{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:OOVCCZ5UOXS46JNLF5JQKGXSNF","short_pith_number":"pith:OOVCCZ5U","canonical_record":{"source":{"id":"2102.12903","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-25T14:56:19Z","cross_cats_sorted":[],"title_canon_sha256":"53041c85d07277b042f282c81eb7a06560cc41274bee8eed32872b07564a43c0","abstract_canon_sha256":"d716c2c7fe3ab82b720e14fa6307b795060b1b10ed0464795380f0a017cbb2d4"},"schema_version":"1.0"},"canonical_sha256":"73aa2167b475e5cf25ab2f53051af2696dad270113aedeca5bf143258b38aff3","source":{"kind":"arxiv","id":"2102.12903","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.12903","created_at":"2026-07-05T02:59:36Z"},{"alias_kind":"arxiv_version","alias_value":"2102.12903v2","created_at":"2026-07-05T02:59:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.12903","created_at":"2026-07-05T02:59:36Z"},{"alias_kind":"pith_short_12","alias_value":"OOVCCZ5UOXS4","created_at":"2026-07-05T02:59:36Z"},{"alias_kind":"pith_short_16","alias_value":"OOVCCZ5UOXS46JNL","created_at":"2026-07-05T02:59:36Z"},{"alias_kind":"pith_short_8","alias_value":"OOVCCZ5U","created_at":"2026-07-05T02:59:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:OOVCCZ5UOXS46JNLF5JQKGXSNF","target":"record","payload":{"canonical_record":{"source":{"id":"2102.12903","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-25T14:56:19Z","cross_cats_sorted":[],"title_canon_sha256":"53041c85d07277b042f282c81eb7a06560cc41274bee8eed32872b07564a43c0","abstract_canon_sha256":"d716c2c7fe3ab82b720e14fa6307b795060b1b10ed0464795380f0a017cbb2d4"},"schema_version":"1.0"},"canonical_sha256":"73aa2167b475e5cf25ab2f53051af2696dad270113aedeca5bf143258b38aff3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:59:36.675846Z","signature_b64":"reVMNrEKI639ESSgRbqWf7A5wvL39yPwCLIgAzSL66tyiqVsus1LxFIqa9n8VkGbmYqyJnjZfCpkdOSRGnE/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73aa2167b475e5cf25ab2f53051af2696dad270113aedeca5bf143258b38aff3","last_reissued_at":"2026-07-05T02:59:36.675393Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:59:36.675393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.12903","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":"2026-07-05T02:59:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q7B/yJHi7l7XWsV16T71POE1S8XLaSrXKu9tJSB9sloJxFEGb580mCOA0NkOHJAuBSiX9DLBs128U6P5V2L1Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:07:23.626326Z"},"content_sha256":"d41afca41eef461d84ce2ad891ce4ebded3959592eba8b40f13f6828e57b0a15","schema_version":"1.0","event_id":"sha256:d41afca41eef461d84ce2ad891ce4ebded3959592eba8b40f13f6828e57b0a15"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:OOVCCZ5UOXS46JNLF5JQKGXSNF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-Tuning for Data-Efficient Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jianmin Wang, Jinghan Gao, Mingsheng Long, Ximei Wang","submitted_at":"2021-02-25T14:56:19Z","abstract_excerpt":"Deep learning has made revolutionary advances to diverse applications in the presence of large-scale labeled datasets. However, it is prohibitively time-costly and labor-expensive to collect sufficient labeled data in most realistic scenarios. To mitigate the requirement for labeled data, semi-supervised learning (SSL) focuses on simultaneously exploring both labeled and unlabeled data, while transfer learning (TL) popularizes a favorable practice of fine-tuning a pre-trained model to the target data. A dilemma is thus encountered: Without a decent pre-trained model to provide an implicit regu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.12903","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/2102.12903/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":"2026-07-05T02:59:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OIik5FpjyDaZPJyOjkhzno1MSofCNPOilbKAOv5PsHb5qVk0unlkIM1TWCB8aackQ20gKz+YsRGznzHVyiVwBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:07:23.626836Z"},"content_sha256":"348acb853f3f060112ad1037b02d28ee65ebc797f31066d2f5202ca870be90eb","schema_version":"1.0","event_id":"sha256:348acb853f3f060112ad1037b02d28ee65ebc797f31066d2f5202ca870be90eb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OOVCCZ5UOXS46JNLF5JQKGXSNF/bundle.json","state_url":"https://pith.science/pith/OOVCCZ5UOXS46JNLF5JQKGXSNF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OOVCCZ5UOXS46JNLF5JQKGXSNF/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":"2026-08-04T21:07:23Z","links":{"resolver":"https://pith.science/pith/OOVCCZ5UOXS46JNLF5JQKGXSNF","bundle":"https://pith.science/pith/OOVCCZ5UOXS46JNLF5JQKGXSNF/bundle.json","state":"https://pith.science/pith/OOVCCZ5UOXS46JNLF5JQKGXSNF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OOVCCZ5UOXS46JNLF5JQKGXSNF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:OOVCCZ5UOXS46JNLF5JQKGXSNF","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":"d716c2c7fe3ab82b720e14fa6307b795060b1b10ed0464795380f0a017cbb2d4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-25T14:56:19Z","title_canon_sha256":"53041c85d07277b042f282c81eb7a06560cc41274bee8eed32872b07564a43c0"},"schema_version":"1.0","source":{"id":"2102.12903","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.12903","created_at":"2026-07-05T02:59:36Z"},{"alias_kind":"arxiv_version","alias_value":"2102.12903v2","created_at":"2026-07-05T02:59:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.12903","created_at":"2026-07-05T02:59:36Z"},{"alias_kind":"pith_short_12","alias_value":"OOVCCZ5UOXS4","created_at":"2026-07-05T02:59:36Z"},{"alias_kind":"pith_short_16","alias_value":"OOVCCZ5UOXS46JNL","created_at":"2026-07-05T02:59:36Z"},{"alias_kind":"pith_short_8","alias_value":"OOVCCZ5U","created_at":"2026-07-05T02:59:36Z"}],"graph_snapshots":[{"event_id":"sha256:348acb853f3f060112ad1037b02d28ee65ebc797f31066d2f5202ca870be90eb","target":"graph","created_at":"2026-07-05T02:59:36Z","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/2102.12903/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep learning has made revolutionary advances to diverse applications in the presence of large-scale labeled datasets. However, it is prohibitively time-costly and labor-expensive to collect sufficient labeled data in most realistic scenarios. To mitigate the requirement for labeled data, semi-supervised learning (SSL) focuses on simultaneously exploring both labeled and unlabeled data, while transfer learning (TL) popularizes a favorable practice of fine-tuning a pre-trained model to the target data. A dilemma is thus encountered: Without a decent pre-trained model to provide an implicit regu","authors_text":"Jianmin Wang, Jinghan Gao, Mingsheng Long, Ximei Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-25T14:56:19Z","title":"Self-Tuning for Data-Efficient Deep Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.12903","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:d41afca41eef461d84ce2ad891ce4ebded3959592eba8b40f13f6828e57b0a15","target":"record","created_at":"2026-07-05T02:59:36Z","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":"d716c2c7fe3ab82b720e14fa6307b795060b1b10ed0464795380f0a017cbb2d4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-25T14:56:19Z","title_canon_sha256":"53041c85d07277b042f282c81eb7a06560cc41274bee8eed32872b07564a43c0"},"schema_version":"1.0","source":{"id":"2102.12903","kind":"arxiv","version":2}},"canonical_sha256":"73aa2167b475e5cf25ab2f53051af2696dad270113aedeca5bf143258b38aff3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73aa2167b475e5cf25ab2f53051af2696dad270113aedeca5bf143258b38aff3","first_computed_at":"2026-07-05T02:59:36.675393Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:59:36.675393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"reVMNrEKI639ESSgRbqWf7A5wvL39yPwCLIgAzSL66tyiqVsus1LxFIqa9n8VkGbmYqyJnjZfCpkdOSRGnE/AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:59:36.675846Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.12903","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d41afca41eef461d84ce2ad891ce4ebded3959592eba8b40f13f6828e57b0a15","sha256:348acb853f3f060112ad1037b02d28ee65ebc797f31066d2f5202ca870be90eb"],"state_sha256":"9a552cd1111e76f1df211515f16fd10b1fa7fba74627c6e487209f371eac05a5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e/qHFN18za4TaC77jPgukyyxYFP/vbOVPfZ2mL97lUEb5UcBlLw4KVJ/K9su5Xo8CpBtz+8mSFe08NNQtZ9eAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T21:07:23.630216Z","bundle_sha256":"94f3b8fd123d0b4a829edf3c376cd0e0defb928c11221cac214a2fd5d81dbf53"}}