{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:DBYH7PRC2KLY5IO6X2K2YK2Z7I","short_pith_number":"pith:DBYH7PRC","canonical_record":{"source":{"id":"1810.13243","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-29T19:36:07Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4b42c1c7f62829300649fa433d0d56f6dcd8ee27b3f97b7f8f9c9d3399565b79","abstract_canon_sha256":"dee684274422ebde8b065ade70ce9b8f61338db21fedd5fcc2c224a96548d24d"},"schema_version":"1.0"},"canonical_sha256":"18707fbe22d2978ea1debe95ac2b59fa1de934d2fc49e8c8be40dcdd102a6dfa","source":{"kind":"arxiv","id":"1810.13243","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.13243","created_at":"2026-05-18T00:01:49Z"},{"alias_kind":"arxiv_version","alias_value":"1810.13243v1","created_at":"2026-05-18T00:01:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.13243","created_at":"2026-05-18T00:01:49Z"},{"alias_kind":"pith_short_12","alias_value":"DBYH7PRC2KLY","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DBYH7PRC2KLY5IO6","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DBYH7PRC","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:DBYH7PRC2KLY5IO6X2K2YK2Z7I","target":"record","payload":{"canonical_record":{"source":{"id":"1810.13243","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-29T19:36:07Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4b42c1c7f62829300649fa433d0d56f6dcd8ee27b3f97b7f8f9c9d3399565b79","abstract_canon_sha256":"dee684274422ebde8b065ade70ce9b8f61338db21fedd5fcc2c224a96548d24d"},"schema_version":"1.0"},"canonical_sha256":"18707fbe22d2978ea1debe95ac2b59fa1de934d2fc49e8c8be40dcdd102a6dfa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:49.892273Z","signature_b64":"L7jvoikeNvAE8ZzKlRipSYmRjB/vTvPTR/fV/WvY9DC957m0xv+TTf2apoo9XT7+Nv0YXwAm/kvz0JnKfAFEAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18707fbe22d2978ea1debe95ac2b59fa1de934d2fc49e8c8be40dcdd102a6dfa","last_reissued_at":"2026-05-18T00:01:49.891677Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:49.891677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.13243","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":"2026-05-18T00:01:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hfFI5/MLIIzk4VeV7c8RctpHXXaKamF3cDz+Lu0/ZBapUFlk9ThgBAAaH5uNwxFyFXCIX5uMtmZ0IAtwVFZzBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T13:59:07.990195Z"},"content_sha256":"c01a1d9a4f35b6abf3288018081ca5529eb11bc01f31a204258b9607a4e4c778","schema_version":"1.0","event_id":"sha256:c01a1d9a4f35b6abf3288018081ca5529eb11bc01f31a204258b9607a4e4c778"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:DBYH7PRC2KLY5IO6X2K2YK2Z7I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Closer Look at Deep Learning Heuristics: Learning rate restarts, Warmup and Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Akhilesh Gotmare, Caiming Xiong, Nitish Shirish Keskar, Richard Socher","submitted_at":"2018-10-29T19:36:07Z","abstract_excerpt":"The convergence rate and final performance of common deep learning models have significantly benefited from heuristics such as learning rate schedules, knowledge distillation, skip connections, and normalization layers. In the absence of theoretical underpinnings, controlled experiments aimed at explaining these strategies can aid our understanding of deep learning landscapes and the training dynamics. Existing approaches for empirical analysis rely on tools of linear interpolation and visualizations with dimensionality reduction, each with their limitations. Instead, we revisit such analysis "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.13243","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":"2026-05-18T00:01:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5qIZO19tjN3UJzcDL67qrodNztFb6pSJj2tddnz49WjlN/zW+afdNlMvG2w3vvDcxNWBjMxwQSu2k4D3/RgiDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T13:59:07.990619Z"},"content_sha256":"b512d4388a9f46996fd1083a6b18eb366b092843237c91af00021b356997e901","schema_version":"1.0","event_id":"sha256:b512d4388a9f46996fd1083a6b18eb366b092843237c91af00021b356997e901"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DBYH7PRC2KLY5IO6X2K2YK2Z7I/bundle.json","state_url":"https://pith.science/pith/DBYH7PRC2KLY5IO6X2K2YK2Z7I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DBYH7PRC2KLY5IO6X2K2YK2Z7I/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":"2026-05-27T13:59:07Z","links":{"resolver":"https://pith.science/pith/DBYH7PRC2KLY5IO6X2K2YK2Z7I","bundle":"https://pith.science/pith/DBYH7PRC2KLY5IO6X2K2YK2Z7I/bundle.json","state":"https://pith.science/pith/DBYH7PRC2KLY5IO6X2K2YK2Z7I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DBYH7PRC2KLY5IO6X2K2YK2Z7I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:DBYH7PRC2KLY5IO6X2K2YK2Z7I","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":"dee684274422ebde8b065ade70ce9b8f61338db21fedd5fcc2c224a96548d24d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-29T19:36:07Z","title_canon_sha256":"4b42c1c7f62829300649fa433d0d56f6dcd8ee27b3f97b7f8f9c9d3399565b79"},"schema_version":"1.0","source":{"id":"1810.13243","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.13243","created_at":"2026-05-18T00:01:49Z"},{"alias_kind":"arxiv_version","alias_value":"1810.13243v1","created_at":"2026-05-18T00:01:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.13243","created_at":"2026-05-18T00:01:49Z"},{"alias_kind":"pith_short_12","alias_value":"DBYH7PRC2KLY","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DBYH7PRC2KLY5IO6","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DBYH7PRC","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:b512d4388a9f46996fd1083a6b18eb366b092843237c91af00021b356997e901","target":"graph","created_at":"2026-05-18T00:01:49Z","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":"The convergence rate and final performance of common deep learning models have significantly benefited from heuristics such as learning rate schedules, knowledge distillation, skip connections, and normalization layers. In the absence of theoretical underpinnings, controlled experiments aimed at explaining these strategies can aid our understanding of deep learning landscapes and the training dynamics. Existing approaches for empirical analysis rely on tools of linear interpolation and visualizations with dimensionality reduction, each with their limitations. Instead, we revisit such analysis ","authors_text":"Akhilesh Gotmare, Caiming Xiong, Nitish Shirish Keskar, Richard Socher","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-29T19:36:07Z","title":"A Closer Look at Deep Learning Heuristics: Learning rate restarts, Warmup and Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.13243","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:c01a1d9a4f35b6abf3288018081ca5529eb11bc01f31a204258b9607a4e4c778","target":"record","created_at":"2026-05-18T00:01:49Z","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":"dee684274422ebde8b065ade70ce9b8f61338db21fedd5fcc2c224a96548d24d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-29T19:36:07Z","title_canon_sha256":"4b42c1c7f62829300649fa433d0d56f6dcd8ee27b3f97b7f8f9c9d3399565b79"},"schema_version":"1.0","source":{"id":"1810.13243","kind":"arxiv","version":1}},"canonical_sha256":"18707fbe22d2978ea1debe95ac2b59fa1de934d2fc49e8c8be40dcdd102a6dfa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"18707fbe22d2978ea1debe95ac2b59fa1de934d2fc49e8c8be40dcdd102a6dfa","first_computed_at":"2026-05-18T00:01:49.891677Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:01:49.891677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L7jvoikeNvAE8ZzKlRipSYmRjB/vTvPTR/fV/WvY9DC957m0xv+TTf2apoo9XT7+Nv0YXwAm/kvz0JnKfAFEAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:01:49.892273Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.13243","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c01a1d9a4f35b6abf3288018081ca5529eb11bc01f31a204258b9607a4e4c778","sha256:b512d4388a9f46996fd1083a6b18eb366b092843237c91af00021b356997e901"],"state_sha256":"6425bec22cddcebd1b4a2bb6261a88c5269b45e50ab6418f1ebb29bb31b5eb2a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gB+RtuXyMQO2+1biCvtrUw6spmVTWFa5GBXLn5I87huaQYoANs0zKuIra2/jlnXCe/yDL23Y5j8N8XyRNsqODQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T13:59:07.993086Z","bundle_sha256":"24405c74e38ef02e57c798478268a5ff16c4abad0bed7e01eca5acaf1146e91d"}}