{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:T6PBMGKWELQG5TA764ZU3ZW2KX","short_pith_number":"pith:T6PBMGKW","canonical_record":{"source":{"id":"1910.00762","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-02T03:34:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1b6030ec506a23d8cbe83366dac0555bea96b2770716fb9e36f8ce1c78e17401","abstract_canon_sha256":"e770c048aa098a76ef26910f494b10c573b75f8d90754aa25fc5a5ad5bbd3472"},"schema_version":"1.0"},"canonical_sha256":"9f9e16195622e06ecc1ff7334de6da55e78a7a32901af8e115f8a74479908aee","source":{"kind":"arxiv","id":"1910.00762","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.00762","created_at":"2026-07-05T00:09:18Z"},{"alias_kind":"arxiv_version","alias_value":"1910.00762v1","created_at":"2026-07-05T00:09:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.00762","created_at":"2026-07-05T00:09:18Z"},{"alias_kind":"pith_short_12","alias_value":"T6PBMGKWELQG","created_at":"2026-07-05T00:09:18Z"},{"alias_kind":"pith_short_16","alias_value":"T6PBMGKWELQG5TA7","created_at":"2026-07-05T00:09:18Z"},{"alias_kind":"pith_short_8","alias_value":"T6PBMGKW","created_at":"2026-07-05T00:09:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:T6PBMGKWELQG5TA764ZU3ZW2KX","target":"record","payload":{"canonical_record":{"source":{"id":"1910.00762","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-02T03:34:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1b6030ec506a23d8cbe83366dac0555bea96b2770716fb9e36f8ce1c78e17401","abstract_canon_sha256":"e770c048aa098a76ef26910f494b10c573b75f8d90754aa25fc5a5ad5bbd3472"},"schema_version":"1.0"},"canonical_sha256":"9f9e16195622e06ecc1ff7334de6da55e78a7a32901af8e115f8a74479908aee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:09:18.848388Z","signature_b64":"Tt0uRBpNJKG26Y84NRK91ZAGqkEFp2Uhc0+RJSx2G5nM6kFcfX27JYhLG45VMBOa2dLWs3lsEnoZpY4gzTCKAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f9e16195622e06ecc1ff7334de6da55e78a7a32901af8e115f8a74479908aee","last_reissued_at":"2026-07-05T00:09:18.847962Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:09:18.847962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.00762","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":"2026-07-05T00:09:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UV0a5mIrcSmSGgO5sTfx9FWTQKgRMyFK3NxDPCxHPq8fWgnB2oIuR2R4O4zNCQKCOL1gLM8IdWWmkhd6D9FfDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T00:32:56.036878Z"},"content_sha256":"0214f462128c92c1bfba898cdfabee9799c76d6d0af10af725dd227c834131f9","schema_version":"1.0","event_id":"sha256:0214f462128c92c1bfba898cdfabee9799c76d6d0af10af725dd227c834131f9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:T6PBMGKWELQG5TA764ZU3ZW2KX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Accelerating Deep Learning by Focusing on the Biggest Losers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Angela H. Jiang, Daniel L.-K. Wong, David G. Andersen, Gauri Joshi, Giulio Zhou, Gregory R. Ganger, Jeffrey Dean, Michael Kaminksy, Michael Kozuch, Padmanabhan Pillai, Zachary C. Lipton","submitted_at":"2019-10-02T03:34:29Z","abstract_excerpt":"This paper introduces Selective-Backprop, a technique that accelerates the training of deep neural networks (DNNs) by prioritizing examples with high loss at each iteration. Selective-Backprop uses the output of a training example's forward pass to decide whether to use that example to compute gradients and update parameters, or to skip immediately to the next example. By reducing the number of computationally-expensive backpropagation steps performed, Selective-Backprop accelerates training. Evaluation on CIFAR10, CIFAR100, and SVHN, across a variety of modern image models, shows that Selecti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.00762","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1910.00762/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":"2026-07-05T00:09:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R7Wf6FgGUQfWM6Pkyw6/ER4YrdcimI0Cq3OOstY2HFwk5oxRQPHMkLr0tgNR/cQr+MDiE5ELKCiReDgU1TVgCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T00:32:56.037798Z"},"content_sha256":"9a5327cc242b1cab301921798fa0b39c5fa3084959f5977016d5b923240cedce","schema_version":"1.0","event_id":"sha256:9a5327cc242b1cab301921798fa0b39c5fa3084959f5977016d5b923240cedce"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T6PBMGKWELQG5TA764ZU3ZW2KX/bundle.json","state_url":"https://pith.science/pith/T6PBMGKWELQG5TA764ZU3ZW2KX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T6PBMGKWELQG5TA764ZU3ZW2KX/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":"2026-08-14T00:32:56Z","links":{"resolver":"https://pith.science/pith/T6PBMGKWELQG5TA764ZU3ZW2KX","bundle":"https://pith.science/pith/T6PBMGKWELQG5TA764ZU3ZW2KX/bundle.json","state":"https://pith.science/pith/T6PBMGKWELQG5TA764ZU3ZW2KX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T6PBMGKWELQG5TA764ZU3ZW2KX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:T6PBMGKWELQG5TA764ZU3ZW2KX","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":"e770c048aa098a76ef26910f494b10c573b75f8d90754aa25fc5a5ad5bbd3472","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-02T03:34:29Z","title_canon_sha256":"1b6030ec506a23d8cbe83366dac0555bea96b2770716fb9e36f8ce1c78e17401"},"schema_version":"1.0","source":{"id":"1910.00762","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.00762","created_at":"2026-07-05T00:09:18Z"},{"alias_kind":"arxiv_version","alias_value":"1910.00762v1","created_at":"2026-07-05T00:09:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.00762","created_at":"2026-07-05T00:09:18Z"},{"alias_kind":"pith_short_12","alias_value":"T6PBMGKWELQG","created_at":"2026-07-05T00:09:18Z"},{"alias_kind":"pith_short_16","alias_value":"T6PBMGKWELQG5TA7","created_at":"2026-07-05T00:09:18Z"},{"alias_kind":"pith_short_8","alias_value":"T6PBMGKW","created_at":"2026-07-05T00:09:18Z"}],"graph_snapshots":[{"event_id":"sha256:9a5327cc242b1cab301921798fa0b39c5fa3084959f5977016d5b923240cedce","target":"graph","created_at":"2026-07-05T00:09:18Z","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/1910.00762/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces Selective-Backprop, a technique that accelerates the training of deep neural networks (DNNs) by prioritizing examples with high loss at each iteration. Selective-Backprop uses the output of a training example's forward pass to decide whether to use that example to compute gradients and update parameters, or to skip immediately to the next example. By reducing the number of computationally-expensive backpropagation steps performed, Selective-Backprop accelerates training. Evaluation on CIFAR10, CIFAR100, and SVHN, across a variety of modern image models, shows that Selecti","authors_text":"Angela H. Jiang, Daniel L.-K. Wong, David G. Andersen, Gauri Joshi, Giulio Zhou, Gregory R. Ganger, Jeffrey Dean, Michael Kaminksy, Michael Kozuch, Padmanabhan Pillai, Zachary C. Lipton","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-02T03:34:29Z","title":"Accelerating Deep Learning by Focusing on the Biggest Losers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.00762","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":"sha256:0214f462128c92c1bfba898cdfabee9799c76d6d0af10af725dd227c834131f9","target":"record","created_at":"2026-07-05T00:09:18Z","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":"e770c048aa098a76ef26910f494b10c573b75f8d90754aa25fc5a5ad5bbd3472","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-02T03:34:29Z","title_canon_sha256":"1b6030ec506a23d8cbe83366dac0555bea96b2770716fb9e36f8ce1c78e17401"},"schema_version":"1.0","source":{"id":"1910.00762","kind":"arxiv","version":1}},"canonical_sha256":"9f9e16195622e06ecc1ff7334de6da55e78a7a32901af8e115f8a74479908aee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f9e16195622e06ecc1ff7334de6da55e78a7a32901af8e115f8a74479908aee","first_computed_at":"2026-07-05T00:09:18.847962Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:09:18.847962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Tt0uRBpNJKG26Y84NRK91ZAGqkEFp2Uhc0+RJSx2G5nM6kFcfX27JYhLG45VMBOa2dLWs3lsEnoZpY4gzTCKAA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:09:18.848388Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.00762","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0214f462128c92c1bfba898cdfabee9799c76d6d0af10af725dd227c834131f9","sha256:9a5327cc242b1cab301921798fa0b39c5fa3084959f5977016d5b923240cedce"],"state_sha256":"74ca15839cf4c3c6b1561267e0531f91d0c0fa194f2b722da6f8839844c76f1f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8uiZ0QxBsliDlzII67tQDscePa1dXZ7j7OVb8jHJcjdAuEOn/+PtQT8opGsJg/5HKKrXkUlOTI6gRa6V+Zf0Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T00:32:56.098152Z","bundle_sha256":"423f2c780fa987f05839ffe0005eabc5a15c1a1897ede992abe5eb15cd7b4e54"}}