{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:J5CWA5PQ5RIZSOWN7XITNCZJJT","short_pith_number":"pith:J5CWA5PQ","canonical_record":{"source":{"id":"2209.15589","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-30T17:04:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"62e1768c756371a553eba74153b86dd7e122751904b70411aa2487442d0bf703","abstract_canon_sha256":"5726c995af6a84e0802ccb1c24e835eff17a427353223f2ef9c18d52d51ea7de"},"schema_version":"1.0"},"canonical_sha256":"4f456075f0ec51993acdfdd1368b294cfbfb15ba27e8e556ffdc1e502adb1ffb","source":{"kind":"arxiv","id":"2209.15589","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.15589","created_at":"2026-07-05T05:08:04Z"},{"alias_kind":"arxiv_version","alias_value":"2209.15589v4","created_at":"2026-07-05T05:08:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.15589","created_at":"2026-07-05T05:08:04Z"},{"alias_kind":"pith_short_12","alias_value":"J5CWA5PQ5RIZ","created_at":"2026-07-05T05:08:04Z"},{"alias_kind":"pith_short_16","alias_value":"J5CWA5PQ5RIZSOWN","created_at":"2026-07-05T05:08:04Z"},{"alias_kind":"pith_short_8","alias_value":"J5CWA5PQ","created_at":"2026-07-05T05:08:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:J5CWA5PQ5RIZSOWN7XITNCZJJT","target":"record","payload":{"canonical_record":{"source":{"id":"2209.15589","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-30T17:04:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"62e1768c756371a553eba74153b86dd7e122751904b70411aa2487442d0bf703","abstract_canon_sha256":"5726c995af6a84e0802ccb1c24e835eff17a427353223f2ef9c18d52d51ea7de"},"schema_version":"1.0"},"canonical_sha256":"4f456075f0ec51993acdfdd1368b294cfbfb15ba27e8e556ffdc1e502adb1ffb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:08:04.997536Z","signature_b64":"eG5wCqxDeMmkmgSkOP8xC+fHoQVTb4t3c88j/osiXofJvWSobqfh/wrtEZs3PB43+TV0ddAceqFLB03lYsX+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f456075f0ec51993acdfdd1368b294cfbfb15ba27e8e556ffdc1e502adb1ffb","last_reissued_at":"2026-07-05T05:08:04.997108Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:08:04.997108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.15589","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:08:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TZyzAzjtNEOUE6kMK5xtZp41LmQvvGOIlEpBXHxVFDCEo2lwBxDOYmURENp698I87IJE8fFQSxB2VzU4j6K5BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T03:06:29.064772Z"},"content_sha256":"434a8e069efb2ff7fbb2458d282903706cdf34d08d4892dcecf25d2f3942ac6d","schema_version":"1.0","event_id":"sha256:434a8e069efb2ff7fbb2458d282903706cdf34d08d4892dcecf25d2f3942ac6d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:J5CWA5PQ5RIZSOWN7XITNCZJJT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Where Should I Spend My FLOPS? Efficiency Evaluations of Visual Pre-training Methods","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrew Jaegle, Evan Shelhamer, Jo\\~ao Carreira, Nikhil Parthasarathy, Olivier H\\'enaff, Relja Arandjelovic, Skanda Koppula, Yazhe Li","submitted_at":"2022-09-30T17:04:55Z","abstract_excerpt":"Self-supervised methods have achieved remarkable success in transfer learning, often achieving the same or better accuracy than supervised pre-training. Most prior work has done so by increasing pre-training computation by adding complex data augmentation, multiple views, or lengthy training schedules. In this work, we investigate a related, but orthogonal question: given a fixed FLOP budget, what are the best datasets, models, and (self-)supervised training methods for obtaining high accuracy on representative visual tasks? Given the availability of large datasets, this setting is often more "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.15589","kind":"arxiv","version":4},"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/2209.15589/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":"2026-07-05T05:08:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PyD7QkBEmOl22kStZUisFXP/WD3oKJaFZCYg4FPH0Qs8k0B44T6lwLnrmJm9gM7yf7ll2By7F5t1gXPwNwavDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T03:06:29.065304Z"},"content_sha256":"fc0aa4b4a09df7e95c2db9824dd0c2fd1ba05a8c60d68d2bf5bdce12b0b8e497","schema_version":"1.0","event_id":"sha256:fc0aa4b4a09df7e95c2db9824dd0c2fd1ba05a8c60d68d2bf5bdce12b0b8e497"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J5CWA5PQ5RIZSOWN7XITNCZJJT/bundle.json","state_url":"https://pith.science/pith/J5CWA5PQ5RIZSOWN7XITNCZJJT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J5CWA5PQ5RIZSOWN7XITNCZJJT/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":"2026-08-14T03:06:29Z","links":{"resolver":"https://pith.science/pith/J5CWA5PQ5RIZSOWN7XITNCZJJT","bundle":"https://pith.science/pith/J5CWA5PQ5RIZSOWN7XITNCZJJT/bundle.json","state":"https://pith.science/pith/J5CWA5PQ5RIZSOWN7XITNCZJJT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J5CWA5PQ5RIZSOWN7XITNCZJJT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:J5CWA5PQ5RIZSOWN7XITNCZJJT","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":"5726c995af6a84e0802ccb1c24e835eff17a427353223f2ef9c18d52d51ea7de","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-30T17:04:55Z","title_canon_sha256":"62e1768c756371a553eba74153b86dd7e122751904b70411aa2487442d0bf703"},"schema_version":"1.0","source":{"id":"2209.15589","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.15589","created_at":"2026-07-05T05:08:04Z"},{"alias_kind":"arxiv_version","alias_value":"2209.15589v4","created_at":"2026-07-05T05:08:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.15589","created_at":"2026-07-05T05:08:04Z"},{"alias_kind":"pith_short_12","alias_value":"J5CWA5PQ5RIZ","created_at":"2026-07-05T05:08:04Z"},{"alias_kind":"pith_short_16","alias_value":"J5CWA5PQ5RIZSOWN","created_at":"2026-07-05T05:08:04Z"},{"alias_kind":"pith_short_8","alias_value":"J5CWA5PQ","created_at":"2026-07-05T05:08:04Z"}],"graph_snapshots":[{"event_id":"sha256:fc0aa4b4a09df7e95c2db9824dd0c2fd1ba05a8c60d68d2bf5bdce12b0b8e497","target":"graph","created_at":"2026-07-05T05:08:04Z","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/2209.15589/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-supervised methods have achieved remarkable success in transfer learning, often achieving the same or better accuracy than supervised pre-training. Most prior work has done so by increasing pre-training computation by adding complex data augmentation, multiple views, or lengthy training schedules. In this work, we investigate a related, but orthogonal question: given a fixed FLOP budget, what are the best datasets, models, and (self-)supervised training methods for obtaining high accuracy on representative visual tasks? Given the availability of large datasets, this setting is often more ","authors_text":"Andrew Jaegle, Evan Shelhamer, Jo\\~ao Carreira, Nikhil Parthasarathy, Olivier H\\'enaff, Relja Arandjelovic, Skanda Koppula, Yazhe Li","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-30T17:04:55Z","title":"Where Should I Spend My FLOPS? Efficiency Evaluations of Visual Pre-training Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.15589","kind":"arxiv","version":4},"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":"sha256:434a8e069efb2ff7fbb2458d282903706cdf34d08d4892dcecf25d2f3942ac6d","target":"record","created_at":"2026-07-05T05:08:04Z","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":"5726c995af6a84e0802ccb1c24e835eff17a427353223f2ef9c18d52d51ea7de","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-30T17:04:55Z","title_canon_sha256":"62e1768c756371a553eba74153b86dd7e122751904b70411aa2487442d0bf703"},"schema_version":"1.0","source":{"id":"2209.15589","kind":"arxiv","version":4}},"canonical_sha256":"4f456075f0ec51993acdfdd1368b294cfbfb15ba27e8e556ffdc1e502adb1ffb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f456075f0ec51993acdfdd1368b294cfbfb15ba27e8e556ffdc1e502adb1ffb","first_computed_at":"2026-07-05T05:08:04.997108Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:08:04.997108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eG5wCqxDeMmkmgSkOP8xC+fHoQVTb4t3c88j/osiXofJvWSobqfh/wrtEZs3PB43+TV0ddAceqFLB03lYsX+Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:08:04.997536Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.15589","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:434a8e069efb2ff7fbb2458d282903706cdf34d08d4892dcecf25d2f3942ac6d","sha256:fc0aa4b4a09df7e95c2db9824dd0c2fd1ba05a8c60d68d2bf5bdce12b0b8e497"],"state_sha256":"2a01275518e9cc173e07a58abde032789759352d02c1e92f1ceac6801317c3bf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rTragWtqsO3SaXE+fSJLY65tkQ5l6/Gg2fryk5UIn2jFTGHm/LW2Pk0rmot6ZNaozZ5OfrHaxHgpoxDgaVqQAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T03:06:29.069689Z","bundle_sha256":"775c67fad1eb4b1e74488913af8b90af32dfedb6357672aaf69861eef8e20468"}}