{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:WN2XGWV4ULQBTZGHEBBRO65ETA","short_pith_number":"pith:WN2XGWV4","canonical_record":{"source":{"id":"2007.03966","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-08T08:48:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"acad2eac4e6e79199c2393c3fb3f8a092c86f26050b71ae560f9be0587a8d9d5","abstract_canon_sha256":"858eb9cbbb572f4dda1e94d572acefcf1bbfe7a8b75d1117dc8a6e48694e5020"},"schema_version":"1.0"},"canonical_sha256":"b375735abca2e019e4c72043177ba49808529f479fab7d2a1683dfa60f8de46f","source":{"kind":"arxiv","id":"2007.03966","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.03966","created_at":"2026-07-05T02:23:57Z"},{"alias_kind":"arxiv_version","alias_value":"2007.03966v2","created_at":"2026-07-05T02:23:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.03966","created_at":"2026-07-05T02:23:57Z"},{"alias_kind":"pith_short_12","alias_value":"WN2XGWV4ULQB","created_at":"2026-07-05T02:23:57Z"},{"alias_kind":"pith_short_16","alias_value":"WN2XGWV4ULQBTZGH","created_at":"2026-07-05T02:23:57Z"},{"alias_kind":"pith_short_8","alias_value":"WN2XGWV4","created_at":"2026-07-05T02:23:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:WN2XGWV4ULQBTZGHEBBRO65ETA","target":"record","payload":{"canonical_record":{"source":{"id":"2007.03966","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-08T08:48:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"acad2eac4e6e79199c2393c3fb3f8a092c86f26050b71ae560f9be0587a8d9d5","abstract_canon_sha256":"858eb9cbbb572f4dda1e94d572acefcf1bbfe7a8b75d1117dc8a6e48694e5020"},"schema_version":"1.0"},"canonical_sha256":"b375735abca2e019e4c72043177ba49808529f479fab7d2a1683dfa60f8de46f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:23:57.576613Z","signature_b64":"oI3O9mhXfwJcFse9IfGciBRAnlvu1dMwhj3/IU19OfHRqlM8OE3oS+ssQj0llHOz6nmlFD0ilx1RwYGZpNyODQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b375735abca2e019e4c72043177ba49808529f479fab7d2a1683dfa60f8de46f","last_reissued_at":"2026-07-05T02:23:57.576156Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:23:57.576156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.03966","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":"2026-07-05T02:23:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v0U4w0PLmkXE6DeKaghf9HmQmBgP0BVhX81mRn+dM6FRYZRHaY1Bc2CG8GJdU+2WHzV6tdlPYPFYrW4fQ3txAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T21:58:23.228501Z"},"content_sha256":"585a1311ee0abc456a3cbd8dae6c95e6b4d79be46183783e30e3abef1959984b","schema_version":"1.0","event_id":"sha256:585a1311ee0abc456a3cbd8dae6c95e6b4d79be46183783e30e3abef1959984b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:WN2XGWV4ULQBTZGHEBBRO65ETA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semi-Supervised Learning with Meta-Gradient","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Haolin Jia, Ming-Hsuan Yang, Ming-Ming Cheng, Taihong Xiao, Xin-Yu Zhang","submitted_at":"2020-07-08T08:48:56Z","abstract_excerpt":"In this work, we propose a simple yet effective meta-learning algorithm in semi-supervised learning. We notice that most existing consistency-based approaches suffer from overfitting and limited model generalization ability, especially when training with only a small number of labeled data. To alleviate this issue, we propose a learn-to-generalize regularization term by utilizing the label information and optimize the problem in a meta-learning fashion. Specifically, we seek the pseudo labels of the unlabeled data so that the model can generalize well on the labeled data, which is formulated a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.03966","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/2007.03966/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":"2026-07-05T02:23:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cgKxTGzI7JJciZxADJ3Vb4XEqORiNVPtg8Y1glitpT4oqzaOermzWZoS2elP54FVrHtiQFZ2X8M4EUsMahmmDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T21:58:23.228946Z"},"content_sha256":"f9b578b0b4996f2dc0c2a6ea7ae9c7b23b8a26f8f95ba4b94632445ec02f8e9a","schema_version":"1.0","event_id":"sha256:f9b578b0b4996f2dc0c2a6ea7ae9c7b23b8a26f8f95ba4b94632445ec02f8e9a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WN2XGWV4ULQBTZGHEBBRO65ETA/bundle.json","state_url":"https://pith.science/pith/WN2XGWV4ULQBTZGHEBBRO65ETA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WN2XGWV4ULQBTZGHEBBRO65ETA/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":"2026-07-07T21:58:23Z","links":{"resolver":"https://pith.science/pith/WN2XGWV4ULQBTZGHEBBRO65ETA","bundle":"https://pith.science/pith/WN2XGWV4ULQBTZGHEBBRO65ETA/bundle.json","state":"https://pith.science/pith/WN2XGWV4ULQBTZGHEBBRO65ETA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WN2XGWV4ULQBTZGHEBBRO65ETA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:WN2XGWV4ULQBTZGHEBBRO65ETA","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":"858eb9cbbb572f4dda1e94d572acefcf1bbfe7a8b75d1117dc8a6e48694e5020","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-08T08:48:56Z","title_canon_sha256":"acad2eac4e6e79199c2393c3fb3f8a092c86f26050b71ae560f9be0587a8d9d5"},"schema_version":"1.0","source":{"id":"2007.03966","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.03966","created_at":"2026-07-05T02:23:57Z"},{"alias_kind":"arxiv_version","alias_value":"2007.03966v2","created_at":"2026-07-05T02:23:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.03966","created_at":"2026-07-05T02:23:57Z"},{"alias_kind":"pith_short_12","alias_value":"WN2XGWV4ULQB","created_at":"2026-07-05T02:23:57Z"},{"alias_kind":"pith_short_16","alias_value":"WN2XGWV4ULQBTZGH","created_at":"2026-07-05T02:23:57Z"},{"alias_kind":"pith_short_8","alias_value":"WN2XGWV4","created_at":"2026-07-05T02:23:57Z"}],"graph_snapshots":[{"event_id":"sha256:f9b578b0b4996f2dc0c2a6ea7ae9c7b23b8a26f8f95ba4b94632445ec02f8e9a","target":"graph","created_at":"2026-07-05T02:23:57Z","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/2007.03966/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we propose a simple yet effective meta-learning algorithm in semi-supervised learning. We notice that most existing consistency-based approaches suffer from overfitting and limited model generalization ability, especially when training with only a small number of labeled data. To alleviate this issue, we propose a learn-to-generalize regularization term by utilizing the label information and optimize the problem in a meta-learning fashion. Specifically, we seek the pseudo labels of the unlabeled data so that the model can generalize well on the labeled data, which is formulated a","authors_text":"Haolin Jia, Ming-Hsuan Yang, Ming-Ming Cheng, Taihong Xiao, Xin-Yu Zhang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-08T08:48:56Z","title":"Semi-Supervised Learning with Meta-Gradient"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.03966","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":"sha256:585a1311ee0abc456a3cbd8dae6c95e6b4d79be46183783e30e3abef1959984b","target":"record","created_at":"2026-07-05T02:23:57Z","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":"858eb9cbbb572f4dda1e94d572acefcf1bbfe7a8b75d1117dc8a6e48694e5020","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-08T08:48:56Z","title_canon_sha256":"acad2eac4e6e79199c2393c3fb3f8a092c86f26050b71ae560f9be0587a8d9d5"},"schema_version":"1.0","source":{"id":"2007.03966","kind":"arxiv","version":2}},"canonical_sha256":"b375735abca2e019e4c72043177ba49808529f479fab7d2a1683dfa60f8de46f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b375735abca2e019e4c72043177ba49808529f479fab7d2a1683dfa60f8de46f","first_computed_at":"2026-07-05T02:23:57.576156Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:23:57.576156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oI3O9mhXfwJcFse9IfGciBRAnlvu1dMwhj3/IU19OfHRqlM8OE3oS+ssQj0llHOz6nmlFD0ilx1RwYGZpNyODQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:23:57.576613Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.03966","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:585a1311ee0abc456a3cbd8dae6c95e6b4d79be46183783e30e3abef1959984b","sha256:f9b578b0b4996f2dc0c2a6ea7ae9c7b23b8a26f8f95ba4b94632445ec02f8e9a"],"state_sha256":"dcce438ee22f7a9f8281218fc9c43af45e74883dbef06d51707510f9e30e9829"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Av3ZGG23kmkVOawctxa0NgR3t9vmQPwSbMH4wq9zK1FDI+JjPURy8/iYJtYQIhl+uFDuPabPJVfElWT1qpP6CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T21:58:23.231842Z","bundle_sha256":"be29ad002b9806171fd79001083607ae29147d72462688fc62eb1028801a62ad"}}