{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:CZZJURM733SBHCCR7SKOBNIONB","short_pith_number":"pith:CZZJURM7","canonical_record":{"source":{"id":"2106.05931","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-06-10T17:26:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c284d5cca5f646a80fa4ce756d60d2a8fc585c71a198b2217f195492ec6dbeb6","abstract_canon_sha256":"d5d4ea9d0c817fa0ffd6cceae67feb936bc98441474ea803a1fc2e0a8c6ed33e"},"schema_version":"1.0"},"canonical_sha256":"16729a459fdee4138851fc94e0b50e68519937d566f57f8fedfac8da2ce4bdbc","source":{"kind":"arxiv","id":"2106.05931","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.05931","created_at":"2026-07-05T03:36:54Z"},{"alias_kind":"arxiv_version","alias_value":"2106.05931v3","created_at":"2026-07-05T03:36:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.05931","created_at":"2026-07-05T03:36:54Z"},{"alias_kind":"pith_short_12","alias_value":"CZZJURM733SB","created_at":"2026-07-05T03:36:54Z"},{"alias_kind":"pith_short_16","alias_value":"CZZJURM733SBHCCR","created_at":"2026-07-05T03:36:54Z"},{"alias_kind":"pith_short_8","alias_value":"CZZJURM7","created_at":"2026-07-05T03:36:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:CZZJURM733SBHCCR7SKOBNIONB","target":"record","payload":{"canonical_record":{"source":{"id":"2106.05931","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-06-10T17:26:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c284d5cca5f646a80fa4ce756d60d2a8fc585c71a198b2217f195492ec6dbeb6","abstract_canon_sha256":"d5d4ea9d0c817fa0ffd6cceae67feb936bc98441474ea803a1fc2e0a8c6ed33e"},"schema_version":"1.0"},"canonical_sha256":"16729a459fdee4138851fc94e0b50e68519937d566f57f8fedfac8da2ce4bdbc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:36:54.788605Z","signature_b64":"HSBF9eEvTSr1hHp8ika9Z0KFYKNKB3YQt15luI2zb5wmD31eQTXsjqK2cv5gfRi548qNUtVXm6mFYIgUkMxtAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16729a459fdee4138851fc94e0b50e68519937d566f57f8fedfac8da2ce4bdbc","last_reissued_at":"2026-07-05T03:36:54.788104Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:36:54.788104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.05931","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:36:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KrQTXoD69yhlO01IBYKzVa37ks88g4bbuM+k8LAF66+TorbJt6vcr5ClDC2c0LL+jQf46Vqt0KjN7o5QCwV7CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:47:22.139178Z"},"content_sha256":"0b3c05aa0bb8b56818bbcdc17502116fc2702734cb7459ef4f86be3c04fca468","schema_version":"1.0","event_id":"sha256:0b3c05aa0bb8b56818bbcdc17502116fc2702734cb7459ef4f86be3c04fca468"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:CZZJURM733SBHCCR7SKOBNIONB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Score-based Generative Modeling in Latent Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Arash Vahdat, Jan Kautz, Karsten Kreis","submitted_at":"2021-06-10T17:26:35Z","abstract_excerpt":"Score-based generative models (SGMs) have recently demonstrated impressive results in terms of both sample quality and distribution coverage. However, they are usually applied directly in data space and often require thousands of network evaluations for sampling. Here, we propose the Latent Score-based Generative Model (LSGM), a novel approach that trains SGMs in a latent space, relying on the variational autoencoder framework. Moving from data to latent space allows us to train more expressive generative models, apply SGMs to non-continuous data, and learn smoother SGMs in a smaller space, re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.05931","kind":"arxiv","version":3},"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/2106.05931/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":"2026-07-05T03:36:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bjkl4s8XRblDCY9dOqcUbNZsLNAuXjqC0cBT1SRKLfoQV8y2i6vck8CH3B+1FL0LG+SiVk6VQeHB7ZL7iRScDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:47:22.139556Z"},"content_sha256":"4bcdb78ab5ec1cad11dbc3430e4c79ec3ff27473ae4fc3e448577fe570ece1e7","schema_version":"1.0","event_id":"sha256:4bcdb78ab5ec1cad11dbc3430e4c79ec3ff27473ae4fc3e448577fe570ece1e7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CZZJURM733SBHCCR7SKOBNIONB/bundle.json","state_url":"https://pith.science/pith/CZZJURM733SBHCCR7SKOBNIONB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CZZJURM733SBHCCR7SKOBNIONB/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":"2026-07-07T14:47:22Z","links":{"resolver":"https://pith.science/pith/CZZJURM733SBHCCR7SKOBNIONB","bundle":"https://pith.science/pith/CZZJURM733SBHCCR7SKOBNIONB/bundle.json","state":"https://pith.science/pith/CZZJURM733SBHCCR7SKOBNIONB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CZZJURM733SBHCCR7SKOBNIONB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:CZZJURM733SBHCCR7SKOBNIONB","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":"d5d4ea9d0c817fa0ffd6cceae67feb936bc98441474ea803a1fc2e0a8c6ed33e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-06-10T17:26:35Z","title_canon_sha256":"c284d5cca5f646a80fa4ce756d60d2a8fc585c71a198b2217f195492ec6dbeb6"},"schema_version":"1.0","source":{"id":"2106.05931","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.05931","created_at":"2026-07-05T03:36:54Z"},{"alias_kind":"arxiv_version","alias_value":"2106.05931v3","created_at":"2026-07-05T03:36:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.05931","created_at":"2026-07-05T03:36:54Z"},{"alias_kind":"pith_short_12","alias_value":"CZZJURM733SB","created_at":"2026-07-05T03:36:54Z"},{"alias_kind":"pith_short_16","alias_value":"CZZJURM733SBHCCR","created_at":"2026-07-05T03:36:54Z"},{"alias_kind":"pith_short_8","alias_value":"CZZJURM7","created_at":"2026-07-05T03:36:54Z"}],"graph_snapshots":[{"event_id":"sha256:4bcdb78ab5ec1cad11dbc3430e4c79ec3ff27473ae4fc3e448577fe570ece1e7","target":"graph","created_at":"2026-07-05T03:36:54Z","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/2106.05931/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Score-based generative models (SGMs) have recently demonstrated impressive results in terms of both sample quality and distribution coverage. However, they are usually applied directly in data space and often require thousands of network evaluations for sampling. Here, we propose the Latent Score-based Generative Model (LSGM), a novel approach that trains SGMs in a latent space, relying on the variational autoencoder framework. Moving from data to latent space allows us to train more expressive generative models, apply SGMs to non-continuous data, and learn smoother SGMs in a smaller space, re","authors_text":"Arash Vahdat, Jan Kautz, Karsten Kreis","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-06-10T17:26:35Z","title":"Score-based Generative Modeling in Latent Space"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.05931","kind":"arxiv","version":3},"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":"sha256:0b3c05aa0bb8b56818bbcdc17502116fc2702734cb7459ef4f86be3c04fca468","target":"record","created_at":"2026-07-05T03:36:54Z","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":"d5d4ea9d0c817fa0ffd6cceae67feb936bc98441474ea803a1fc2e0a8c6ed33e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-06-10T17:26:35Z","title_canon_sha256":"c284d5cca5f646a80fa4ce756d60d2a8fc585c71a198b2217f195492ec6dbeb6"},"schema_version":"1.0","source":{"id":"2106.05931","kind":"arxiv","version":3}},"canonical_sha256":"16729a459fdee4138851fc94e0b50e68519937d566f57f8fedfac8da2ce4bdbc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"16729a459fdee4138851fc94e0b50e68519937d566f57f8fedfac8da2ce4bdbc","first_computed_at":"2026-07-05T03:36:54.788104Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:36:54.788104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HSBF9eEvTSr1hHp8ika9Z0KFYKNKB3YQt15luI2zb5wmD31eQTXsjqK2cv5gfRi548qNUtVXm6mFYIgUkMxtAA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:36:54.788605Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.05931","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b3c05aa0bb8b56818bbcdc17502116fc2702734cb7459ef4f86be3c04fca468","sha256:4bcdb78ab5ec1cad11dbc3430e4c79ec3ff27473ae4fc3e448577fe570ece1e7"],"state_sha256":"d497c390eec28eac44d6c5f1ad01e683d724ef88c0d5769d50c319addb5dafa6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/EXzUOSNQ4IUJbPyzcKSrA9TvOaWgeuxwPQx0a/ugyvoO31khWAmegcty5qji9dCUR8BVwMGyuCvaEKf6BpJDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T14:47:22.141440Z","bundle_sha256":"35c04dd4671d214588f10db05e61d458308c1c38affcb46ef6799af033430a5d"}}