{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:QCMI3THHLAXHYNADE56W37MK5C","short_pith_number":"pith:QCMI3THH","canonical_record":{"source":{"id":"1704.00109","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-01T02:42:55Z","cross_cats_sorted":[],"title_canon_sha256":"7b9b7b651c70af06996438c3abd4174713c85e6af812b2fa47b4bad1477ef5ff","abstract_canon_sha256":"3089fee70881f344e67be712816ffb2c9a74173993205cf528924acdf04ebb89"},"schema_version":"1.0"},"canonical_sha256":"80988dcce7582e7c3403277d6dfd8ae89493f5ca39645bd3c91aa9dcadcd3639","source":{"kind":"arxiv","id":"1704.00109","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.00109","created_at":"2026-05-18T00:47:25Z"},{"alias_kind":"arxiv_version","alias_value":"1704.00109v1","created_at":"2026-05-18T00:47:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.00109","created_at":"2026-05-18T00:47:25Z"},{"alias_kind":"pith_short_12","alias_value":"QCMI3THHLAXH","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"QCMI3THHLAXHYNAD","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"QCMI3THH","created_at":"2026-05-18T12:31:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:QCMI3THHLAXHYNADE56W37MK5C","target":"record","payload":{"canonical_record":{"source":{"id":"1704.00109","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-01T02:42:55Z","cross_cats_sorted":[],"title_canon_sha256":"7b9b7b651c70af06996438c3abd4174713c85e6af812b2fa47b4bad1477ef5ff","abstract_canon_sha256":"3089fee70881f344e67be712816ffb2c9a74173993205cf528924acdf04ebb89"},"schema_version":"1.0"},"canonical_sha256":"80988dcce7582e7c3403277d6dfd8ae89493f5ca39645bd3c91aa9dcadcd3639","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:47:25.427512Z","signature_b64":"mQaeaecKdtmwYd+pN8Z0/UjHiKZMw6s0p6iwADUkxtxR6jQB504CxF8yQQIngjmqcq5Mcpg01VTlrLCAeknPAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80988dcce7582e7c3403277d6dfd8ae89493f5ca39645bd3c91aa9dcadcd3639","last_reissued_at":"2026-05-18T00:47:25.426835Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:47:25.426835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1704.00109","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:47:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pJQJVvgimHI6Gg65L4e8HT+pnwiBZMQcpTLS4MUVQKCG0w1pDTiGRIlbfR4nnogRLewycnNGv1LfzOtZNoA7Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T03:44:09.686142Z"},"content_sha256":"2b1c73d9c4741f41c699f4bb298c355b033bf8c74921de37d07b4761839f4eae","schema_version":"1.0","event_id":"sha256:2b1c73d9c4741f41c699f4bb298c355b033bf8c74921de37d07b4761839f4eae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:QCMI3THHLAXHYNADE56W37MK5C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Snapshot Ensembles: Train 1, get M for free","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gao Huang, Geoff Pleiss, John E. Hopcroft, Kilian Q. Weinberger, Yixuan Li, Zhuang Liu","submitted_at":"2017-04-01T02:42:55Z","abstract_excerpt":"Ensembles of neural networks are known to be much more robust and accurate than individual networks. However, training multiple deep networks for model averaging is computationally expensive. In this paper, we propose a method to obtain the seemingly contradictory goal of ensembling multiple neural networks at no additional training cost. We achieve this goal by training a single neural network, converging to several local minima along its optimization path and saving the model parameters. To obtain repeated rapid convergence, we leverage recent work on cyclic learning rate schedules. The resu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.00109","kind":"arxiv","version":1},"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":"2026-05-18T00:47:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gLzc4hfkax5hyDqf8snS4bOvvByjcAVpsE1J9y77O25dIyaXCRA6maswvOHWoVzMIc5+ICzGQTV8dp6TQ75OAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T03:44:09.686499Z"},"content_sha256":"4d49fe7b4e67e86608bb3588b77536503514aed46413ee2e37adf10969ca407b","schema_version":"1.0","event_id":"sha256:4d49fe7b4e67e86608bb3588b77536503514aed46413ee2e37adf10969ca407b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QCMI3THHLAXHYNADE56W37MK5C/bundle.json","state_url":"https://pith.science/pith/QCMI3THHLAXHYNADE56W37MK5C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QCMI3THHLAXHYNADE56W37MK5C/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":"2026-06-01T03:44:09Z","links":{"resolver":"https://pith.science/pith/QCMI3THHLAXHYNADE56W37MK5C","bundle":"https://pith.science/pith/QCMI3THHLAXHYNADE56W37MK5C/bundle.json","state":"https://pith.science/pith/QCMI3THHLAXHYNADE56W37MK5C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QCMI3THHLAXHYNADE56W37MK5C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:QCMI3THHLAXHYNADE56W37MK5C","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":"3089fee70881f344e67be712816ffb2c9a74173993205cf528924acdf04ebb89","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-01T02:42:55Z","title_canon_sha256":"7b9b7b651c70af06996438c3abd4174713c85e6af812b2fa47b4bad1477ef5ff"},"schema_version":"1.0","source":{"id":"1704.00109","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.00109","created_at":"2026-05-18T00:47:25Z"},{"alias_kind":"arxiv_version","alias_value":"1704.00109v1","created_at":"2026-05-18T00:47:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.00109","created_at":"2026-05-18T00:47:25Z"},{"alias_kind":"pith_short_12","alias_value":"QCMI3THHLAXH","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"QCMI3THHLAXHYNAD","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"QCMI3THH","created_at":"2026-05-18T12:31:37Z"}],"graph_snapshots":[{"event_id":"sha256:4d49fe7b4e67e86608bb3588b77536503514aed46413ee2e37adf10969ca407b","target":"graph","created_at":"2026-05-18T00:47:25Z","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":"Ensembles of neural networks are known to be much more robust and accurate than individual networks. However, training multiple deep networks for model averaging is computationally expensive. In this paper, we propose a method to obtain the seemingly contradictory goal of ensembling multiple neural networks at no additional training cost. We achieve this goal by training a single neural network, converging to several local minima along its optimization path and saving the model parameters. To obtain repeated rapid convergence, we leverage recent work on cyclic learning rate schedules. The resu","authors_text":"Gao Huang, Geoff Pleiss, John E. Hopcroft, Kilian Q. Weinberger, Yixuan Li, Zhuang Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-01T02:42:55Z","title":"Snapshot Ensembles: Train 1, get M for free"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.00109","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":"sha256:2b1c73d9c4741f41c699f4bb298c355b033bf8c74921de37d07b4761839f4eae","target":"record","created_at":"2026-05-18T00:47:25Z","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":"3089fee70881f344e67be712816ffb2c9a74173993205cf528924acdf04ebb89","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-01T02:42:55Z","title_canon_sha256":"7b9b7b651c70af06996438c3abd4174713c85e6af812b2fa47b4bad1477ef5ff"},"schema_version":"1.0","source":{"id":"1704.00109","kind":"arxiv","version":1}},"canonical_sha256":"80988dcce7582e7c3403277d6dfd8ae89493f5ca39645bd3c91aa9dcadcd3639","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80988dcce7582e7c3403277d6dfd8ae89493f5ca39645bd3c91aa9dcadcd3639","first_computed_at":"2026-05-18T00:47:25.426835Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:47:25.426835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mQaeaecKdtmwYd+pN8Z0/UjHiKZMw6s0p6iwADUkxtxR6jQB504CxF8yQQIngjmqcq5Mcpg01VTlrLCAeknPAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:47:25.427512Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.00109","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b1c73d9c4741f41c699f4bb298c355b033bf8c74921de37d07b4761839f4eae","sha256:4d49fe7b4e67e86608bb3588b77536503514aed46413ee2e37adf10969ca407b"],"state_sha256":"cb3ed740d4371590d22310ea0e1ca61a6accd102476436df4cece11d658ebd4d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4nPngYo3gRU1+9LHxkzV06YOw+3LJW+IIysM35vBqPXj0AopUlVdtC2nSVseXrQn5b4saq+EZt2wW/ulo2rkDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T03:44:09.688447Z","bundle_sha256":"c7ed088c236db014e325564bb5252d60b187fa821c4be5c1e85e4881973bfa9f"}}