{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:IEKUNNTE5O7OZCSAJKAXCYOWTZ","short_pith_number":"pith:IEKUNNTE","canonical_record":{"source":{"id":"2212.11481","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-12-22T04:41:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9fdb116102aa43b4e6a4ff119cb2c3756b43b1e2f6cfb308f9a665558f399516","abstract_canon_sha256":"892643714dd83074516a8de019c9f6bf1d5eac06cbb1af2b737fff1bd4a0d78b"},"schema_version":"1.0"},"canonical_sha256":"411546b664ebbeec8a404a817161d69e5dcbf1d4f045cd7078b77f152c8dca13","source":{"kind":"arxiv","id":"2212.11481","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.11481","created_at":"2026-07-05T05:29:04Z"},{"alias_kind":"arxiv_version","alias_value":"2212.11481v2","created_at":"2026-07-05T05:29:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.11481","created_at":"2026-07-05T05:29:04Z"},{"alias_kind":"pith_short_12","alias_value":"IEKUNNTE5O7O","created_at":"2026-07-05T05:29:04Z"},{"alias_kind":"pith_short_16","alias_value":"IEKUNNTE5O7OZCSA","created_at":"2026-07-05T05:29:04Z"},{"alias_kind":"pith_short_8","alias_value":"IEKUNNTE","created_at":"2026-07-05T05:29:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:IEKUNNTE5O7OZCSAJKAXCYOWTZ","target":"record","payload":{"canonical_record":{"source":{"id":"2212.11481","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-12-22T04:41:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9fdb116102aa43b4e6a4ff119cb2c3756b43b1e2f6cfb308f9a665558f399516","abstract_canon_sha256":"892643714dd83074516a8de019c9f6bf1d5eac06cbb1af2b737fff1bd4a0d78b"},"schema_version":"1.0"},"canonical_sha256":"411546b664ebbeec8a404a817161d69e5dcbf1d4f045cd7078b77f152c8dca13","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:29:04.809899Z","signature_b64":"70bsUXfULvwFXsdGr1CPq8Z11V5gz1ZRoPDnAEe5Aew8vmawzWxZeSSfg4SAQf4QrTa42nkYioLiqmpiZB8CDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"411546b664ebbeec8a404a817161d69e5dcbf1d4f045cd7078b77f152c8dca13","last_reissued_at":"2026-07-05T05:29:04.809476Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:29:04.809476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.11481","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":"2026-07-05T05:29:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+RXWnumRzdjEuj6Ju7EYgw2iOCR7uasd6/4/G3mRxRUo7l88PsNCVwbRqYkQYJimwzEAOKJ4fSTZRQL7wlTFBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:21:47.742289Z"},"content_sha256":"24943845a2cea1c77d37de1ee4bf2c0be206c268a763f43bf6ddd56c347357b4","schema_version":"1.0","event_id":"sha256:24943845a2cea1c77d37de1ee4bf2c0be206c268a763f43bf6ddd56c347357b4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:IEKUNNTE5O7OZCSAJKAXCYOWTZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Mathematical Framework for Learning Probability Distributions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Hongkang Yang","submitted_at":"2022-12-22T04:41:45Z","abstract_excerpt":"The modeling of probability distributions, specifically generative modeling and density estimation, has become an immensely popular subject in recent years by virtue of its outstanding performance on sophisticated data such as images and texts. Nevertheless, a theoretical understanding of its success is still incomplete. One mystery is the paradox between memorization and generalization: In theory, the model is trained to be exactly the same as the empirical distribution of the finite samples, whereas in practice, the trained model can generate new samples or estimate the likelihood of unseen "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.11481","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/2212.11481/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":"2026-07-05T05:29:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sEXcdPTvr7xCdV2qqIAiuJZjagZDTRInfSfVblYww6am5XiEKGGzT9O5X67m5wkPvEgNgKKXUQOMMPvtZrVUBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:21:47.742825Z"},"content_sha256":"0000f41feba386c4043a71670ec8de482a0fe7e564e481a2a2b9215d694d5604","schema_version":"1.0","event_id":"sha256:0000f41feba386c4043a71670ec8de482a0fe7e564e481a2a2b9215d694d5604"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IEKUNNTE5O7OZCSAJKAXCYOWTZ/bundle.json","state_url":"https://pith.science/pith/IEKUNNTE5O7OZCSAJKAXCYOWTZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IEKUNNTE5O7OZCSAJKAXCYOWTZ/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":"2026-08-08T19:21:47Z","links":{"resolver":"https://pith.science/pith/IEKUNNTE5O7OZCSAJKAXCYOWTZ","bundle":"https://pith.science/pith/IEKUNNTE5O7OZCSAJKAXCYOWTZ/bundle.json","state":"https://pith.science/pith/IEKUNNTE5O7OZCSAJKAXCYOWTZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IEKUNNTE5O7OZCSAJKAXCYOWTZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:IEKUNNTE5O7OZCSAJKAXCYOWTZ","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":"892643714dd83074516a8de019c9f6bf1d5eac06cbb1af2b737fff1bd4a0d78b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-12-22T04:41:45Z","title_canon_sha256":"9fdb116102aa43b4e6a4ff119cb2c3756b43b1e2f6cfb308f9a665558f399516"},"schema_version":"1.0","source":{"id":"2212.11481","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.11481","created_at":"2026-07-05T05:29:04Z"},{"alias_kind":"arxiv_version","alias_value":"2212.11481v2","created_at":"2026-07-05T05:29:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.11481","created_at":"2026-07-05T05:29:04Z"},{"alias_kind":"pith_short_12","alias_value":"IEKUNNTE5O7O","created_at":"2026-07-05T05:29:04Z"},{"alias_kind":"pith_short_16","alias_value":"IEKUNNTE5O7OZCSA","created_at":"2026-07-05T05:29:04Z"},{"alias_kind":"pith_short_8","alias_value":"IEKUNNTE","created_at":"2026-07-05T05:29:04Z"}],"graph_snapshots":[{"event_id":"sha256:0000f41feba386c4043a71670ec8de482a0fe7e564e481a2a2b9215d694d5604","target":"graph","created_at":"2026-07-05T05:29:04Z","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/2212.11481/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The modeling of probability distributions, specifically generative modeling and density estimation, has become an immensely popular subject in recent years by virtue of its outstanding performance on sophisticated data such as images and texts. Nevertheless, a theoretical understanding of its success is still incomplete. One mystery is the paradox between memorization and generalization: In theory, the model is trained to be exactly the same as the empirical distribution of the finite samples, whereas in practice, the trained model can generate new samples or estimate the likelihood of unseen ","authors_text":"Hongkang Yang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-12-22T04:41:45Z","title":"A Mathematical Framework for Learning Probability Distributions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.11481","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":"sha256:24943845a2cea1c77d37de1ee4bf2c0be206c268a763f43bf6ddd56c347357b4","target":"record","created_at":"2026-07-05T05:29:04Z","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":"892643714dd83074516a8de019c9f6bf1d5eac06cbb1af2b737fff1bd4a0d78b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-12-22T04:41:45Z","title_canon_sha256":"9fdb116102aa43b4e6a4ff119cb2c3756b43b1e2f6cfb308f9a665558f399516"},"schema_version":"1.0","source":{"id":"2212.11481","kind":"arxiv","version":2}},"canonical_sha256":"411546b664ebbeec8a404a817161d69e5dcbf1d4f045cd7078b77f152c8dca13","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"411546b664ebbeec8a404a817161d69e5dcbf1d4f045cd7078b77f152c8dca13","first_computed_at":"2026-07-05T05:29:04.809476Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:29:04.809476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"70bsUXfULvwFXsdGr1CPq8Z11V5gz1ZRoPDnAEe5Aew8vmawzWxZeSSfg4SAQf4QrTa42nkYioLiqmpiZB8CDg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:29:04.809899Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.11481","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:24943845a2cea1c77d37de1ee4bf2c0be206c268a763f43bf6ddd56c347357b4","sha256:0000f41feba386c4043a71670ec8de482a0fe7e564e481a2a2b9215d694d5604"],"state_sha256":"4039da8a22db3303c4f9806cb4fa9a973577a1184c2ca98f3f9f8b8a3f25077e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oIPF6A3emfhK6suCdpyIjbUkfyra9k77NIGgt9HjPtWrtX4cLnzR+jcbvQyHQ2YIedbgyuEN/E3pVFXbM4ueDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T19:21:47.748059Z","bundle_sha256":"27c96f156c1e3848acbf9c7c3cb4eaab81af2c2c80b5fc08aafdb83efbaee7ab"}}