{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:3TK7BFQHNO5RISDH3T5HVK6332","short_pith_number":"pith:3TK7BFQH","canonical_record":{"source":{"id":"2002.11770","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-19T18:59:52Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"35cf37c4b0c326843f33bb7c629ae624a50d54fb6d80189001f8181568a0611c","abstract_canon_sha256":"c6151f1acdd152613e55ec9305cd3b40cc2b7942a1db3a1fee5306d9e08ec887"},"schema_version":"1.0"},"canonical_sha256":"dcd5f096076bbb144867dcfa7aabdbdead0cd79aa20f1b7430aa20ef55efec86","source":{"kind":"arxiv","id":"2002.11770","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.11770","created_at":"2026-07-05T00:44:08Z"},{"alias_kind":"arxiv_version","alias_value":"2002.11770v1","created_at":"2026-07-05T00:44:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.11770","created_at":"2026-07-05T00:44:08Z"},{"alias_kind":"pith_short_12","alias_value":"3TK7BFQHNO5R","created_at":"2026-07-05T00:44:08Z"},{"alias_kind":"pith_short_16","alias_value":"3TK7BFQHNO5RISDH","created_at":"2026-07-05T00:44:08Z"},{"alias_kind":"pith_short_8","alias_value":"3TK7BFQH","created_at":"2026-07-05T00:44:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:3TK7BFQHNO5RISDH3T5HVK6332","target":"record","payload":{"canonical_record":{"source":{"id":"2002.11770","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-19T18:59:52Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"35cf37c4b0c326843f33bb7c629ae624a50d54fb6d80189001f8181568a0611c","abstract_canon_sha256":"c6151f1acdd152613e55ec9305cd3b40cc2b7942a1db3a1fee5306d9e08ec887"},"schema_version":"1.0"},"canonical_sha256":"dcd5f096076bbb144867dcfa7aabdbdead0cd79aa20f1b7430aa20ef55efec86","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:44:08.776918Z","signature_b64":"rpV1+OxNlzHS8VgrC9fU4M6Rgz8bifp9TAfVOheAmuQx7cLY1tM/skAMHHkWfaIeJMdgk1obyGIoskcH5SY5Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcd5f096076bbb144867dcfa7aabdbdead0cd79aa20f1b7430aa20ef55efec86","last_reissued_at":"2026-07-05T00:44:08.776458Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:44:08.776458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.11770","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":"2026-07-05T00:44:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mFCGQ+TtqAVvSeWJb2yxQqJvvPdAlV2iIcN+kYbApKjyo3/JzejGO5tceEZshWGoV5y2uYx3I/k9/xlMOj6kDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T00:57:33.401804Z"},"content_sha256":"0fdf19154402622c7ad830adcf795b75404da68703a32d789fb286b02ccdbced","schema_version":"1.0","event_id":"sha256:0fdf19154402622c7ad830adcf795b75404da68703a32d789fb286b02ccdbced"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:3TK7BFQHNO5RISDH3T5HVK6332","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rethinking the Hyperparameters for Fine-tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Avinash Ravichandran, Hao Li, Hao Yang, Michael Lam, Pratik Chaudhari, Rahul Bhotika, Stefano Soatto","submitted_at":"2020-02-19T18:59:52Z","abstract_excerpt":"Fine-tuning from pre-trained ImageNet models has become the de-facto standard for various computer vision tasks. Current practices for fine-tuning typically involve selecting an ad-hoc choice of hyperparameters and keeping them fixed to values normally used for training from scratch. This paper re-examines several common practices of setting hyperparameters for fine-tuning. Our findings are based on extensive empirical evaluation for fine-tuning on various transfer learning benchmarks. (1) While prior works have thoroughly investigated learning rate and batch size, momentum for fine-tuning is "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.11770","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/2002.11770/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":"2026-07-05T00:44:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HDZ1O1PsUEGFqH3i8antdTIF04w4NmUFu6lDeStXG9JcF1uN2z42mXtX1iYSsJBEe9EE5Ky90UWc59ovFTEMBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T00:57:33.402630Z"},"content_sha256":"4a16525840c082c97a7d8dc3c745b8faacf156b42d7f57e8d78b299b05929d00","schema_version":"1.0","event_id":"sha256:4a16525840c082c97a7d8dc3c745b8faacf156b42d7f57e8d78b299b05929d00"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3TK7BFQHNO5RISDH3T5HVK6332/bundle.json","state_url":"https://pith.science/pith/3TK7BFQHNO5RISDH3T5HVK6332/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3TK7BFQHNO5RISDH3T5HVK6332/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":"2026-08-16T00:57:33Z","links":{"resolver":"https://pith.science/pith/3TK7BFQHNO5RISDH3T5HVK6332","bundle":"https://pith.science/pith/3TK7BFQHNO5RISDH3T5HVK6332/bundle.json","state":"https://pith.science/pith/3TK7BFQHNO5RISDH3T5HVK6332/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3TK7BFQHNO5RISDH3T5HVK6332/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:3TK7BFQHNO5RISDH3T5HVK6332","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":"c6151f1acdd152613e55ec9305cd3b40cc2b7942a1db3a1fee5306d9e08ec887","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-19T18:59:52Z","title_canon_sha256":"35cf37c4b0c326843f33bb7c629ae624a50d54fb6d80189001f8181568a0611c"},"schema_version":"1.0","source":{"id":"2002.11770","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.11770","created_at":"2026-07-05T00:44:08Z"},{"alias_kind":"arxiv_version","alias_value":"2002.11770v1","created_at":"2026-07-05T00:44:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.11770","created_at":"2026-07-05T00:44:08Z"},{"alias_kind":"pith_short_12","alias_value":"3TK7BFQHNO5R","created_at":"2026-07-05T00:44:08Z"},{"alias_kind":"pith_short_16","alias_value":"3TK7BFQHNO5RISDH","created_at":"2026-07-05T00:44:08Z"},{"alias_kind":"pith_short_8","alias_value":"3TK7BFQH","created_at":"2026-07-05T00:44:08Z"}],"graph_snapshots":[{"event_id":"sha256:4a16525840c082c97a7d8dc3c745b8faacf156b42d7f57e8d78b299b05929d00","target":"graph","created_at":"2026-07-05T00:44:08Z","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/2002.11770/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning from pre-trained ImageNet models has become the de-facto standard for various computer vision tasks. Current practices for fine-tuning typically involve selecting an ad-hoc choice of hyperparameters and keeping them fixed to values normally used for training from scratch. This paper re-examines several common practices of setting hyperparameters for fine-tuning. Our findings are based on extensive empirical evaluation for fine-tuning on various transfer learning benchmarks. (1) While prior works have thoroughly investigated learning rate and batch size, momentum for fine-tuning is ","authors_text":"Avinash Ravichandran, Hao Li, Hao Yang, Michael Lam, Pratik Chaudhari, Rahul Bhotika, Stefano Soatto","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-19T18:59:52Z","title":"Rethinking the Hyperparameters for Fine-tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.11770","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":"sha256:0fdf19154402622c7ad830adcf795b75404da68703a32d789fb286b02ccdbced","target":"record","created_at":"2026-07-05T00:44:08Z","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":"c6151f1acdd152613e55ec9305cd3b40cc2b7942a1db3a1fee5306d9e08ec887","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-19T18:59:52Z","title_canon_sha256":"35cf37c4b0c326843f33bb7c629ae624a50d54fb6d80189001f8181568a0611c"},"schema_version":"1.0","source":{"id":"2002.11770","kind":"arxiv","version":1}},"canonical_sha256":"dcd5f096076bbb144867dcfa7aabdbdead0cd79aa20f1b7430aa20ef55efec86","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dcd5f096076bbb144867dcfa7aabdbdead0cd79aa20f1b7430aa20ef55efec86","first_computed_at":"2026-07-05T00:44:08.776458Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:44:08.776458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rpV1+OxNlzHS8VgrC9fU4M6Rgz8bifp9TAfVOheAmuQx7cLY1tM/skAMHHkWfaIeJMdgk1obyGIoskcH5SY5Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:44:08.776918Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.11770","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0fdf19154402622c7ad830adcf795b75404da68703a32d789fb286b02ccdbced","sha256:4a16525840c082c97a7d8dc3c745b8faacf156b42d7f57e8d78b299b05929d00"],"state_sha256":"7207dca79e29f31c6196365d894731e628053d36fa6c724c1e056014db98f924"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"imp6taaJI8eafCDYWGkLdCVrWzYnPZZlFWKqz7KQtLQHnTXShnFHD7gILd23zNzUd2aqb/gwvjHEH9NPqGmdBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T00:57:33.409378Z","bundle_sha256":"fe888eeb5908d7ec5ff746f55b892d6850725cca5ba9dbdbadd16fbb66e04296"}}