{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:KSHKSRA6DDLBWYVGHB4MA5O65E","short_pith_number":"pith:KSHKSRA6","canonical_record":{"source":{"id":"1605.08803","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-27T21:24:32Z","cross_cats_sorted":["cs.AI","cs.NE","stat.ML"],"title_canon_sha256":"5e09c8168f9e184cd9b4b962a12d2ed3900dcc804fb67834a83e67215a7202f1","abstract_canon_sha256":"15fd050b25b8790968e3fb9dbf4b188ae708e586ea08d825c7fa0e6b3e1b2c4f"},"schema_version":"1.0"},"canonical_sha256":"548ea9441e18d61b62a63878c075dee904f082a417ae46ffe5e65ea8d6abed5e","source":{"kind":"arxiv","id":"1605.08803","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.08803","created_at":"2026-07-04T21:47:27Z"},{"alias_kind":"arxiv_version","alias_value":"1605.08803v3","created_at":"2026-07-04T21:47:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.08803","created_at":"2026-07-04T21:47:27Z"},{"alias_kind":"pith_short_12","alias_value":"KSHKSRA6DDLB","created_at":"2026-07-04T21:47:27Z"},{"alias_kind":"pith_short_16","alias_value":"KSHKSRA6DDLBWYVG","created_at":"2026-07-04T21:47:27Z"},{"alias_kind":"pith_short_8","alias_value":"KSHKSRA6","created_at":"2026-07-04T21:47:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:KSHKSRA6DDLBWYVGHB4MA5O65E","target":"record","payload":{"canonical_record":{"source":{"id":"1605.08803","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-27T21:24:32Z","cross_cats_sorted":["cs.AI","cs.NE","stat.ML"],"title_canon_sha256":"5e09c8168f9e184cd9b4b962a12d2ed3900dcc804fb67834a83e67215a7202f1","abstract_canon_sha256":"15fd050b25b8790968e3fb9dbf4b188ae708e586ea08d825c7fa0e6b3e1b2c4f"},"schema_version":"1.0"},"canonical_sha256":"548ea9441e18d61b62a63878c075dee904f082a417ae46ffe5e65ea8d6abed5e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T21:47:27.716792Z","signature_b64":"xLPyn+4YCZodB3LTdSD6pVqYIrbls3FUmQk1uq2NA0gQ6LgaqCv4yxOZo6gxNr0vzmsKG8MW5SKbmhY29S2QBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"548ea9441e18d61b62a63878c075dee904f082a417ae46ffe5e65ea8d6abed5e","last_reissued_at":"2026-07-04T21:47:27.716279Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T21:47:27.716279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1605.08803","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":"2026-07-04T21:47:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BVCC+1VUHMWKjXDLrXynYS027hJ2l0vMcE9vJwgF9Fvcl9M1gNfJu4gHrvVB/4T2L/ddfhxbrPDlGghmHNnNCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T18:33:56.470020Z"},"content_sha256":"4aa545fd40bde22a154970d034518ec97d17204d834f1ea697865e14f817f79c","schema_version":"1.0","event_id":"sha256:4aa545fd40bde22a154970d034518ec97d17204d834f1ea697865e14f817f79c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:KSHKSRA6DDLBWYVGHB4MA5O65E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Density estimation using Real NVP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Real NVP transformations provide invertible mappings that make density estimation tractable with exact likelihood computation, sampling, and latent inference.","cross_cats":["cs.AI","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jascha Sohl-Dickstein, Laurent Dinh, Samy Bengio","submitted_at":"2016-05-27T21:24:32Z","abstract_excerpt":"Unsupervised learning of probabilistic models is a central yet challenging problem in machine learning. Specifically, designing models with tractable learning, sampling, inference and evaluation is crucial in solving this task. We extend the space of such models using real-valued non-volume preserving (real NVP) transformations, a set of powerful invertible and learnable transformations, resulting in an unsupervised learning algorithm with exact log-likelihood computation, exact sampling, exact inference of latent variables, and an interpretable latent space. We demonstrate its ability to mode"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We extend the space of such models using real-valued non-volume preserving (real NVP) transformations, a set of powerful invertible and learnable transformations, resulting in an unsupervised learning algorithm with exact log-likelihood computation, exact sampling, exact inference of latent variables, and an interpretable latent space.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the chosen affine coupling layers and neural-network parameterizations are expressive enough to capture the high-dimensional structure of natural images without requiring prohibitive depth or width.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Real NVP uses affine coupling layers to create invertible transformations that support exact density estimation, sampling, and latent inference without approximations.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Real NVP transformations provide invertible mappings that make density estimation tractable with exact likelihood computation, sampling, and latent inference.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"2b2b715022213d252ee25906685aa3a3d77e6d36d0d2c7dda5fc574deb9add8d"},"source":{"id":"1605.08803","kind":"arxiv","version":3},"verdict":{"id":"c59dbedf-5950-41c8-a695-14387ad2ed2e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-11T23:49:35.826368Z","strongest_claim":"We extend the space of such models using real-valued non-volume preserving (real NVP) transformations, a set of powerful invertible and learnable transformations, resulting in an unsupervised learning algorithm with exact log-likelihood computation, exact sampling, exact inference of latent variables, and an interpretable latent space.","one_line_summary":"Real NVP uses affine coupling layers to create invertible transformations that support exact density estimation, sampling, and latent inference without approximations.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the chosen affine coupling layers and neural-network parameterizations are expressive enough to capture the high-dimensional structure of natural images without requiring prohibitive depth or width.","pith_extraction_headline":"Real NVP transformations provide invertible mappings that make density estimation tractable with exact likelihood computation, sampling, and latent inference."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1605.08803/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":71,"sample":[{"doi":"","year":2016,"title":"TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems","work_id":"91f3c09e-dae6-48ca-80c0-463dd1b1f6e1","ref_index":1,"cited_arxiv_id":"1603.04467","is_internal_anchor":false},{"doi":"","year":2015,"title":"Understanding symmetries in deep networks","work_id":"a84db6a0-d054-4336-8e9b-3863537c5a9a","ref_index":2,"cited_arxiv_id":"1511.01029","is_internal_anchor":false},{"doi":"","year":2015,"title":"Density modeling of images using a generalized normalization transformation","work_id":"684ad908-be43-4653-a586-652248094887","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1995,"title":"An information-maximization approach to blind separation and blind deconvolution","work_id":"afa2377e-f961-4254-8c64-0c2bc9cbc08e","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1991,"title":"Artificial neural networks and their application to sequence recognition","work_id":"3eaa38f8-a20b-474b-81e0-56073618936b","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":71,"snapshot_sha256":"71ea32d52bd98cbf6ae8917244007e621c87fac6ac27e3aff0e6747491fddd8c","internal_anchors":16},"formal_canon":{"evidence_count":3,"snapshot_sha256":"a2bfb0380876acbcf50d76b1c7e937a529f7fa45c48d7295a23fc0f9271552b5"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"c59dbedf-5950-41c8-a695-14387ad2ed2e"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-04T21:47:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LJFBX6alh33R8YiLWvs72Mn7axPVGeMSCD7ht1m5kCgfys/i0YjoN/obSYiZp93OfF7s3yRDCZ4NjjxohJf4BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T18:33:56.470526Z"},"content_sha256":"baf64dba040a7cee3512bab509f2ff3015a8c48c1aa1b15ce457f83a72ffff1b","schema_version":"1.0","event_id":"sha256:baf64dba040a7cee3512bab509f2ff3015a8c48c1aa1b15ce457f83a72ffff1b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KSHKSRA6DDLBWYVGHB4MA5O65E/bundle.json","state_url":"https://pith.science/pith/KSHKSRA6DDLBWYVGHB4MA5O65E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KSHKSRA6DDLBWYVGHB4MA5O65E/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":"2026-08-05T18:33:56Z","links":{"resolver":"https://pith.science/pith/KSHKSRA6DDLBWYVGHB4MA5O65E","bundle":"https://pith.science/pith/KSHKSRA6DDLBWYVGHB4MA5O65E/bundle.json","state":"https://pith.science/pith/KSHKSRA6DDLBWYVGHB4MA5O65E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KSHKSRA6DDLBWYVGHB4MA5O65E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:KSHKSRA6DDLBWYVGHB4MA5O65E","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":"15fd050b25b8790968e3fb9dbf4b188ae708e586ea08d825c7fa0e6b3e1b2c4f","cross_cats_sorted":["cs.AI","cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-27T21:24:32Z","title_canon_sha256":"5e09c8168f9e184cd9b4b962a12d2ed3900dcc804fb67834a83e67215a7202f1"},"schema_version":"1.0","source":{"id":"1605.08803","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.08803","created_at":"2026-07-04T21:47:27Z"},{"alias_kind":"arxiv_version","alias_value":"1605.08803v3","created_at":"2026-07-04T21:47:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.08803","created_at":"2026-07-04T21:47:27Z"},{"alias_kind":"pith_short_12","alias_value":"KSHKSRA6DDLB","created_at":"2026-07-04T21:47:27Z"},{"alias_kind":"pith_short_16","alias_value":"KSHKSRA6DDLBWYVG","created_at":"2026-07-04T21:47:27Z"},{"alias_kind":"pith_short_8","alias_value":"KSHKSRA6","created_at":"2026-07-04T21:47:27Z"}],"graph_snapshots":[{"event_id":"sha256:baf64dba040a7cee3512bab509f2ff3015a8c48c1aa1b15ce457f83a72ffff1b","target":"graph","created_at":"2026-07-04T21:47:27Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"We extend the space of such models using real-valued non-volume preserving (real NVP) transformations, a set of powerful invertible and learnable transformations, resulting in an unsupervised learning algorithm with exact log-likelihood computation, exact sampling, exact inference of latent variables, and an interpretable latent space."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the chosen affine coupling layers and neural-network parameterizations are expressive enough to capture the high-dimensional structure of natural images without requiring prohibitive depth or width."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Real NVP uses affine coupling layers to create invertible transformations that support exact density estimation, sampling, and latent inference without approximations."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Real NVP transformations provide invertible mappings that make density estimation tractable with exact likelihood computation, sampling, and latent inference."}],"snapshot_sha256":"2b2b715022213d252ee25906685aa3a3d77e6d36d0d2c7dda5fc574deb9add8d"},"formal_canon":{"evidence_count":3,"snapshot_sha256":"a2bfb0380876acbcf50d76b1c7e937a529f7fa45c48d7295a23fc0f9271552b5"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1605.08803/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unsupervised learning of probabilistic models is a central yet challenging problem in machine learning. Specifically, designing models with tractable learning, sampling, inference and evaluation is crucial in solving this task. We extend the space of such models using real-valued non-volume preserving (real NVP) transformations, a set of powerful invertible and learnable transformations, resulting in an unsupervised learning algorithm with exact log-likelihood computation, exact sampling, exact inference of latent variables, and an interpretable latent space. We demonstrate its ability to mode","authors_text":"Jascha Sohl-Dickstein, Laurent Dinh, Samy Bengio","cross_cats":["cs.AI","cs.NE","stat.ML"],"headline":"Real NVP transformations provide invertible mappings that make density estimation tractable with exact likelihood computation, sampling, and latent inference.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-27T21:24:32Z","title":"Density estimation using Real NVP"},"references":{"count":71,"internal_anchors":16,"resolved_work":71,"sample":[{"cited_arxiv_id":"1603.04467","doi":"","is_internal_anchor":false,"ref_index":1,"title":"TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems","work_id":"91f3c09e-dae6-48ca-80c0-463dd1b1f6e1","year":2016},{"cited_arxiv_id":"1511.01029","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Understanding symmetries in deep networks","work_id":"a84db6a0-d054-4336-8e9b-3863537c5a9a","year":2015},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Density modeling of images using a generalized normalization transformation","work_id":"684ad908-be43-4653-a586-652248094887","year":2015},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"An information-maximization approach to blind separation and blind deconvolution","work_id":"afa2377e-f961-4254-8c64-0c2bc9cbc08e","year":1995},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Artificial neural networks and their application to sequence recognition","work_id":"3eaa38f8-a20b-474b-81e0-56073618936b","year":1991}],"snapshot_sha256":"71ea32d52bd98cbf6ae8917244007e621c87fac6ac27e3aff0e6747491fddd8c"},"source":{"id":"1605.08803","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-11T23:49:35.826368Z","id":"c59dbedf-5950-41c8-a695-14387ad2ed2e","model_set":{"reader":"grok-4.3"},"one_line_summary":"Real NVP uses affine coupling layers to create invertible transformations that support exact density estimation, sampling, and latent inference without approximations.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Real NVP transformations provide invertible mappings that make density estimation tractable with exact likelihood computation, sampling, and latent inference.","strongest_claim":"We extend the space of such models using real-valued non-volume preserving (real NVP) transformations, a set of powerful invertible and learnable transformations, resulting in an unsupervised learning algorithm with exact log-likelihood computation, exact sampling, exact inference of latent variables, and an interpretable latent space.","weakest_assumption":"That the chosen affine coupling layers and neural-network parameterizations are expressive enough to capture the high-dimensional structure of natural images without requiring prohibitive depth or width."}},"verdict_id":"c59dbedf-5950-41c8-a695-14387ad2ed2e"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4aa545fd40bde22a154970d034518ec97d17204d834f1ea697865e14f817f79c","target":"record","created_at":"2026-07-04T21:47:27Z","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":"15fd050b25b8790968e3fb9dbf4b188ae708e586ea08d825c7fa0e6b3e1b2c4f","cross_cats_sorted":["cs.AI","cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-27T21:24:32Z","title_canon_sha256":"5e09c8168f9e184cd9b4b962a12d2ed3900dcc804fb67834a83e67215a7202f1"},"schema_version":"1.0","source":{"id":"1605.08803","kind":"arxiv","version":3}},"canonical_sha256":"548ea9441e18d61b62a63878c075dee904f082a417ae46ffe5e65ea8d6abed5e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"548ea9441e18d61b62a63878c075dee904f082a417ae46ffe5e65ea8d6abed5e","first_computed_at":"2026-07-04T21:47:27.716279Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T21:47:27.716279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xLPyn+4YCZodB3LTdSD6pVqYIrbls3FUmQk1uq2NA0gQ6LgaqCv4yxOZo6gxNr0vzmsKG8MW5SKbmhY29S2QBg==","signature_status":"signed_v1","signed_at":"2026-07-04T21:47:27.716792Z","signed_message":"canonical_sha256_bytes"},"source_id":"1605.08803","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4aa545fd40bde22a154970d034518ec97d17204d834f1ea697865e14f817f79c","sha256:baf64dba040a7cee3512bab509f2ff3015a8c48c1aa1b15ce457f83a72ffff1b"],"state_sha256":"d73987b6edaa1989c48f18fff04ca7d3eb704e8761aeaf642b4e7051bf4ddecf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VpR/fKHe5cRo55N0Mwak/fry+f+7yWojJx7aQUELyIIpslRHf8TtACHT1BsIC3Un5iKlmXEIYRtwZLT6YAVLDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T18:33:56.474790Z","bundle_sha256":"d312a79bb52c66959deef02171fd176d122fa5e83f5e3a63aede7fc723a5ef8d"}}