{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JQ3WXDJXSB53QWOOEICR5OPFAY","short_pith_number":"pith:JQ3WXDJX","canonical_record":{"source":{"id":"2405.08815","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-14T17:59:40Z","cross_cats_sorted":[],"title_canon_sha256":"2fc712dae4e9795f372ac311b9bf00d6e743d1cb1e8c13666c87dea501de8061","abstract_canon_sha256":"2fef3afad2fec59e14b882247c1671af935d2f5bd0bcded831e146e73ed40a3f"},"schema_version":"1.0"},"canonical_sha256":"4c376b8d37907bb859ce22051eb9e5063ac6d1b9f372f8ac98f26d9e264312e4","source":{"kind":"arxiv","id":"2405.08815","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.08815","created_at":"2026-07-05T08:19:06Z"},{"alias_kind":"arxiv_version","alias_value":"2405.08815v1","created_at":"2026-07-05T08:19:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.08815","created_at":"2026-07-05T08:19:06Z"},{"alias_kind":"pith_short_12","alias_value":"JQ3WXDJXSB53","created_at":"2026-07-05T08:19:06Z"},{"alias_kind":"pith_short_16","alias_value":"JQ3WXDJXSB53QWOO","created_at":"2026-07-05T08:19:06Z"},{"alias_kind":"pith_short_8","alias_value":"JQ3WXDJX","created_at":"2026-07-05T08:19:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JQ3WXDJXSB53QWOOEICR5OPFAY","target":"record","payload":{"canonical_record":{"source":{"id":"2405.08815","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-14T17:59:40Z","cross_cats_sorted":[],"title_canon_sha256":"2fc712dae4e9795f372ac311b9bf00d6e743d1cb1e8c13666c87dea501de8061","abstract_canon_sha256":"2fef3afad2fec59e14b882247c1671af935d2f5bd0bcded831e146e73ed40a3f"},"schema_version":"1.0"},"canonical_sha256":"4c376b8d37907bb859ce22051eb9e5063ac6d1b9f372f8ac98f26d9e264312e4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:19:06.099263Z","signature_b64":"TkpwFvg390jdC5EcLyzxjnPwpQ+In4fVMjZIvsXtUGcLPPa1igTSZxly8gxjob47J13oTjTVVVn+ckSOFe9CBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c376b8d37907bb859ce22051eb9e5063ac6d1b9f372f8ac98f26d9e264312e4","last_reissued_at":"2026-07-05T08:19:06.098813Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:19:06.098813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.08815","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:19:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S6Sq/hDs7Whj9NlLGmVHzf8w5PeKy7liFcckkxJwmN7KbjzaN1j4XmTEbWZPlUkoPzFy4aXBdS9knb6aiAuVDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T07:59:55.244530Z"},"content_sha256":"7f06de7c7e8178fa49ac0b3f1168d249a72e3c2813b057e7efc49534f791bd7e","schema_version":"1.0","event_id":"sha256:7f06de7c7e8178fa49ac0b3f1168d249a72e3c2813b057e7efc49534f791bd7e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JQ3WXDJXSB53QWOOEICR5OPFAY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Vision-Language Pre-training by Cluster Masking","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Owens, Zihao Wei, Zixuan Pan","submitted_at":"2024-05-14T17:59:40Z","abstract_excerpt":"We propose a simple strategy for masking image patches during visual-language contrastive learning that improves the quality of the learned representations and the training speed. During each iteration of training, we randomly mask clusters of visually similar image patches, as measured by their raw pixel intensities. This provides an extra learning signal, beyond the contrastive training itself, since it forces a model to predict words for masked visual structures solely from context. It also speeds up training by reducing the amount of data used in each image. We evaluate the effectiveness o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.08815","kind":"arxiv","version":1},"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/2405.08815/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":"2026-07-05T08:19:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fzeVYHV31sA1AyScS8/8HxhjxA1QVhhCU6hnjk4/3Z/4j5MzqYMZ+m/Xygh4fXMUavREKdQ1bjGj9h1zfXZrCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T07:59:55.245036Z"},"content_sha256":"4c6822724ebd5f985c4887ff9c33a4ee7449aec6a5f623bb1a962ab066c486e5","schema_version":"1.0","event_id":"sha256:4c6822724ebd5f985c4887ff9c33a4ee7449aec6a5f623bb1a962ab066c486e5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JQ3WXDJXSB53QWOOEICR5OPFAY/bundle.json","state_url":"https://pith.science/pith/JQ3WXDJXSB53QWOOEICR5OPFAY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JQ3WXDJXSB53QWOOEICR5OPFAY/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":"2026-08-12T07:59:55Z","links":{"resolver":"https://pith.science/pith/JQ3WXDJXSB53QWOOEICR5OPFAY","bundle":"https://pith.science/pith/JQ3WXDJXSB53QWOOEICR5OPFAY/bundle.json","state":"https://pith.science/pith/JQ3WXDJXSB53QWOOEICR5OPFAY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JQ3WXDJXSB53QWOOEICR5OPFAY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JQ3WXDJXSB53QWOOEICR5OPFAY","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":"2fef3afad2fec59e14b882247c1671af935d2f5bd0bcded831e146e73ed40a3f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-14T17:59:40Z","title_canon_sha256":"2fc712dae4e9795f372ac311b9bf00d6e743d1cb1e8c13666c87dea501de8061"},"schema_version":"1.0","source":{"id":"2405.08815","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.08815","created_at":"2026-07-05T08:19:06Z"},{"alias_kind":"arxiv_version","alias_value":"2405.08815v1","created_at":"2026-07-05T08:19:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.08815","created_at":"2026-07-05T08:19:06Z"},{"alias_kind":"pith_short_12","alias_value":"JQ3WXDJXSB53","created_at":"2026-07-05T08:19:06Z"},{"alias_kind":"pith_short_16","alias_value":"JQ3WXDJXSB53QWOO","created_at":"2026-07-05T08:19:06Z"},{"alias_kind":"pith_short_8","alias_value":"JQ3WXDJX","created_at":"2026-07-05T08:19:06Z"}],"graph_snapshots":[{"event_id":"sha256:4c6822724ebd5f985c4887ff9c33a4ee7449aec6a5f623bb1a962ab066c486e5","target":"graph","created_at":"2026-07-05T08:19:06Z","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/2405.08815/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a simple strategy for masking image patches during visual-language contrastive learning that improves the quality of the learned representations and the training speed. During each iteration of training, we randomly mask clusters of visually similar image patches, as measured by their raw pixel intensities. This provides an extra learning signal, beyond the contrastive training itself, since it forces a model to predict words for masked visual structures solely from context. It also speeds up training by reducing the amount of data used in each image. We evaluate the effectiveness o","authors_text":"Andrew Owens, Zihao Wei, Zixuan Pan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-14T17:59:40Z","title":"Efficient Vision-Language Pre-training by Cluster Masking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.08815","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":"sha256:7f06de7c7e8178fa49ac0b3f1168d249a72e3c2813b057e7efc49534f791bd7e","target":"record","created_at":"2026-07-05T08:19:06Z","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":"2fef3afad2fec59e14b882247c1671af935d2f5bd0bcded831e146e73ed40a3f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-14T17:59:40Z","title_canon_sha256":"2fc712dae4e9795f372ac311b9bf00d6e743d1cb1e8c13666c87dea501de8061"},"schema_version":"1.0","source":{"id":"2405.08815","kind":"arxiv","version":1}},"canonical_sha256":"4c376b8d37907bb859ce22051eb9e5063ac6d1b9f372f8ac98f26d9e264312e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c376b8d37907bb859ce22051eb9e5063ac6d1b9f372f8ac98f26d9e264312e4","first_computed_at":"2026-07-05T08:19:06.098813Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:19:06.098813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TkpwFvg390jdC5EcLyzxjnPwpQ+In4fVMjZIvsXtUGcLPPa1igTSZxly8gxjob47J13oTjTVVVn+ckSOFe9CBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:19:06.099263Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.08815","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f06de7c7e8178fa49ac0b3f1168d249a72e3c2813b057e7efc49534f791bd7e","sha256:4c6822724ebd5f985c4887ff9c33a4ee7449aec6a5f623bb1a962ab066c486e5"],"state_sha256":"70566341386674d910508757a6fee71794844743a64df7faecb5719ef4b83682"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BQcs0m1Yheps8PklTxS0sbzKoNuhCZjtBXxdTRNKJhhdm1M0SPh9RuUFflstMo6sZXtKoT1c5krjHFt+V6FXDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T07:59:55.249884Z","bundle_sha256":"0169a0f6c9fb538f82bacb361487a1096d5566e9c644ec2461f4140ebd5ef34e"}}