{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:MPUEBW3PD2SNGNGBFEUAJ25OL2","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":"427b991e33fa555df491603e484c9eadcebb39215ff17d164825dc5bd8109835","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-12T17:58:56Z","title_canon_sha256":"9fd441e56c5405e345cf9f60931a7b60d2338d0a71c2934e85e8eb58b28c58d7"},"schema_version":"1.0","source":{"id":"2108.05887","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.05887","created_at":"2026-07-05T03:05:23Z"},{"alias_kind":"arxiv_version","alias_value":"2108.05887v1","created_at":"2026-07-05T03:05:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.05887","created_at":"2026-07-05T03:05:23Z"},{"alias_kind":"pith_short_12","alias_value":"MPUEBW3PD2SN","created_at":"2026-07-05T03:05:23Z"},{"alias_kind":"pith_short_16","alias_value":"MPUEBW3PD2SNGNGB","created_at":"2026-07-05T03:05:23Z"},{"alias_kind":"pith_short_8","alias_value":"MPUEBW3P","created_at":"2026-07-05T03:05:23Z"}],"graph_snapshots":[{"event_id":"sha256:4ff79ab849447b593cde5b516e95493c20c5529a64647a1df5c9ad2d865db5b4","target":"graph","created_at":"2026-07-05T03:05:23Z","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/2108.05887/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale pretraining of visual representations has led to state-of-the-art performance on a range of benchmark computer vision tasks, yet the benefits of these techniques at extreme scale in complex production systems has been relatively unexplored. We consider the case of a popular visual discovery product, where these representations are trained with multi-task learning, from use-case specific visual understanding (e.g. skin tone classification) to general representation learning for all visual content (e.g. embeddings for retrieval). In this work, we describe how we (1) generate a datase","authors_text":"Andrew Zhai, Dmitry Kislyuk, Dong Huk Park, Hao-Yu Wu, Josh Beal","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-12T17:58:56Z","title":"Billion-Scale Pretraining with Vision Transformers for Multi-Task Visual Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.05887","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:f63eaa6b93233f6b0abdb46ee05da38c9c0810573bc5436e2b389fa9fe7e56d9","target":"record","created_at":"2026-07-05T03:05:23Z","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":"427b991e33fa555df491603e484c9eadcebb39215ff17d164825dc5bd8109835","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-12T17:58:56Z","title_canon_sha256":"9fd441e56c5405e345cf9f60931a7b60d2338d0a71c2934e85e8eb58b28c58d7"},"schema_version":"1.0","source":{"id":"2108.05887","kind":"arxiv","version":1}},"canonical_sha256":"63e840db6f1ea4d334c1292804ebae5e9d760639fbcdce2fda09e34feb82b5eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63e840db6f1ea4d334c1292804ebae5e9d760639fbcdce2fda09e34feb82b5eb","first_computed_at":"2026-07-05T03:05:23.540542Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:05:23.540542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7Ivt5lmGxiIp7cfv+NZ9+c6AGF7u5U5raIwAMnTtC+N20rio2ugRKNjZUtsYrTQqjgaPsZeIx4SHIrd4yZn6CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:05:23.540935Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.05887","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f63eaa6b93233f6b0abdb46ee05da38c9c0810573bc5436e2b389fa9fe7e56d9","sha256:4ff79ab849447b593cde5b516e95493c20c5529a64647a1df5c9ad2d865db5b4"],"state_sha256":"942b87e6fe0fd8129eef0d9018337d1873c297b9cae5fc836ba25e1bf714574e"}