{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:PMF4WBSRQLHHFHYSCLGPY4HND3","short_pith_number":"pith:PMF4WBSR","canonical_record":{"source":{"id":"2102.05918","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-02-11T10:08:12Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"014b1ee0d362b8ad566293f27262f7584eb3fae1619db2fbf94fe78709138490","abstract_canon_sha256":"d00fe77f2ddaf8c54ef23758c3a5ff3a82d546ddd1544a89cedb9b606d7a7939"},"schema_version":"1.0"},"canonical_sha256":"7b0bcb065182ce729f1212ccfc70ed1ec9257b161817588c5a22711f2257eead","source":{"kind":"arxiv","id":"2102.05918","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.05918","created_at":"2026-07-05T02:48:21Z"},{"alias_kind":"arxiv_version","alias_value":"2102.05918v2","created_at":"2026-07-05T02:48:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.05918","created_at":"2026-07-05T02:48:21Z"},{"alias_kind":"pith_short_12","alias_value":"PMF4WBSRQLHH","created_at":"2026-07-05T02:48:21Z"},{"alias_kind":"pith_short_16","alias_value":"PMF4WBSRQLHHFHYS","created_at":"2026-07-05T02:48:21Z"},{"alias_kind":"pith_short_8","alias_value":"PMF4WBSR","created_at":"2026-07-05T02:48:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:PMF4WBSRQLHHFHYSCLGPY4HND3","target":"record","payload":{"canonical_record":{"source":{"id":"2102.05918","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-02-11T10:08:12Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"014b1ee0d362b8ad566293f27262f7584eb3fae1619db2fbf94fe78709138490","abstract_canon_sha256":"d00fe77f2ddaf8c54ef23758c3a5ff3a82d546ddd1544a89cedb9b606d7a7939"},"schema_version":"1.0"},"canonical_sha256":"7b0bcb065182ce729f1212ccfc70ed1ec9257b161817588c5a22711f2257eead","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:48:21.053136Z","signature_b64":"NkhnZDN/XlA45VXW9PRk/xQ/+icnX7Hy+3qVZxYOg0Clkk1URVzOul15U0bSpn/wdE2Js6pBRLTR6l8YtyfIBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b0bcb065182ce729f1212ccfc70ed1ec9257b161817588c5a22711f2257eead","last_reissued_at":"2026-07-05T02:48:21.052575Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:48:21.052575Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.05918","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":"2026-07-05T02:48:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vY7UnNaNDtmPpYnxwaKk1/Ai4DPWmkmyOzTW6jqE97pR5dCEyx4mbyNFn62y6Kb7DfzyOnRqLQ2iOQZHGZGtCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:02:49.829497Z"},"content_sha256":"56f4cd62e86d6a9e95254f173348cb0939600679e5127e7f6b65ebebf237220e","schema_version":"1.0","event_id":"sha256:56f4cd62e86d6a9e95254f173348cb0939600679e5127e7f6b65ebebf237220e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:PMF4WBSRQLHHFHYSCLGPY4HND3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chao Jia, Hieu Pham, Quoc V. Le, Tom Duerig, Ye Xia, Yinfei Yang, Yi-Ting Chen, Yunhsuan Sung, Zarana Parekh, Zhen Li","submitted_at":"2021-02-11T10:08:12Z","abstract_excerpt":"Pre-trained representations are becoming crucial for many NLP and perception tasks. While representation learning in NLP has transitioned to training on raw text without human annotations, visual and vision-language representations still rely heavily on curated training datasets that are expensive or require expert knowledge. For vision applications, representations are mostly learned using datasets with explicit class labels such as ImageNet or OpenImages. For vision-language, popular datasets like Conceptual Captions, MSCOCO, or CLIP all involve a non-trivial data collection (and cleaning) p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.05918","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/2102.05918/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":"2026-07-05T02:48:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O5bOAzS+XaE8SYPneY88/mx1Gv8HGOhEPQ84i6QXeJ8PKBAdW0oPhDZzve6wFNDC+xZ01IIwGkIm9X7zStxcBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:02:49.830053Z"},"content_sha256":"4a049c65a2b3f49af125c23d957f0e02852737c4d17fdf0cd7718585b3aea435","schema_version":"1.0","event_id":"sha256:4a049c65a2b3f49af125c23d957f0e02852737c4d17fdf0cd7718585b3aea435"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PMF4WBSRQLHHFHYSCLGPY4HND3/bundle.json","state_url":"https://pith.science/pith/PMF4WBSRQLHHFHYSCLGPY4HND3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PMF4WBSRQLHHFHYSCLGPY4HND3/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":"2026-08-04T23:02:49Z","links":{"resolver":"https://pith.science/pith/PMF4WBSRQLHHFHYSCLGPY4HND3","bundle":"https://pith.science/pith/PMF4WBSRQLHHFHYSCLGPY4HND3/bundle.json","state":"https://pith.science/pith/PMF4WBSRQLHHFHYSCLGPY4HND3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PMF4WBSRQLHHFHYSCLGPY4HND3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:PMF4WBSRQLHHFHYSCLGPY4HND3","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":"d00fe77f2ddaf8c54ef23758c3a5ff3a82d546ddd1544a89cedb9b606d7a7939","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-02-11T10:08:12Z","title_canon_sha256":"014b1ee0d362b8ad566293f27262f7584eb3fae1619db2fbf94fe78709138490"},"schema_version":"1.0","source":{"id":"2102.05918","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.05918","created_at":"2026-07-05T02:48:21Z"},{"alias_kind":"arxiv_version","alias_value":"2102.05918v2","created_at":"2026-07-05T02:48:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.05918","created_at":"2026-07-05T02:48:21Z"},{"alias_kind":"pith_short_12","alias_value":"PMF4WBSRQLHH","created_at":"2026-07-05T02:48:21Z"},{"alias_kind":"pith_short_16","alias_value":"PMF4WBSRQLHHFHYS","created_at":"2026-07-05T02:48:21Z"},{"alias_kind":"pith_short_8","alias_value":"PMF4WBSR","created_at":"2026-07-05T02:48:21Z"}],"graph_snapshots":[{"event_id":"sha256:4a049c65a2b3f49af125c23d957f0e02852737c4d17fdf0cd7718585b3aea435","target":"graph","created_at":"2026-07-05T02:48:21Z","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/2102.05918/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained representations are becoming crucial for many NLP and perception tasks. While representation learning in NLP has transitioned to training on raw text without human annotations, visual and vision-language representations still rely heavily on curated training datasets that are expensive or require expert knowledge. For vision applications, representations are mostly learned using datasets with explicit class labels such as ImageNet or OpenImages. For vision-language, popular datasets like Conceptual Captions, MSCOCO, or CLIP all involve a non-trivial data collection (and cleaning) p","authors_text":"Chao Jia, Hieu Pham, Quoc V. Le, Tom Duerig, Ye Xia, Yinfei Yang, Yi-Ting Chen, Yunhsuan Sung, Zarana Parekh, Zhen Li","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-02-11T10:08:12Z","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.05918","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":"sha256:56f4cd62e86d6a9e95254f173348cb0939600679e5127e7f6b65ebebf237220e","target":"record","created_at":"2026-07-05T02:48:21Z","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":"d00fe77f2ddaf8c54ef23758c3a5ff3a82d546ddd1544a89cedb9b606d7a7939","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-02-11T10:08:12Z","title_canon_sha256":"014b1ee0d362b8ad566293f27262f7584eb3fae1619db2fbf94fe78709138490"},"schema_version":"1.0","source":{"id":"2102.05918","kind":"arxiv","version":2}},"canonical_sha256":"7b0bcb065182ce729f1212ccfc70ed1ec9257b161817588c5a22711f2257eead","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b0bcb065182ce729f1212ccfc70ed1ec9257b161817588c5a22711f2257eead","first_computed_at":"2026-07-05T02:48:21.052575Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:48:21.052575Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NkhnZDN/XlA45VXW9PRk/xQ/+icnX7Hy+3qVZxYOg0Clkk1URVzOul15U0bSpn/wdE2Js6pBRLTR6l8YtyfIBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:48:21.053136Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.05918","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:56f4cd62e86d6a9e95254f173348cb0939600679e5127e7f6b65ebebf237220e","sha256:4a049c65a2b3f49af125c23d957f0e02852737c4d17fdf0cd7718585b3aea435"],"state_sha256":"0e1d76b7c01048e1d6c75723353e0fc86022b26f956a2765389e8419ea85d20c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vvSCNKHlIflMvlvCBa5TKG0XvCBDpCYGnhXChu7oJsOIfY9RfjY3969CckAvUtKaIOvXRO+3LwUFjKmrxB3KAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T23:02:49.834156Z","bundle_sha256":"f342ba3bb48b8b991c14a3c0cefd99289c032e6f98e0b08cd02df46124deced4"}}