{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:WOTCNS3L6VIRYYIVG7VQDGJTU3","short_pith_number":"pith:WOTCNS3L","canonical_record":{"source":{"id":"1607.04579","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-07-15T16:56:22Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"a7790efc1310838f36c835d42f45b9a0c1e25d7adf440cc0b44663e1b7ba98e7","abstract_canon_sha256":"857ed71fee32d15b561bd04989f121c32581922e5bf4747798ceaa060772b221"},"schema_version":"1.0"},"canonical_sha256":"b3a626cb6bf5511c611537eb019933a6c21660565a1644ec81a92ed1a52d2da6","source":{"kind":"arxiv","id":"1607.04579","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1607.04579","created_at":"2026-05-18T00:53:40Z"},{"alias_kind":"arxiv_version","alias_value":"1607.04579v2","created_at":"2026-05-18T00:53:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.04579","created_at":"2026-05-18T00:53:40Z"},{"alias_kind":"pith_short_12","alias_value":"WOTCNS3L6VIR","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_16","alias_value":"WOTCNS3L6VIRYYIV","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_8","alias_value":"WOTCNS3L","created_at":"2026-05-18T12:30:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:WOTCNS3L6VIRYYIVG7VQDGJTU3","target":"record","payload":{"canonical_record":{"source":{"id":"1607.04579","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-07-15T16:56:22Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"a7790efc1310838f36c835d42f45b9a0c1e25d7adf440cc0b44663e1b7ba98e7","abstract_canon_sha256":"857ed71fee32d15b561bd04989f121c32581922e5bf4747798ceaa060772b221"},"schema_version":"1.0"},"canonical_sha256":"b3a626cb6bf5511c611537eb019933a6c21660565a1644ec81a92ed1a52d2da6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:53:40.173650Z","signature_b64":"l0euC9JKUkTSUiJ0pHrlKJP1w/UmMwW2M5S/PCXVWTBXe64/sbWU4ei9ION0ruAuWXxnoLPMKGT9sfg1dZbaDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3a626cb6bf5511c611537eb019933a6c21660565a1644ec81a92ed1a52d2da6","last_reissued_at":"2026-05-18T00:53:40.173190Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:53:40.173190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1607.04579","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":"2026-05-18T00:53:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"typ6S78WcRe+4kyJ6MSA4uOW2sFtK4Mo3JU7w6C4twpJmCEBmwkGeAyunwzR0jrGmmF23DUArJEgYVxTxZTNCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T23:24:09.074357Z"},"content_sha256":"4444b14e0b2fdb7ef9e2a14f1b09cbe35356bb5c6265e7afaf4900d930fae7d0","schema_version":"1.0","event_id":"sha256:4444b14e0b2fdb7ef9e2a14f1b09cbe35356bb5c6265e7afaf4900d930fae7d0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:WOTCNS3L6VIRYYIVG7VQDGJTU3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning from Conditional Distributions via Dual Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Dai, Byron Boots, Le Song, Niao He, Yunpeng Pan","submitted_at":"2016-07-15T16:56:22Z","abstract_excerpt":"Many machine learning tasks, such as learning with invariance and policy evaluation in reinforcement learning, can be characterized as problems of learning from conditional distributions. In such problems, each sample $x$ itself is associated with a conditional distribution $p(z|x)$ represented by samples $\\{z_i\\}_{i=1}^M$, and the goal is to learn a function $f$ that links these conditional distributions to target values $y$. These learning problems become very challenging when we only have limited samples or in the extreme case only one sample from each conditional distribution. Commonly use"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.04579","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":""},"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":"2026-05-18T00:53:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N4JEErGOk2g/knDl6JdcrJ+mQDn1MS9uYT2L+Q8L9tx7lwpxz6Gc4iDzUaabxE2IfzlsR9UZAE0U07YJgI+NAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T23:24:09.074991Z"},"content_sha256":"db2083de8ea71c5ddb4dff20664e08a3618a6dd750a045fdbbbd047d7a16d098","schema_version":"1.0","event_id":"sha256:db2083de8ea71c5ddb4dff20664e08a3618a6dd750a045fdbbbd047d7a16d098"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WOTCNS3L6VIRYYIVG7VQDGJTU3/bundle.json","state_url":"https://pith.science/pith/WOTCNS3L6VIRYYIVG7VQDGJTU3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WOTCNS3L6VIRYYIVG7VQDGJTU3/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":"2026-05-25T23:24:09Z","links":{"resolver":"https://pith.science/pith/WOTCNS3L6VIRYYIVG7VQDGJTU3","bundle":"https://pith.science/pith/WOTCNS3L6VIRYYIVG7VQDGJTU3/bundle.json","state":"https://pith.science/pith/WOTCNS3L6VIRYYIVG7VQDGJTU3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WOTCNS3L6VIRYYIVG7VQDGJTU3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:WOTCNS3L6VIRYYIVG7VQDGJTU3","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":"857ed71fee32d15b561bd04989f121c32581922e5bf4747798ceaa060772b221","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-07-15T16:56:22Z","title_canon_sha256":"a7790efc1310838f36c835d42f45b9a0c1e25d7adf440cc0b44663e1b7ba98e7"},"schema_version":"1.0","source":{"id":"1607.04579","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1607.04579","created_at":"2026-05-18T00:53:40Z"},{"alias_kind":"arxiv_version","alias_value":"1607.04579v2","created_at":"2026-05-18T00:53:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.04579","created_at":"2026-05-18T00:53:40Z"},{"alias_kind":"pith_short_12","alias_value":"WOTCNS3L6VIR","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_16","alias_value":"WOTCNS3L6VIRYYIV","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_8","alias_value":"WOTCNS3L","created_at":"2026-05-18T12:30:51Z"}],"graph_snapshots":[{"event_id":"sha256:db2083de8ea71c5ddb4dff20664e08a3618a6dd750a045fdbbbd047d7a16d098","target":"graph","created_at":"2026-05-18T00:53:40Z","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"},"paper":{"abstract_excerpt":"Many machine learning tasks, such as learning with invariance and policy evaluation in reinforcement learning, can be characterized as problems of learning from conditional distributions. In such problems, each sample $x$ itself is associated with a conditional distribution $p(z|x)$ represented by samples $\\{z_i\\}_{i=1}^M$, and the goal is to learn a function $f$ that links these conditional distributions to target values $y$. These learning problems become very challenging when we only have limited samples or in the extreme case only one sample from each conditional distribution. Commonly use","authors_text":"Bo Dai, Byron Boots, Le Song, Niao He, Yunpeng Pan","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-07-15T16:56:22Z","title":"Learning from Conditional Distributions via Dual Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.04579","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":"sha256:4444b14e0b2fdb7ef9e2a14f1b09cbe35356bb5c6265e7afaf4900d930fae7d0","target":"record","created_at":"2026-05-18T00:53:40Z","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":"857ed71fee32d15b561bd04989f121c32581922e5bf4747798ceaa060772b221","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-07-15T16:56:22Z","title_canon_sha256":"a7790efc1310838f36c835d42f45b9a0c1e25d7adf440cc0b44663e1b7ba98e7"},"schema_version":"1.0","source":{"id":"1607.04579","kind":"arxiv","version":2}},"canonical_sha256":"b3a626cb6bf5511c611537eb019933a6c21660565a1644ec81a92ed1a52d2da6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b3a626cb6bf5511c611537eb019933a6c21660565a1644ec81a92ed1a52d2da6","first_computed_at":"2026-05-18T00:53:40.173190Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:53:40.173190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l0euC9JKUkTSUiJ0pHrlKJP1w/UmMwW2M5S/PCXVWTBXe64/sbWU4ei9ION0ruAuWXxnoLPMKGT9sfg1dZbaDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:53:40.173650Z","signed_message":"canonical_sha256_bytes"},"source_id":"1607.04579","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4444b14e0b2fdb7ef9e2a14f1b09cbe35356bb5c6265e7afaf4900d930fae7d0","sha256:db2083de8ea71c5ddb4dff20664e08a3618a6dd750a045fdbbbd047d7a16d098"],"state_sha256":"7eb23b750a76a461a16ee5821f376f94892beafd42b5a899e38a38bd7ce052a5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sGJl7SdHUOIM2aFX5faNd20IZ3/758lCuFRS8y/E+Mt+u7SfHufHeev6Kp6LQBmHwgJ0u1GX4XPB8jUdlBlHBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T23:24:09.078686Z","bundle_sha256":"9ce323b9983ede94050c16a110ef685e33d1792033a56941cbe93f765d5ab01f"}}