{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:C3ADTMRMO74E35WF5CCQLZIZ6Z","short_pith_number":"pith:C3ADTMRM","canonical_record":{"source":{"id":"1810.02334","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-04T17:29:17Z","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"title_canon_sha256":"f3993955ca85825ba35cc91a1346c473ef82418589268401f34ec6911d691246","abstract_canon_sha256":"0b85a5ecca4055cd25d4ebd1d3aba368b5f62ed4bddbefb4753e2d5b6c86710a"},"schema_version":"1.0"},"canonical_sha256":"16c039b22c77f84df6c5e88505e519f672a31023dc33d077f6248a17646ac177","source":{"kind":"arxiv","id":"1810.02334","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.02334","created_at":"2026-05-17T23:50:41Z"},{"alias_kind":"arxiv_version","alias_value":"1810.02334v6","created_at":"2026-05-17T23:50:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.02334","created_at":"2026-05-17T23:50:41Z"},{"alias_kind":"pith_short_12","alias_value":"C3ADTMRMO74E","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"C3ADTMRMO74E35WF","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"C3ADTMRM","created_at":"2026-05-18T12:32:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:C3ADTMRMO74E35WF5CCQLZIZ6Z","target":"record","payload":{"canonical_record":{"source":{"id":"1810.02334","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-04T17:29:17Z","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"title_canon_sha256":"f3993955ca85825ba35cc91a1346c473ef82418589268401f34ec6911d691246","abstract_canon_sha256":"0b85a5ecca4055cd25d4ebd1d3aba368b5f62ed4bddbefb4753e2d5b6c86710a"},"schema_version":"1.0"},"canonical_sha256":"16c039b22c77f84df6c5e88505e519f672a31023dc33d077f6248a17646ac177","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:41.071325Z","signature_b64":"sDpTz+j8JVAVyD9dbaH27lDKi+sy6dLMdy/gqMLgEfbflDPFGQP3gBwh8DRmlxwutdrInhMobpCyITVx6lSaBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16c039b22c77f84df6c5e88505e519f672a31023dc33d077f6248a17646ac177","last_reissued_at":"2026-05-17T23:50:41.070855Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:41.070855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.02334","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:50:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DyYbN3B3TuI9b7hWKA2YYlJCkNIyNGIOINu/lbZZEu/AchZybaiRMtxJ/e68fDkyzZE43gupZfiLClI6VgQ5BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T04:28:06.849110Z"},"content_sha256":"3658a9bcf0449882f12d64b2ce83397094fbfec7344bf716df102705673619b3","schema_version":"1.0","event_id":"sha256:3658a9bcf0449882f12d64b2ce83397094fbfec7344bf716df102705673619b3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:C3ADTMRMO74E35WF5CCQLZIZ6Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised Learning via Meta-Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chelsea Finn, Kyle Hsu, Sergey Levine","submitted_at":"2018-10-04T17:29:17Z","abstract_excerpt":"A central goal of unsupervised learning is to acquire representations from unlabeled data or experience that can be used for more effective learning of downstream tasks from modest amounts of labeled data. Many prior unsupervised learning works aim to do so by developing proxy objectives based on reconstruction, disentanglement, prediction, and other metrics. Instead, we develop an unsupervised meta-learning method that explicitly optimizes for the ability to learn a variety of tasks from small amounts of data. To do so, we construct tasks from unlabeled data in an automatic way and run meta-l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.02334","kind":"arxiv","version":6},"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":"2026-05-17T23:50:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y6cJtRbhdsUSqBFTTuHqgioV14+6trfhEU+WAyQ1Es+/282y1k2LEM6DW4fIKjp46N+WZfqn0zq6XulvkUWVBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T04:28:06.849470Z"},"content_sha256":"dc63e0319eaabee2b7315fd171b13d3ac9f6a7a2e1bc74aa7d621b3dfc4d560c","schema_version":"1.0","event_id":"sha256:dc63e0319eaabee2b7315fd171b13d3ac9f6a7a2e1bc74aa7d621b3dfc4d560c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C3ADTMRMO74E35WF5CCQLZIZ6Z/bundle.json","state_url":"https://pith.science/pith/C3ADTMRMO74E35WF5CCQLZIZ6Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C3ADTMRMO74E35WF5CCQLZIZ6Z/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":"2026-07-02T04:28:06Z","links":{"resolver":"https://pith.science/pith/C3ADTMRMO74E35WF5CCQLZIZ6Z","bundle":"https://pith.science/pith/C3ADTMRMO74E35WF5CCQLZIZ6Z/bundle.json","state":"https://pith.science/pith/C3ADTMRMO74E35WF5CCQLZIZ6Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C3ADTMRMO74E35WF5CCQLZIZ6Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:C3ADTMRMO74E35WF5CCQLZIZ6Z","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":"0b85a5ecca4055cd25d4ebd1d3aba368b5f62ed4bddbefb4753e2d5b6c86710a","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-04T17:29:17Z","title_canon_sha256":"f3993955ca85825ba35cc91a1346c473ef82418589268401f34ec6911d691246"},"schema_version":"1.0","source":{"id":"1810.02334","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.02334","created_at":"2026-05-17T23:50:41Z"},{"alias_kind":"arxiv_version","alias_value":"1810.02334v6","created_at":"2026-05-17T23:50:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.02334","created_at":"2026-05-17T23:50:41Z"},{"alias_kind":"pith_short_12","alias_value":"C3ADTMRMO74E","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"C3ADTMRMO74E35WF","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"C3ADTMRM","created_at":"2026-05-18T12:32:16Z"}],"graph_snapshots":[{"event_id":"sha256:dc63e0319eaabee2b7315fd171b13d3ac9f6a7a2e1bc74aa7d621b3dfc4d560c","target":"graph","created_at":"2026-05-17T23:50:41Z","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":"A central goal of unsupervised learning is to acquire representations from unlabeled data or experience that can be used for more effective learning of downstream tasks from modest amounts of labeled data. Many prior unsupervised learning works aim to do so by developing proxy objectives based on reconstruction, disentanglement, prediction, and other metrics. Instead, we develop an unsupervised meta-learning method that explicitly optimizes for the ability to learn a variety of tasks from small amounts of data. To do so, we construct tasks from unlabeled data in an automatic way and run meta-l","authors_text":"Chelsea Finn, Kyle Hsu, Sergey Levine","cross_cats":["cs.AI","cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-04T17:29:17Z","title":"Unsupervised Learning via Meta-Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.02334","kind":"arxiv","version":6},"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":"sha256:3658a9bcf0449882f12d64b2ce83397094fbfec7344bf716df102705673619b3","target":"record","created_at":"2026-05-17T23:50:41Z","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":"0b85a5ecca4055cd25d4ebd1d3aba368b5f62ed4bddbefb4753e2d5b6c86710a","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-04T17:29:17Z","title_canon_sha256":"f3993955ca85825ba35cc91a1346c473ef82418589268401f34ec6911d691246"},"schema_version":"1.0","source":{"id":"1810.02334","kind":"arxiv","version":6}},"canonical_sha256":"16c039b22c77f84df6c5e88505e519f672a31023dc33d077f6248a17646ac177","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"16c039b22c77f84df6c5e88505e519f672a31023dc33d077f6248a17646ac177","first_computed_at":"2026-05-17T23:50:41.070855Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:50:41.070855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sDpTz+j8JVAVyD9dbaH27lDKi+sy6dLMdy/gqMLgEfbflDPFGQP3gBwh8DRmlxwutdrInhMobpCyITVx6lSaBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:50:41.071325Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.02334","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3658a9bcf0449882f12d64b2ce83397094fbfec7344bf716df102705673619b3","sha256:dc63e0319eaabee2b7315fd171b13d3ac9f6a7a2e1bc74aa7d621b3dfc4d560c"],"state_sha256":"de7e28c484d896d1c6886a3254b47bc11b660dfcd5b3d8de0439c90e57c110b2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p7lvFELWwE8nVPS5meRFshflHPd3CLQrFNjmGwlrzgF/ffzh4Bmwp6F8nUVK2zJWlt3I9icGy/NP6oxjC1jIAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T04:28:06.851538Z","bundle_sha256":"e9cca7461c1a67314765492526a02f926b0e34880ce0b0cd26352289aa4f9ced"}}