{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:5GYLCNZSNVPY4X7OVWLVL4XLHK","short_pith_number":"pith:5GYLCNZS","canonical_record":{"source":{"id":"1711.06959","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-19T02:44:31Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"1f389682c7fba4e2209a9f6d44f9ce3f8008f27da7cdb84759bf4677f7250f5c","abstract_canon_sha256":"3cb530c2a4850289df1a852eb256c604c3427aa6aa60a47bea1fc026a58ba2d6"},"schema_version":"1.0"},"canonical_sha256":"e9b0b137326d5f8e5feead9755f2eb3a9c86ff67a5b568c6e8223cedd6944dd3","source":{"kind":"arxiv","id":"1711.06959","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.06959","created_at":"2026-05-18T00:30:15Z"},{"alias_kind":"arxiv_version","alias_value":"1711.06959v1","created_at":"2026-05-18T00:30:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.06959","created_at":"2026-05-18T00:30:15Z"},{"alias_kind":"pith_short_12","alias_value":"5GYLCNZSNVPY","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"5GYLCNZSNVPY4X7O","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"5GYLCNZS","created_at":"2026-05-18T12:31:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:5GYLCNZSNVPY4X7OVWLVL4XLHK","target":"record","payload":{"canonical_record":{"source":{"id":"1711.06959","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-19T02:44:31Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"1f389682c7fba4e2209a9f6d44f9ce3f8008f27da7cdb84759bf4677f7250f5c","abstract_canon_sha256":"3cb530c2a4850289df1a852eb256c604c3427aa6aa60a47bea1fc026a58ba2d6"},"schema_version":"1.0"},"canonical_sha256":"e9b0b137326d5f8e5feead9755f2eb3a9c86ff67a5b568c6e8223cedd6944dd3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:15.044623Z","signature_b64":"NC2XE9wgBPw0osvwiBvgzwt/TqanADM7bBuecdA9ZRnRba8KwSKhzKCkwe1SJw/kq7wXSDueH9vlJXxNoZe0AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9b0b137326d5f8e5feead9755f2eb3a9c86ff67a5b568c6e8223cedd6944dd3","last_reissued_at":"2026-05-18T00:30:15.043894Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:15.043894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1711.06959","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":"2026-05-18T00:30:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OcnuTaYOb9LSRPmXnH6xOVC4FJdEXWaLt0DrNSwZXo2yBQz4PHRWJ2eqsKryOSgq967gK2s/pAK+kS7OPCUaBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T18:21:39.576868Z"},"content_sha256":"ed25a5f565b1370c949209c59ee95705f80394f8d81958aa62468bb50f3f438c","schema_version":"1.0","event_id":"sha256:ed25a5f565b1370c949209c59ee95705f80394f8d81958aa62468bb50f3f438c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:5GYLCNZSNVPY4X7OVWLVL4XLHK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BPGrad: Towards Global Optimality in Deep Learning via Branch and Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Guanghui Wang, Yuanwei Wu, Ziming Zhang","submitted_at":"2017-11-19T02:44:31Z","abstract_excerpt":"Understanding the global optimality in deep learning (DL) has been attracting more and more attention recently. Conventional DL solvers, however, have not been developed intentionally to seek for such global optimality. In this paper we propose a novel approximation algorithm, BPGrad, towards optimizing deep models globally via branch and pruning. Our BPGrad algorithm is based on the assumption of Lipschitz continuity in DL, and as a result it can adaptively determine the step size for current gradient given the history of previous updates, wherein theoretically no smaller steps can achieve th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.06959","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":"2026-05-18T00:30:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8K09f9xUw4q6EutNucLQRYnYLuqOQTEh2r9ht3+6suLVqK5dz7N7siEOUVwQlBpyMwzjURmfr+RYbVtqRqJiBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T18:21:39.577246Z"},"content_sha256":"08b0cf443543311b2e329a4c7005ea9206e70c64c643ddf8c4957262e87c2855","schema_version":"1.0","event_id":"sha256:08b0cf443543311b2e329a4c7005ea9206e70c64c643ddf8c4957262e87c2855"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5GYLCNZSNVPY4X7OVWLVL4XLHK/bundle.json","state_url":"https://pith.science/pith/5GYLCNZSNVPY4X7OVWLVL4XLHK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5GYLCNZSNVPY4X7OVWLVL4XLHK/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":"2026-06-10T18:21:39Z","links":{"resolver":"https://pith.science/pith/5GYLCNZSNVPY4X7OVWLVL4XLHK","bundle":"https://pith.science/pith/5GYLCNZSNVPY4X7OVWLVL4XLHK/bundle.json","state":"https://pith.science/pith/5GYLCNZSNVPY4X7OVWLVL4XLHK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5GYLCNZSNVPY4X7OVWLVL4XLHK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:5GYLCNZSNVPY4X7OVWLVL4XLHK","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":"3cb530c2a4850289df1a852eb256c604c3427aa6aa60a47bea1fc026a58ba2d6","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-19T02:44:31Z","title_canon_sha256":"1f389682c7fba4e2209a9f6d44f9ce3f8008f27da7cdb84759bf4677f7250f5c"},"schema_version":"1.0","source":{"id":"1711.06959","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.06959","created_at":"2026-05-18T00:30:15Z"},{"alias_kind":"arxiv_version","alias_value":"1711.06959v1","created_at":"2026-05-18T00:30:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.06959","created_at":"2026-05-18T00:30:15Z"},{"alias_kind":"pith_short_12","alias_value":"5GYLCNZSNVPY","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"5GYLCNZSNVPY4X7O","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"5GYLCNZS","created_at":"2026-05-18T12:31:00Z"}],"graph_snapshots":[{"event_id":"sha256:08b0cf443543311b2e329a4c7005ea9206e70c64c643ddf8c4957262e87c2855","target":"graph","created_at":"2026-05-18T00:30:15Z","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":"Understanding the global optimality in deep learning (DL) has been attracting more and more attention recently. Conventional DL solvers, however, have not been developed intentionally to seek for such global optimality. In this paper we propose a novel approximation algorithm, BPGrad, towards optimizing deep models globally via branch and pruning. Our BPGrad algorithm is based on the assumption of Lipschitz continuity in DL, and as a result it can adaptively determine the step size for current gradient given the history of previous updates, wherein theoretically no smaller steps can achieve th","authors_text":"Guanghui Wang, Yuanwei Wu, Ziming Zhang","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-19T02:44:31Z","title":"BPGrad: Towards Global Optimality in Deep Learning via Branch and Pruning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.06959","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:ed25a5f565b1370c949209c59ee95705f80394f8d81958aa62468bb50f3f438c","target":"record","created_at":"2026-05-18T00:30:15Z","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":"3cb530c2a4850289df1a852eb256c604c3427aa6aa60a47bea1fc026a58ba2d6","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-19T02:44:31Z","title_canon_sha256":"1f389682c7fba4e2209a9f6d44f9ce3f8008f27da7cdb84759bf4677f7250f5c"},"schema_version":"1.0","source":{"id":"1711.06959","kind":"arxiv","version":1}},"canonical_sha256":"e9b0b137326d5f8e5feead9755f2eb3a9c86ff67a5b568c6e8223cedd6944dd3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e9b0b137326d5f8e5feead9755f2eb3a9c86ff67a5b568c6e8223cedd6944dd3","first_computed_at":"2026-05-18T00:30:15.043894Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:30:15.043894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NC2XE9wgBPw0osvwiBvgzwt/TqanADM7bBuecdA9ZRnRba8KwSKhzKCkwe1SJw/kq7wXSDueH9vlJXxNoZe0AA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:30:15.044623Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.06959","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed25a5f565b1370c949209c59ee95705f80394f8d81958aa62468bb50f3f438c","sha256:08b0cf443543311b2e329a4c7005ea9206e70c64c643ddf8c4957262e87c2855"],"state_sha256":"17c1f0549c02e94b27fd7b55b8fc3b4a039f6b2ccd61ce4bab79b51da059c66b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WjY0codcdhS24vLpWDjnr8I7r90fHsjAS9Z0EySg3uqa9ZBg0EH2UBS/C8QBM2UQJFxBbrjQabut6poaIwkDAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T18:21:39.579337Z","bundle_sha256":"560a558ed1adfc7f05566a1cb563b499d21491bdbff9a68260f6596a87be5bd7"}}