{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ISBB6EUOV7ONXWVZM62DDYW2YJ","short_pith_number":"pith:ISBB6EUO","canonical_record":{"source":{"id":"2102.02374","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-04T02:21:08Z","cross_cats_sorted":[],"title_canon_sha256":"b3ab9ac6d2d56334c9cc5bbee268b6f888fecb4e81c229a937cb668a8c421acb","abstract_canon_sha256":"042e2540c55beee85be19f39a583f72a823cc07bc1cf519d0f8753f50dcb34b3"},"schema_version":"1.0"},"canonical_sha256":"44821f128eafdcdbdab967b431e2dac25fb8cbaa7ae4b642cf64921010e8992d","source":{"kind":"arxiv","id":"2102.02374","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.02374","created_at":"2026-07-05T02:18:59Z"},{"alias_kind":"arxiv_version","alias_value":"2102.02374v2","created_at":"2026-07-05T02:18:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.02374","created_at":"2026-07-05T02:18:59Z"},{"alias_kind":"pith_short_12","alias_value":"ISBB6EUOV7ON","created_at":"2026-07-05T02:18:59Z"},{"alias_kind":"pith_short_16","alias_value":"ISBB6EUOV7ONXWVZ","created_at":"2026-07-05T02:18:59Z"},{"alias_kind":"pith_short_8","alias_value":"ISBB6EUO","created_at":"2026-07-05T02:18:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ISBB6EUOV7ONXWVZM62DDYW2YJ","target":"record","payload":{"canonical_record":{"source":{"id":"2102.02374","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-04T02:21:08Z","cross_cats_sorted":[],"title_canon_sha256":"b3ab9ac6d2d56334c9cc5bbee268b6f888fecb4e81c229a937cb668a8c421acb","abstract_canon_sha256":"042e2540c55beee85be19f39a583f72a823cc07bc1cf519d0f8753f50dcb34b3"},"schema_version":"1.0"},"canonical_sha256":"44821f128eafdcdbdab967b431e2dac25fb8cbaa7ae4b642cf64921010e8992d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:18:59.680165Z","signature_b64":"KRi/bVDJEjKIhCC43N7YZy0HwWgtWRu+13Dt5rLpqph5hNJEm3wlMVptdeFeL8gUEQnOHKcYQacuKtrX1Zi6DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44821f128eafdcdbdab967b431e2dac25fb8cbaa7ae4b642cf64921010e8992d","last_reissued_at":"2026-07-05T02:18:59.679750Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:18:59.679750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.02374","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":"2026-07-05T02:18:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EmmfIHThRXSG7PAXxwZ7SV8xTPIH1ZBzFeMECfl+CY69dQXOjpp+RvZXN9IggQWXN6HtxVj/euOio9gr6FOyCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:36:06.554802Z"},"content_sha256":"7cb25d0a14d9697c7703b0aab8fa8799e53073d89d92f7fec513ed3192b01997","schema_version":"1.0","event_id":"sha256:7cb25d0a14d9697c7703b0aab8fa8799e53073d89d92f7fec513ed3192b01997"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ISBB6EUOV7ONXWVZM62DDYW2YJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sampling in Combinatorial Spaces with SurVAE Flow Augmented MCMC","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Didrik Nielsen, Max Welling, Priyank Jaini","submitted_at":"2021-02-04T02:21:08Z","abstract_excerpt":"Hybrid Monte Carlo is a powerful Markov Chain Monte Carlo method for sampling from complex continuous distributions. However, a major limitation of HMC is its inability to be applied to discrete domains due to the lack of gradient signal. In this work, we introduce a new approach based on augmenting Monte Carlo methods with SurVAE Flows to sample from discrete distributions using a combination of neural transport methods like normalizing flows and variational dequantization, and the Metropolis-Hastings rule. Our method first learns a continuous embedding of the discrete space using a surjectiv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.02374","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/2102.02374/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":"2026-07-05T02:18:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2OjCWJmADapWZEDA3iAg846AWscWKxEPpRRvwSJxOM1GaaHF8QTyQb6qako1H5l4rF4n+ERgj8XyBaAMOGrMDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:36:06.555356Z"},"content_sha256":"526ad4db5d8c94bfbab8bd0c7068fa46d0f00433aaa612bdf646bf7f23fe0582","schema_version":"1.0","event_id":"sha256:526ad4db5d8c94bfbab8bd0c7068fa46d0f00433aaa612bdf646bf7f23fe0582"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ISBB6EUOV7ONXWVZM62DDYW2YJ/bundle.json","state_url":"https://pith.science/pith/ISBB6EUOV7ONXWVZM62DDYW2YJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ISBB6EUOV7ONXWVZM62DDYW2YJ/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":"2026-08-04T21:36:06Z","links":{"resolver":"https://pith.science/pith/ISBB6EUOV7ONXWVZM62DDYW2YJ","bundle":"https://pith.science/pith/ISBB6EUOV7ONXWVZM62DDYW2YJ/bundle.json","state":"https://pith.science/pith/ISBB6EUOV7ONXWVZM62DDYW2YJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ISBB6EUOV7ONXWVZM62DDYW2YJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ISBB6EUOV7ONXWVZM62DDYW2YJ","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":"042e2540c55beee85be19f39a583f72a823cc07bc1cf519d0f8753f50dcb34b3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-04T02:21:08Z","title_canon_sha256":"b3ab9ac6d2d56334c9cc5bbee268b6f888fecb4e81c229a937cb668a8c421acb"},"schema_version":"1.0","source":{"id":"2102.02374","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.02374","created_at":"2026-07-05T02:18:59Z"},{"alias_kind":"arxiv_version","alias_value":"2102.02374v2","created_at":"2026-07-05T02:18:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.02374","created_at":"2026-07-05T02:18:59Z"},{"alias_kind":"pith_short_12","alias_value":"ISBB6EUOV7ON","created_at":"2026-07-05T02:18:59Z"},{"alias_kind":"pith_short_16","alias_value":"ISBB6EUOV7ONXWVZ","created_at":"2026-07-05T02:18:59Z"},{"alias_kind":"pith_short_8","alias_value":"ISBB6EUO","created_at":"2026-07-05T02:18:59Z"}],"graph_snapshots":[{"event_id":"sha256:526ad4db5d8c94bfbab8bd0c7068fa46d0f00433aaa612bdf646bf7f23fe0582","target":"graph","created_at":"2026-07-05T02:18:59Z","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/2102.02374/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hybrid Monte Carlo is a powerful Markov Chain Monte Carlo method for sampling from complex continuous distributions. However, a major limitation of HMC is its inability to be applied to discrete domains due to the lack of gradient signal. In this work, we introduce a new approach based on augmenting Monte Carlo methods with SurVAE Flows to sample from discrete distributions using a combination of neural transport methods like normalizing flows and variational dequantization, and the Metropolis-Hastings rule. Our method first learns a continuous embedding of the discrete space using a surjectiv","authors_text":"Didrik Nielsen, Max Welling, Priyank Jaini","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-04T02:21:08Z","title":"Sampling in Combinatorial Spaces with SurVAE Flow Augmented MCMC"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.02374","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":"sha256:7cb25d0a14d9697c7703b0aab8fa8799e53073d89d92f7fec513ed3192b01997","target":"record","created_at":"2026-07-05T02:18:59Z","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":"042e2540c55beee85be19f39a583f72a823cc07bc1cf519d0f8753f50dcb34b3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-04T02:21:08Z","title_canon_sha256":"b3ab9ac6d2d56334c9cc5bbee268b6f888fecb4e81c229a937cb668a8c421acb"},"schema_version":"1.0","source":{"id":"2102.02374","kind":"arxiv","version":2}},"canonical_sha256":"44821f128eafdcdbdab967b431e2dac25fb8cbaa7ae4b642cf64921010e8992d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"44821f128eafdcdbdab967b431e2dac25fb8cbaa7ae4b642cf64921010e8992d","first_computed_at":"2026-07-05T02:18:59.679750Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:18:59.679750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KRi/bVDJEjKIhCC43N7YZy0HwWgtWRu+13Dt5rLpqph5hNJEm3wlMVptdeFeL8gUEQnOHKcYQacuKtrX1Zi6DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:18:59.680165Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.02374","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7cb25d0a14d9697c7703b0aab8fa8799e53073d89d92f7fec513ed3192b01997","sha256:526ad4db5d8c94bfbab8bd0c7068fa46d0f00433aaa612bdf646bf7f23fe0582"],"state_sha256":"c969f5b9ad73b4d83016e296ca24dc05cbe0466e9a1cdcd08c390d8aaa9a3fdd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/iQkY96yxRgDC/5Gki3MJ+UWwSTFewsRBH/00o+frjXlTmJGPWC/j6SkRhVF3S9baMh8dxQX+KIxMmgyFxvFBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T21:36:06.559204Z","bundle_sha256":"4cd939ddc5fce507301ac57fc002f75d948c11e9102bac5875dc6cc7f219f437"}}