-26T10:43:28Z","title_canon_sha256":"ae60004efc36a2d3b41b5a7e5d95d6ba2cbcf15ad67c6c7a717234f799115832"},"schema_version":"1.0","source":{"id":"2010.13476","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.13476","created_at":"2026-07-05T02:37:06Z"},{"alias_kind":"arxiv_version","alias_value":"2010.13476v2","created_at":"2026-07-05T02:37:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.13476","created_at":"2026-07-05T02:37:06Z"},{"alias_kind":"pith_short_12","alias_value":"7SMSLWTM6A7W","created_at":"2026-07-05T02:37:06Z"},{"alias_kind":"pith_short_16","alias_value":"7SMSLWTM6A7WAQM2","created_at":"2026-07-05T02:37:06Z"},{"alias_kind":"pith_short_8","alias_value":"7SMSLWTM","created_at":"2026-07-05T02:37:06Z"}],"graph_snapshots":[{"event_id":"sha256:6e163a78cec3a65ab2468368587b0368faa3b9da5764a13e784c2fe2d0766c8d","target":"graph","created_at":"2026-07-05T02:37:06Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2010.13476/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep generative models provide a powerful set of tools to understand real-world data. But as these models improve, they increase in size and complexity, so their computational cost in memory and execution time grows. Using binary weights in neural networks is one method which has shown promise in reducing this cost. However, whether binary neural networks can be used in generative models is an open problem. In this work we show, for the first time, that we can successfully train generative models which utilize binary neural networks. This reduces the computational cost of the models massively.","authors_text":"David Barber, Friso H. Kingma, Thomas Bird","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-26T10:43:28Z","title":"Reducing the Computational Cost of Deep Generative Models with Binary Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.13476","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":"sha256:998d0153e1cc02329b81a37d214be0995dec1b8799e377cebae9b4eeaa111b74","target":"record","created_at":"2026-07-05T02:37:06Z","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":"bdccea32da5a79d54d195882547515ded6374c47ce459689eb475c3c8b73b0c5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-26T10:43:28Z","title_canon_sha256":"ae60004efc36a2d3b41b5a7e5d95d6ba2cbcf15ad67c6c7a717234f799115832"},"schema_version":"1.0","source":{"id":"2010.13476","kind":"arxiv","version":2}},"canonical_sha256":"fc9925da6cf03f60419a741ee031557a1e73e4f744928f6cf5398b6e8e35d64d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc9925da6cf03f60419a741ee031557a1e73e4f744928f6cf5398b6e8e35d64d","first_computed_at":"2026-07-05T02:37:06.606390Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:37:06.606390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Dz8VxXkkuqj5gXabgBDpDl5SFTLXGKbFzGPG+wJQx8P5abmxB7a6SQFGbZkElfRe3D23+kOhL6VRpXxBx81ODQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:37:06.606873Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.13476","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:998d0153e1cc02329b81a37d214be0995dec1b8799e377cebae9b4eeaa111b74","sha256:6e163a78cec3a65ab2468368587b0368faa3b9da5764a13e784c2fe2d0766c8d"],"state_sha256":"c6eba0e7932b418ececb116cd3c1b61c2ccdec55235d250292a35986ccfcd149"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A76I0lUOKo5X9KdKHwwn7/oNc+kdip2hDTsYLFkKqHNhTQy9mXynxiw2DQsX4nZ659BgDh76+gwwA0hmGqdVAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T03:31:47.450442Z","bundle_sha256":"67856dbc83d8cc293e17d84a5333c5de2df02ed5db6d4ad498c625e78e915840"}}