{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:TSYK5UUJ7FEMODD7CQBNI5QL4D","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":"f2829adda0141bc43d1e9007924c3002516afe7d52a77f112e3329f0392e0e51","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-29T02:39:27Z","title_canon_sha256":"f584447c106bcfd94984db20f7904e60e38aecc6ea47350ca93fbfcbbe387d42"},"schema_version":"1.0","source":{"id":"1908.11024","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.11024","created_at":"2026-07-05T00:00:29Z"},{"alias_kind":"arxiv_version","alias_value":"1908.11024v1","created_at":"2026-07-05T00:00:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.11024","created_at":"2026-07-05T00:00:29Z"},{"alias_kind":"pith_short_12","alias_value":"TSYK5UUJ7FEM","created_at":"2026-07-05T00:00:29Z"},{"alias_kind":"pith_short_16","alias_value":"TSYK5UUJ7FEMODD7","created_at":"2026-07-05T00:00:29Z"},{"alias_kind":"pith_short_8","alias_value":"TSYK5UUJ","created_at":"2026-07-05T00:00:29Z"}],"graph_snapshots":[{"event_id":"sha256:e2773962337c2350d0bde4bc4bbe6039a04dafcf951e48ca17ea492f836f8a7f","target":"graph","created_at":"2026-07-05T00:00:29Z","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/1908.11024/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One of the ways to improve the performance of a target task is to learn the transfer of abundant knowledge of a pre-trained network. However, learning of the pre-trained network requires high computation capability and large-scale labeled dataset. To mitigate the burden of large-scale labeling, learning in un/self-supervised manner can be a solution. In addition, using unsupervised multi-task learning, a generalized feature representation can be learned. However, unsupervised multi-task learning can be biased to a specific task. To overcome this problem, we propose the metric-based regularizat","authors_text":"Byung Cheol Song, Dae Ha Kim, Seung Hyun Lee","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-29T02:39:27Z","title":"Metric-based Regularization and Temporal Ensemble for Multi-task Learning using Heterogeneous Unsupervised Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.11024","kind":"arxiv","version":1},"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":"sha256:4e8b33f3b0d37f61823936d970466d7529ddeadaea4eb0210eb56e6af299d83e","target":"record","created_at":"2026-07-05T00:00:29Z","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":"f2829adda0141bc43d1e9007924c3002516afe7d52a77f112e3329f0392e0e51","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-29T02:39:27Z","title_canon_sha256":"f584447c106bcfd94984db20f7904e60e38aecc6ea47350ca93fbfcbbe387d42"},"schema_version":"1.0","source":{"id":"1908.11024","kind":"arxiv","version":1}},"canonical_sha256":"9cb0aed289f948c70c7f1402d4760be0cc3c70eb16a93b032c03ae28a700b8be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9cb0aed289f948c70c7f1402d4760be0cc3c70eb16a93b032c03ae28a700b8be","first_computed_at":"2026-07-05T00:00:29.436412Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:00:29.436412Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Dqy+0Amjn0prehdtpE+xT+BdiWyZ/z2z7jCwaKxRHC/o3phlMf9adkm4Udxm04ZqyoOtYuScEQhVBPxl5pC6Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T00:00:29.436809Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.11024","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e8b33f3b0d37f61823936d970466d7529ddeadaea4eb0210eb56e6af299d83e","sha256:e2773962337c2350d0bde4bc4bbe6039a04dafcf951e48ca17ea492f836f8a7f"],"state_sha256":"3a7ee4db722dbe50af7d662acbe798dba86d854ccaeaf0f1d2337f063808084d"}