{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:NZJQPK66M45M6C4OWVP3AKRBU5","short_pith_number":"pith:NZJQPK66","canonical_record":{"source":{"id":"1610.02242","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-10-07T12:15:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d697603c64a2302a7da665ca1ace0411c2a733a0a2616d1c0e835348c57d5cd2","abstract_canon_sha256":"2ba944c432f72d30a8178cff050d55a21ea9b279352b7ab07d5a4ec24870dd98"},"schema_version":"1.0"},"canonical_sha256":"6e5307abde673acf0b8eb55fb02a21a75a050f6f2b094adc1979816d0bea50d6","source":{"kind":"arxiv","id":"1610.02242","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.02242","created_at":"2026-05-18T00:48:42Z"},{"alias_kind":"arxiv_version","alias_value":"1610.02242v3","created_at":"2026-05-18T00:48:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.02242","created_at":"2026-05-18T00:48:42Z"},{"alias_kind":"pith_short_12","alias_value":"NZJQPK66M45M","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"NZJQPK66M45M6C4O","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"NZJQPK66","created_at":"2026-05-18T12:30:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:NZJQPK66M45M6C4OWVP3AKRBU5","target":"record","payload":{"canonical_record":{"source":{"id":"1610.02242","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-10-07T12:15:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d697603c64a2302a7da665ca1ace0411c2a733a0a2616d1c0e835348c57d5cd2","abstract_canon_sha256":"2ba944c432f72d30a8178cff050d55a21ea9b279352b7ab07d5a4ec24870dd98"},"schema_version":"1.0"},"canonical_sha256":"6e5307abde673acf0b8eb55fb02a21a75a050f6f2b094adc1979816d0bea50d6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:48:42.260289Z","signature_b64":"Hf3TlGjYxa6XWqoqdvThlTqDLQr6u7Y0pGrgL97cX5dSkeENGlkXhzN0V5OnQb110OyUn9kAWKNNqQygVHYoBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e5307abde673acf0b8eb55fb02a21a75a050f6f2b094adc1979816d0bea50d6","last_reissued_at":"2026-05-18T00:48:42.259608Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:48:42.259608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1610.02242","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:48:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yJ2e+qFzvaeF4/318NGmR7QPElUMnotJP6OyEl2Kc94fzEg8Of5olktkxCYASIMF0ulaxgGLvaHuFKBOnfzPAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T03:35:33.577547Z"},"content_sha256":"d500b6faf9da39f84208c5633256e9650f981d22e430dfb64864515c75b08470","schema_version":"1.0","event_id":"sha256:d500b6faf9da39f84208c5633256e9650f981d22e430dfb64864515c75b08470"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:NZJQPK66M45M6C4OWVP3AKRBU5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Temporal Ensembling for Semi-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Samuli Laine, Timo Aila","submitted_at":"2016-10-07T12:15:42Z","abstract_excerpt":"In this paper, we present a simple and efficient method for training deep neural networks in a semi-supervised setting where only a small portion of training data is labeled. We introduce self-ensembling, where we form a consensus prediction of the unknown labels using the outputs of the network-in-training on different epochs, and most importantly, under different regularization and input augmentation conditions. This ensemble prediction can be expected to be a better predictor for the unknown labels than the output of the network at the most recent training epoch, and can thus be used as a t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.02242","kind":"arxiv","version":3},"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":"2026-05-18T00:48:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5OY1raKg34t/70zNa7xHxhRqOmEBms5san1P3nVTmo0RFJToR90jNxohqRA2OfXxlxBlVRgCdqQcrKBO8U0EAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T03:35:33.577907Z"},"content_sha256":"163c33006e3eeeb73f12c2045f3e4a5408ba08600a498943289c44d112b59198","schema_version":"1.0","event_id":"sha256:163c33006e3eeeb73f12c2045f3e4a5408ba08600a498943289c44d112b59198"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NZJQPK66M45M6C4OWVP3AKRBU5/bundle.json","state_url":"https://pith.science/pith/NZJQPK66M45M6C4OWVP3AKRBU5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NZJQPK66M45M6C4OWVP3AKRBU5/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":"2026-06-01T03:35:33Z","links":{"resolver":"https://pith.science/pith/NZJQPK66M45M6C4OWVP3AKRBU5","bundle":"https://pith.science/pith/NZJQPK66M45M6C4OWVP3AKRBU5/bundle.json","state":"https://pith.science/pith/NZJQPK66M45M6C4OWVP3AKRBU5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NZJQPK66M45M6C4OWVP3AKRBU5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:NZJQPK66M45M6C4OWVP3AKRBU5","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":"2ba944c432f72d30a8178cff050d55a21ea9b279352b7ab07d5a4ec24870dd98","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-10-07T12:15:42Z","title_canon_sha256":"d697603c64a2302a7da665ca1ace0411c2a733a0a2616d1c0e835348c57d5cd2"},"schema_version":"1.0","source":{"id":"1610.02242","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.02242","created_at":"2026-05-18T00:48:42Z"},{"alias_kind":"arxiv_version","alias_value":"1610.02242v3","created_at":"2026-05-18T00:48:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.02242","created_at":"2026-05-18T00:48:42Z"},{"alias_kind":"pith_short_12","alias_value":"NZJQPK66M45M","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"NZJQPK66M45M6C4O","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"NZJQPK66","created_at":"2026-05-18T12:30:36Z"}],"graph_snapshots":[{"event_id":"sha256:163c33006e3eeeb73f12c2045f3e4a5408ba08600a498943289c44d112b59198","target":"graph","created_at":"2026-05-18T00:48:42Z","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":"In this paper, we present a simple and efficient method for training deep neural networks in a semi-supervised setting where only a small portion of training data is labeled. We introduce self-ensembling, where we form a consensus prediction of the unknown labels using the outputs of the network-in-training on different epochs, and most importantly, under different regularization and input augmentation conditions. This ensemble prediction can be expected to be a better predictor for the unknown labels than the output of the network at the most recent training epoch, and can thus be used as a t","authors_text":"Samuli Laine, Timo Aila","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-10-07T12:15:42Z","title":"Temporal Ensembling for Semi-Supervised Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.02242","kind":"arxiv","version":3},"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:d500b6faf9da39f84208c5633256e9650f981d22e430dfb64864515c75b08470","target":"record","created_at":"2026-05-18T00:48:42Z","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":"2ba944c432f72d30a8178cff050d55a21ea9b279352b7ab07d5a4ec24870dd98","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-10-07T12:15:42Z","title_canon_sha256":"d697603c64a2302a7da665ca1ace0411c2a733a0a2616d1c0e835348c57d5cd2"},"schema_version":"1.0","source":{"id":"1610.02242","kind":"arxiv","version":3}},"canonical_sha256":"6e5307abde673acf0b8eb55fb02a21a75a050f6f2b094adc1979816d0bea50d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e5307abde673acf0b8eb55fb02a21a75a050f6f2b094adc1979816d0bea50d6","first_computed_at":"2026-05-18T00:48:42.259608Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:48:42.259608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Hf3TlGjYxa6XWqoqdvThlTqDLQr6u7Y0pGrgL97cX5dSkeENGlkXhzN0V5OnQb110OyUn9kAWKNNqQygVHYoBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:48:42.260289Z","signed_message":"canonical_sha256_bytes"},"source_id":"1610.02242","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d500b6faf9da39f84208c5633256e9650f981d22e430dfb64864515c75b08470","sha256:163c33006e3eeeb73f12c2045f3e4a5408ba08600a498943289c44d112b59198"],"state_sha256":"504d35c4e85b88373cf0058f96effee9bc57c3aea84cc2ac9dd20820e5a5de6c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GmNJvFf09fqE/B+ZynePD/W1527NRsZS36XjPMn6fqKfDtlxI8rWy4WK47AcjoLLnSIzn1VJ0XNa9QGpsTFRCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T03:35:33.579966Z","bundle_sha256":"bff3418598f71d2c009a07e7f191ee459ab755f9287c34d08919d6428bd149a5"}}