{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:63QHP7JICERVFOO57SEV7HXMPD","short_pith_number":"pith:63QHP7JI","canonical_record":{"source":{"id":"2111.06977","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-12T22:53:28Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"5148a28f90b716072f8aefc5f2475c3411f15b173d8e9fe359fd050393cd8fe1","abstract_canon_sha256":"e55f5f95a4cac99cb9f493e26d2850942eb31a4d6002319debc1461947a6d8be"},"schema_version":"1.0"},"canonical_sha256":"f6e077fd28112352b9ddfc895f9eec78e88a5bcfb8206c0b101ab5ba137c91ee","source":{"kind":"arxiv","id":"2111.06977","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.06977","created_at":"2026-07-05T03:47:26Z"},{"alias_kind":"arxiv_version","alias_value":"2111.06977v2","created_at":"2026-07-05T03:47:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.06977","created_at":"2026-07-05T03:47:26Z"},{"alias_kind":"pith_short_12","alias_value":"63QHP7JICERV","created_at":"2026-07-05T03:47:26Z"},{"alias_kind":"pith_short_16","alias_value":"63QHP7JICERVFOO5","created_at":"2026-07-05T03:47:26Z"},{"alias_kind":"pith_short_8","alias_value":"63QHP7JI","created_at":"2026-07-05T03:47:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:63QHP7JICERVFOO57SEV7HXMPD","target":"record","payload":{"canonical_record":{"source":{"id":"2111.06977","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-12T22:53:28Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"5148a28f90b716072f8aefc5f2475c3411f15b173d8e9fe359fd050393cd8fe1","abstract_canon_sha256":"e55f5f95a4cac99cb9f493e26d2850942eb31a4d6002319debc1461947a6d8be"},"schema_version":"1.0"},"canonical_sha256":"f6e077fd28112352b9ddfc895f9eec78e88a5bcfb8206c0b101ab5ba137c91ee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:47:26.493563Z","signature_b64":"APLbbEYRtuyRrpaUa7dkP5sJ9to5Ffe8TQ7b8R/1sgPbJtMEzcnD1VRVCUrKip7NgRZ6ilFwDVIUDhABXrjqCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6e077fd28112352b9ddfc895f9eec78e88a5bcfb8206c0b101ab5ba137c91ee","last_reissued_at":"2026-07-05T03:47:26.493036Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:47:26.493036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.06977","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":"2026-07-05T03:47:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JJ6VB2B438twwpxmaY66m9Ic8D445n/5SElZAjFZdWmACfHMYxc4YzjzpLse4I9O02ZvjHvV5JFMhYsdDZEuCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T12:20:06.570566Z"},"content_sha256":"beff2c2ab65db8e62461c5d822ca55784e10ca975da7b9112b99f3e078566552","schema_version":"1.0","event_id":"sha256:beff2c2ab65db8e62461c5d822ca55784e10ca975da7b9112b99f3e078566552"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:63QHP7JICERVFOO57SEV7HXMPD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scalable Diverse Model Selection for Accessible Transfer Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Daniel Bolya, Judy Hoffman, Rohit Mittapalli","submitted_at":"2021-11-12T22:53:28Z","abstract_excerpt":"With the preponderance of pretrained deep learning models available off-the-shelf from model banks today, finding the best weights to fine-tune to your use-case can be a daunting task. Several methods have recently been proposed to find good models for transfer learning, but they either don't scale well to large model banks or don't perform well on the diversity of off-the-shelf models. Ideally the question we want to answer is, \"given some data and a source model, can you quickly predict the model's accuracy after fine-tuning?\" In this paper, we formalize this setting as \"Scalable Diverse Mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.06977","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/2111.06977/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":"2026-07-05T03:47:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vHywyjFaobhxP2iYP6X+vUDidpoxR3t4fa6KfZKkFoeo6soZmKoe+oEZTkYDvHiVQ+NQn61Hb75811QXI1eDAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T12:20:06.571277Z"},"content_sha256":"08ebd5132e2c7f9901e437122d98d5100763bb6ff8b14fe168d68249902c12d7","schema_version":"1.0","event_id":"sha256:08ebd5132e2c7f9901e437122d98d5100763bb6ff8b14fe168d68249902c12d7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/63QHP7JICERVFOO57SEV7HXMPD/bundle.json","state_url":"https://pith.science/pith/63QHP7JICERVFOO57SEV7HXMPD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/63QHP7JICERVFOO57SEV7HXMPD/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":"2026-08-12T12:20:06Z","links":{"resolver":"https://pith.science/pith/63QHP7JICERVFOO57SEV7HXMPD","bundle":"https://pith.science/pith/63QHP7JICERVFOO57SEV7HXMPD/bundle.json","state":"https://pith.science/pith/63QHP7JICERVFOO57SEV7HXMPD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/63QHP7JICERVFOO57SEV7HXMPD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:63QHP7JICERVFOO57SEV7HXMPD","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":"e55f5f95a4cac99cb9f493e26d2850942eb31a4d6002319debc1461947a6d8be","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-12T22:53:28Z","title_canon_sha256":"5148a28f90b716072f8aefc5f2475c3411f15b173d8e9fe359fd050393cd8fe1"},"schema_version":"1.0","source":{"id":"2111.06977","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.06977","created_at":"2026-07-05T03:47:26Z"},{"alias_kind":"arxiv_version","alias_value":"2111.06977v2","created_at":"2026-07-05T03:47:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.06977","created_at":"2026-07-05T03:47:26Z"},{"alias_kind":"pith_short_12","alias_value":"63QHP7JICERV","created_at":"2026-07-05T03:47:26Z"},{"alias_kind":"pith_short_16","alias_value":"63QHP7JICERVFOO5","created_at":"2026-07-05T03:47:26Z"},{"alias_kind":"pith_short_8","alias_value":"63QHP7JI","created_at":"2026-07-05T03:47:26Z"}],"graph_snapshots":[{"event_id":"sha256:08ebd5132e2c7f9901e437122d98d5100763bb6ff8b14fe168d68249902c12d7","target":"graph","created_at":"2026-07-05T03:47:26Z","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/2111.06977/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the preponderance of pretrained deep learning models available off-the-shelf from model banks today, finding the best weights to fine-tune to your use-case can be a daunting task. Several methods have recently been proposed to find good models for transfer learning, but they either don't scale well to large model banks or don't perform well on the diversity of off-the-shelf models. Ideally the question we want to answer is, \"given some data and a source model, can you quickly predict the model's accuracy after fine-tuning?\" In this paper, we formalize this setting as \"Scalable Diverse Mod","authors_text":"Daniel Bolya, Judy Hoffman, Rohit Mittapalli","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-12T22:53:28Z","title":"Scalable Diverse Model Selection for Accessible Transfer Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.06977","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:beff2c2ab65db8e62461c5d822ca55784e10ca975da7b9112b99f3e078566552","target":"record","created_at":"2026-07-05T03:47:26Z","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":"e55f5f95a4cac99cb9f493e26d2850942eb31a4d6002319debc1461947a6d8be","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-12T22:53:28Z","title_canon_sha256":"5148a28f90b716072f8aefc5f2475c3411f15b173d8e9fe359fd050393cd8fe1"},"schema_version":"1.0","source":{"id":"2111.06977","kind":"arxiv","version":2}},"canonical_sha256":"f6e077fd28112352b9ddfc895f9eec78e88a5bcfb8206c0b101ab5ba137c91ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f6e077fd28112352b9ddfc895f9eec78e88a5bcfb8206c0b101ab5ba137c91ee","first_computed_at":"2026-07-05T03:47:26.493036Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:47:26.493036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"APLbbEYRtuyRrpaUa7dkP5sJ9to5Ffe8TQ7b8R/1sgPbJtMEzcnD1VRVCUrKip7NgRZ6ilFwDVIUDhABXrjqCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:47:26.493563Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.06977","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:beff2c2ab65db8e62461c5d822ca55784e10ca975da7b9112b99f3e078566552","sha256:08ebd5132e2c7f9901e437122d98d5100763bb6ff8b14fe168d68249902c12d7"],"state_sha256":"b85d434a7c6f81dbaf3ba4fb25cbc8707d39af63d57f2c61edf9064b93dcef86"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NUXOnovKz+Tm+RPfLESYAR6Hs5Jb8k6P61xXQ5gCSEVAFCIeoMceYeWTa6Z0kqTEtQD2Cff/eUeayYaHG7gvAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T12:20:06.579127Z","bundle_sha256":"a7995e324a705021c8296a715f764b8410c531381220348dba30b1b35a4d1c6d"}}