{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NGPZH42LM4FID226ZT2I7ZUYFG","short_pith_number":"pith:NGPZH42L","canonical_record":{"source":{"id":"2406.01661","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-03T17:55:02Z","cross_cats_sorted":["cs.AI","cs.DM","stat.ML"],"title_canon_sha256":"7a926bf5ef92b819577b4bfa5657eac6da9f26b1f631ed87d90585c8056da9cd","abstract_canon_sha256":"5baa94b48eccb69eb72529fe6d19652088dbd6c65d5e94992a7777b7861572d4"},"schema_version":"1.0"},"canonical_sha256":"699f93f34b670a81eb5eccf48fe69829bded19b4c2604fe98e4cca78836f7262","source":{"kind":"arxiv","id":"2406.01661","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.01661","created_at":"2026-07-05T11:57:31Z"},{"alias_kind":"arxiv_version","alias_value":"2406.01661v3","created_at":"2026-07-05T11:57:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01661","created_at":"2026-07-05T11:57:31Z"},{"alias_kind":"pith_short_12","alias_value":"NGPZH42LM4FI","created_at":"2026-07-05T11:57:31Z"},{"alias_kind":"pith_short_16","alias_value":"NGPZH42LM4FID226","created_at":"2026-07-05T11:57:31Z"},{"alias_kind":"pith_short_8","alias_value":"NGPZH42L","created_at":"2026-07-05T11:57:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NGPZH42LM4FID226ZT2I7ZUYFG","target":"record","payload":{"canonical_record":{"source":{"id":"2406.01661","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-03T17:55:02Z","cross_cats_sorted":["cs.AI","cs.DM","stat.ML"],"title_canon_sha256":"7a926bf5ef92b819577b4bfa5657eac6da9f26b1f631ed87d90585c8056da9cd","abstract_canon_sha256":"5baa94b48eccb69eb72529fe6d19652088dbd6c65d5e94992a7777b7861572d4"},"schema_version":"1.0"},"canonical_sha256":"699f93f34b670a81eb5eccf48fe69829bded19b4c2604fe98e4cca78836f7262","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:57:31.539112Z","signature_b64":"9w0gYo3JaylJ7mqnV3r4jZE446PGR0LU3FRuy+QcXFI58DQedP2R1sx64L6kBJcY+ldZAkQYDhmLodGZUafHDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"699f93f34b670a81eb5eccf48fe69829bded19b4c2604fe98e4cca78836f7262","last_reissued_at":"2026-07-05T11:57:31.538611Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:57:31.538611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.01661","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":"2026-07-05T11:57:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iOUMwhmp93pjAyjZ5QdFG23D5eDk9GO287meBnilondrP41zMmDtblLe8rHt+YXHJp+9+lRVL/3Kp+cAyDOEDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:13:29.120400Z"},"content_sha256":"63aed8e2f523345a844d7ffb3ffc67c370e2b36a2b3e52802b542c171106bc7f","schema_version":"1.0","event_id":"sha256:63aed8e2f523345a844d7ffb3ffc67c370e2b36a2b3e52802b542c171106bc7f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NGPZH42LM4FID226ZT2I7ZUYFG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Diffusion Model Framework for Unsupervised Neural Combinatorial Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DM","stat.ML"],"primary_cat":"cs.LG","authors_text":"Sebastian Lehner, Sebastian Sanokowski, Sepp Hochreiter","submitted_at":"2024-06-03T17:55:02Z","abstract_excerpt":"Learning to sample from intractable distributions over discrete sets without relying on corresponding training data is a central problem in a wide range of fields, including Combinatorial Optimization. Currently, popular deep learning-based approaches rely primarily on generative models that yield exact sample likelihoods. This work introduces a method that lifts this restriction and opens the possibility to employ highly expressive latent variable models like diffusion models. Our approach is conceptually based on a loss that upper bounds the reverse Kullback-Leibler divergence and evades the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01661","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/2406.01661/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":"2026-07-05T11:57:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pxSJKOtO48IjWZkICKUJj5yDF4QC+jUepGsn/wH+TwFI+phFhRIg+j4LVVcmtexXCbsZl6p3mO4oIdhT+JSECw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:13:29.121878Z"},"content_sha256":"c273fb59892b59677c0bc72956626ec5b6a1a6a6f104567fffd6e9d1a4777cf1","schema_version":"1.0","event_id":"sha256:c273fb59892b59677c0bc72956626ec5b6a1a6a6f104567fffd6e9d1a4777cf1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NGPZH42LM4FID226ZT2I7ZUYFG/bundle.json","state_url":"https://pith.science/pith/NGPZH42LM4FID226ZT2I7ZUYFG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NGPZH42LM4FID226ZT2I7ZUYFG/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":"2026-08-07T17:13:29Z","links":{"resolver":"https://pith.science/pith/NGPZH42LM4FID226ZT2I7ZUYFG","bundle":"https://pith.science/pith/NGPZH42LM4FID226ZT2I7ZUYFG/bundle.json","state":"https://pith.science/pith/NGPZH42LM4FID226ZT2I7ZUYFG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NGPZH42LM4FID226ZT2I7ZUYFG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NGPZH42LM4FID226ZT2I7ZUYFG","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":"5baa94b48eccb69eb72529fe6d19652088dbd6c65d5e94992a7777b7861572d4","cross_cats_sorted":["cs.AI","cs.DM","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-03T17:55:02Z","title_canon_sha256":"7a926bf5ef92b819577b4bfa5657eac6da9f26b1f631ed87d90585c8056da9cd"},"schema_version":"1.0","source":{"id":"2406.01661","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.01661","created_at":"2026-07-05T11:57:31Z"},{"alias_kind":"arxiv_version","alias_value":"2406.01661v3","created_at":"2026-07-05T11:57:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01661","created_at":"2026-07-05T11:57:31Z"},{"alias_kind":"pith_short_12","alias_value":"NGPZH42LM4FI","created_at":"2026-07-05T11:57:31Z"},{"alias_kind":"pith_short_16","alias_value":"NGPZH42LM4FID226","created_at":"2026-07-05T11:57:31Z"},{"alias_kind":"pith_short_8","alias_value":"NGPZH42L","created_at":"2026-07-05T11:57:31Z"}],"graph_snapshots":[{"event_id":"sha256:c273fb59892b59677c0bc72956626ec5b6a1a6a6f104567fffd6e9d1a4777cf1","target":"graph","created_at":"2026-07-05T11:57:31Z","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/2406.01661/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning to sample from intractable distributions over discrete sets without relying on corresponding training data is a central problem in a wide range of fields, including Combinatorial Optimization. Currently, popular deep learning-based approaches rely primarily on generative models that yield exact sample likelihoods. This work introduces a method that lifts this restriction and opens the possibility to employ highly expressive latent variable models like diffusion models. Our approach is conceptually based on a loss that upper bounds the reverse Kullback-Leibler divergence and evades the","authors_text":"Sebastian Lehner, Sebastian Sanokowski, Sepp Hochreiter","cross_cats":["cs.AI","cs.DM","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-03T17:55:02Z","title":"A Diffusion Model Framework for Unsupervised Neural Combinatorial Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01661","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":"sha256:63aed8e2f523345a844d7ffb3ffc67c370e2b36a2b3e52802b542c171106bc7f","target":"record","created_at":"2026-07-05T11:57:31Z","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":"5baa94b48eccb69eb72529fe6d19652088dbd6c65d5e94992a7777b7861572d4","cross_cats_sorted":["cs.AI","cs.DM","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-03T17:55:02Z","title_canon_sha256":"7a926bf5ef92b819577b4bfa5657eac6da9f26b1f631ed87d90585c8056da9cd"},"schema_version":"1.0","source":{"id":"2406.01661","kind":"arxiv","version":3}},"canonical_sha256":"699f93f34b670a81eb5eccf48fe69829bded19b4c2604fe98e4cca78836f7262","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"699f93f34b670a81eb5eccf48fe69829bded19b4c2604fe98e4cca78836f7262","first_computed_at":"2026-07-05T11:57:31.538611Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:57:31.538611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9w0gYo3JaylJ7mqnV3r4jZE446PGR0LU3FRuy+QcXFI58DQedP2R1sx64L6kBJcY+ldZAkQYDhmLodGZUafHDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:57:31.539112Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.01661","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:63aed8e2f523345a844d7ffb3ffc67c370e2b36a2b3e52802b542c171106bc7f","sha256:c273fb59892b59677c0bc72956626ec5b6a1a6a6f104567fffd6e9d1a4777cf1"],"state_sha256":"30910194a30a89a3ec879e3450b3b626cebe34df7a3b827d785dfcb3cc56776b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x2Yrs1MOFYGgQfe+iWjwbs3zH3FaTNJ7mkhD+RlT25j2hqJZh1MRFPXQ6WZuRRPDQEe78fTuQFYmgZYbA4GrBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T17:13:29.136399Z","bundle_sha256":"46dd0ab24c111af387404c7a46125151fa7d16dc47b102ad069e6600e72ea334"}}