{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GX4UNHO2UVMKJRW5KUE4EEGPXL","short_pith_number":"pith:GX4UNHO2","canonical_record":{"source":{"id":"2310.19909","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-30T18:23:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"43ff0942503e33b9971ead67f30523876d8fa08e63d7798d2c210c205f10c557","abstract_canon_sha256":"aa9747bcf48e438a895fa70b6388f34c6001e5e5ca9a921b5e7bc44d3b802299"},"schema_version":"1.0"},"canonical_sha256":"35f9469ddaa558a4c6dd5509c210cfbadb0e9643dd141001912c0db4acc9982e","source":{"kind":"arxiv","id":"2310.19909","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.19909","created_at":"2026-07-05T07:14:19Z"},{"alias_kind":"arxiv_version","alias_value":"2310.19909v2","created_at":"2026-07-05T07:14:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19909","created_at":"2026-07-05T07:14:19Z"},{"alias_kind":"pith_short_12","alias_value":"GX4UNHO2UVMK","created_at":"2026-07-05T07:14:19Z"},{"alias_kind":"pith_short_16","alias_value":"GX4UNHO2UVMKJRW5","created_at":"2026-07-05T07:14:19Z"},{"alias_kind":"pith_short_8","alias_value":"GX4UNHO2","created_at":"2026-07-05T07:14:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GX4UNHO2UVMKJRW5KUE4EEGPXL","target":"record","payload":{"canonical_record":{"source":{"id":"2310.19909","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-30T18:23:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"43ff0942503e33b9971ead67f30523876d8fa08e63d7798d2c210c205f10c557","abstract_canon_sha256":"aa9747bcf48e438a895fa70b6388f34c6001e5e5ca9a921b5e7bc44d3b802299"},"schema_version":"1.0"},"canonical_sha256":"35f9469ddaa558a4c6dd5509c210cfbadb0e9643dd141001912c0db4acc9982e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:14:19.836120Z","signature_b64":"b86edPQSbkDF2FR6yUa0dnNhTp+edF5XTNh318V0d4vQTWes7s1JcOzDb37yQiCeOW1mQa5MMJTZNLs/MaZaCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35f9469ddaa558a4c6dd5509c210cfbadb0e9643dd141001912c0db4acc9982e","last_reissued_at":"2026-07-05T07:14:19.835657Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:14:19.835657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.19909","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:14:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wSRxBfwpNiAQWHOm7jqhRkJ3RCtKV3kaHNy2RVWULpRxpkDgwmT4+e73VVIxsucL510uYEULAs5XkWL56FMIAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:13:02.931383Z"},"content_sha256":"78486ef001482fd1d6db17436c9754ca784b7bf5c278fcda725cdafe543371fd","schema_version":"1.0","event_id":"sha256:78486ef001482fd1d6db17436c9754ca784b7bf5c278fcda725cdafe543371fd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GX4UNHO2UVMKJRW5KUE4EEGPXL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Adrien Bardes, Andrew Gordon Wilson, Gowthami Somepalli, Hossein Souri, Judy Hoffman, Manli Shu, Mark Ibrahim, Micah Goldblum, Prithvijit Chattopadhyay, Rama Chellappa, Renkun Ni, Tom Goldstein, Viraj Prabhu","submitted_at":"2023-10-30T18:23:58Z","abstract_excerpt":"Neural network based computer vision systems are typically built on a backbone, a pretrained or randomly initialized feature extractor. Several years ago, the default option was an ImageNet-trained convolutional neural network. However, the recent past has seen the emergence of countless backbones pretrained using various algorithms and datasets. While this abundance of choice has led to performance increases for a range of systems, it is difficult for practitioners to make informed decisions about which backbone to choose. Battle of the Backbones (BoB) makes this choice easier by benchmarking"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.19909","kind":"arxiv","version":2},"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/2310.19909/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":"2026-07-05T07:14:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cekTcHIxCcwot01G84fD4Ngdoab7R//ZHVUWtU0gOgzmqGvYjzKeBeQxCyes4aUjuhIB4VTGzJSQ5jsududYCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:13:02.932010Z"},"content_sha256":"a1eba560f57a02513e1a73e02b635a1a0ed880afe8c2145a60153cd0d8e74565","schema_version":"1.0","event_id":"sha256:a1eba560f57a02513e1a73e02b635a1a0ed880afe8c2145a60153cd0d8e74565"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GX4UNHO2UVMKJRW5KUE4EEGPXL/bundle.json","state_url":"https://pith.science/pith/GX4UNHO2UVMKJRW5KUE4EEGPXL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GX4UNHO2UVMKJRW5KUE4EEGPXL/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":"2026-08-05T11:13:02Z","links":{"resolver":"https://pith.science/pith/GX4UNHO2UVMKJRW5KUE4EEGPXL","bundle":"https://pith.science/pith/GX4UNHO2UVMKJRW5KUE4EEGPXL/bundle.json","state":"https://pith.science/pith/GX4UNHO2UVMKJRW5KUE4EEGPXL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GX4UNHO2UVMKJRW5KUE4EEGPXL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GX4UNHO2UVMKJRW5KUE4EEGPXL","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":"aa9747bcf48e438a895fa70b6388f34c6001e5e5ca9a921b5e7bc44d3b802299","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-30T18:23:58Z","title_canon_sha256":"43ff0942503e33b9971ead67f30523876d8fa08e63d7798d2c210c205f10c557"},"schema_version":"1.0","source":{"id":"2310.19909","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.19909","created_at":"2026-07-05T07:14:19Z"},{"alias_kind":"arxiv_version","alias_value":"2310.19909v2","created_at":"2026-07-05T07:14:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19909","created_at":"2026-07-05T07:14:19Z"},{"alias_kind":"pith_short_12","alias_value":"GX4UNHO2UVMK","created_at":"2026-07-05T07:14:19Z"},{"alias_kind":"pith_short_16","alias_value":"GX4UNHO2UVMKJRW5","created_at":"2026-07-05T07:14:19Z"},{"alias_kind":"pith_short_8","alias_value":"GX4UNHO2","created_at":"2026-07-05T07:14:19Z"}],"graph_snapshots":[{"event_id":"sha256:a1eba560f57a02513e1a73e02b635a1a0ed880afe8c2145a60153cd0d8e74565","target":"graph","created_at":"2026-07-05T07:14:19Z","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/2310.19909/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural network based computer vision systems are typically built on a backbone, a pretrained or randomly initialized feature extractor. Several years ago, the default option was an ImageNet-trained convolutional neural network. However, the recent past has seen the emergence of countless backbones pretrained using various algorithms and datasets. While this abundance of choice has led to performance increases for a range of systems, it is difficult for practitioners to make informed decisions about which backbone to choose. Battle of the Backbones (BoB) makes this choice easier by benchmarking","authors_text":"Adrien Bardes, Andrew Gordon Wilson, Gowthami Somepalli, Hossein Souri, Judy Hoffman, Manli Shu, Mark Ibrahim, Micah Goldblum, Prithvijit Chattopadhyay, Rama Chellappa, Renkun Ni, Tom Goldstein, Viraj Prabhu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-30T18:23:58Z","title":"Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.19909","kind":"arxiv","version":2},"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":"sha256:78486ef001482fd1d6db17436c9754ca784b7bf5c278fcda725cdafe543371fd","target":"record","created_at":"2026-07-05T07:14:19Z","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":"aa9747bcf48e438a895fa70b6388f34c6001e5e5ca9a921b5e7bc44d3b802299","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-30T18:23:58Z","title_canon_sha256":"43ff0942503e33b9971ead67f30523876d8fa08e63d7798d2c210c205f10c557"},"schema_version":"1.0","source":{"id":"2310.19909","kind":"arxiv","version":2}},"canonical_sha256":"35f9469ddaa558a4c6dd5509c210cfbadb0e9643dd141001912c0db4acc9982e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35f9469ddaa558a4c6dd5509c210cfbadb0e9643dd141001912c0db4acc9982e","first_computed_at":"2026-07-05T07:14:19.835657Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:14:19.835657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b86edPQSbkDF2FR6yUa0dnNhTp+edF5XTNh318V0d4vQTWes7s1JcOzDb37yQiCeOW1mQa5MMJTZNLs/MaZaCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:14:19.836120Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.19909","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:78486ef001482fd1d6db17436c9754ca784b7bf5c278fcda725cdafe543371fd","sha256:a1eba560f57a02513e1a73e02b635a1a0ed880afe8c2145a60153cd0d8e74565"],"state_sha256":"21cca1e240302511852557ee773e85254a1b922604dfc3da1c7e7948d1ba8150"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6GxHu9/D4B0xgNT5J5kj8xFGFB5KOVSUtYeZnKbqg51uAel0xFgu3qYBnAbKrtW1Pvz+KYaB0cmXTGAXb3FOBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T11:13:02.937513Z","bundle_sha256":"02fc9e491c00448f6c4e3c7b6a908606011ea1bfcfcd69c095c3931edd422ba6"}}