{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:N6QRLZKVFAJZRYPZ6F6NVXFI4Q","short_pith_number":"pith:N6QRLZKV","canonical_record":{"source":{"id":"2208.06049","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-08-11T21:58:36Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"911714e6f1374fd2853a02badc922a206c4232f1b9c3a5928525eb1c60f9316f","abstract_canon_sha256":"48df178bab7f32759a8825636d2befe98b223086b16b047c8f190f02ff81aaf2"},"schema_version":"1.0"},"canonical_sha256":"6fa115e555281398e1f9f17cdadca8e4067741291ef42e31cb5573852c12f825","source":{"kind":"arxiv","id":"2208.06049","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.06049","created_at":"2026-07-05T05:26:46Z"},{"alias_kind":"arxiv_version","alias_value":"2208.06049v3","created_at":"2026-07-05T05:26:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.06049","created_at":"2026-07-05T05:26:46Z"},{"alias_kind":"pith_short_12","alias_value":"N6QRLZKVFAJZ","created_at":"2026-07-05T05:26:46Z"},{"alias_kind":"pith_short_16","alias_value":"N6QRLZKVFAJZRYPZ","created_at":"2026-07-05T05:26:46Z"},{"alias_kind":"pith_short_8","alias_value":"N6QRLZKV","created_at":"2026-07-05T05:26:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:N6QRLZKVFAJZRYPZ6F6NVXFI4Q","target":"record","payload":{"canonical_record":{"source":{"id":"2208.06049","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-08-11T21:58:36Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"911714e6f1374fd2853a02badc922a206c4232f1b9c3a5928525eb1c60f9316f","abstract_canon_sha256":"48df178bab7f32759a8825636d2befe98b223086b16b047c8f190f02ff81aaf2"},"schema_version":"1.0"},"canonical_sha256":"6fa115e555281398e1f9f17cdadca8e4067741291ef42e31cb5573852c12f825","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:26:46.937037Z","signature_b64":"/pVaR9B04Hl+x6M3GL+hUOTO4X5JQ5vvyKsest/tuwLJi68hdJo8v2mF90IWGDcRDZSQNMz5yuIe8NZlBuh6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fa115e555281398e1f9f17cdadca8e4067741291ef42e31cb5573852c12f825","last_reissued_at":"2026-07-05T05:26:46.936627Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:26:46.936627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2208.06049","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:26:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k1Ey/7WBwBetrd7I3gX5XP3SmrmCClxz7K3WPv3pNCPs+YcOPhHeLGHUD1bZxcb79CpD+dNP2D77NPu4PnpXBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T03:27:21.314156Z"},"content_sha256":"e404dd1c88d14e05dd1bd56335a3a255419de12af748f72dd2192266578e8020","schema_version":"1.0","event_id":"sha256:e404dd1c88d14e05dd1bd56335a3a255419de12af748f72dd2192266578e8020"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:N6QRLZKVFAJZRYPZ6F6NVXFI4Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MILAN: Masked Image Pretraining on Language Assisted Representation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Fei Sun, Sun-Yuan Kung, Yen-Kuang Chen, Yuan Xie, Zejiang Hou","submitted_at":"2022-08-11T21:58:36Z","abstract_excerpt":"Self-attention based transformer models have been dominating many computer vision tasks in the past few years. Their superb model qualities heavily depend on the excessively large labeled image datasets. In order to reduce the reliance on large labeled datasets, reconstruction based masked autoencoders are gaining popularity, which learn high quality transferable representations from unlabeled images. For the same purpose, recent weakly supervised image pretraining methods explore language supervision from text captions accompanying the images. In this work, we propose masked image pretraining"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.06049","kind":"arxiv","version":3},"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/2208.06049/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":"2026-07-05T05:26:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OlPasGh3hKgyz5SFVIPTWFR9NrGOA2sy8IHTKYQ4OvICYUxtGSYrbRAkznRrcKlA3d0/uhtsEcWm+8NRCmDtAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T03:27:21.314874Z"},"content_sha256":"edc40808cb4c9941c2abeeb3a3b2b57d34e2407240599a629234b1dd5264465c","schema_version":"1.0","event_id":"sha256:edc40808cb4c9941c2abeeb3a3b2b57d34e2407240599a629234b1dd5264465c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N6QRLZKVFAJZRYPZ6F6NVXFI4Q/bundle.json","state_url":"https://pith.science/pith/N6QRLZKVFAJZRYPZ6F6NVXFI4Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N6QRLZKVFAJZRYPZ6F6NVXFI4Q/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":"2026-08-13T03:27:21Z","links":{"resolver":"https://pith.science/pith/N6QRLZKVFAJZRYPZ6F6NVXFI4Q","bundle":"https://pith.science/pith/N6QRLZKVFAJZRYPZ6F6NVXFI4Q/bundle.json","state":"https://pith.science/pith/N6QRLZKVFAJZRYPZ6F6NVXFI4Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N6QRLZKVFAJZRYPZ6F6NVXFI4Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:N6QRLZKVFAJZRYPZ6F6NVXFI4Q","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":"48df178bab7f32759a8825636d2befe98b223086b16b047c8f190f02ff81aaf2","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-08-11T21:58:36Z","title_canon_sha256":"911714e6f1374fd2853a02badc922a206c4232f1b9c3a5928525eb1c60f9316f"},"schema_version":"1.0","source":{"id":"2208.06049","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.06049","created_at":"2026-07-05T05:26:46Z"},{"alias_kind":"arxiv_version","alias_value":"2208.06049v3","created_at":"2026-07-05T05:26:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.06049","created_at":"2026-07-05T05:26:46Z"},{"alias_kind":"pith_short_12","alias_value":"N6QRLZKVFAJZ","created_at":"2026-07-05T05:26:46Z"},{"alias_kind":"pith_short_16","alias_value":"N6QRLZKVFAJZRYPZ","created_at":"2026-07-05T05:26:46Z"},{"alias_kind":"pith_short_8","alias_value":"N6QRLZKV","created_at":"2026-07-05T05:26:46Z"}],"graph_snapshots":[{"event_id":"sha256:edc40808cb4c9941c2abeeb3a3b2b57d34e2407240599a629234b1dd5264465c","target":"graph","created_at":"2026-07-05T05:26:46Z","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/2208.06049/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-attention based transformer models have been dominating many computer vision tasks in the past few years. Their superb model qualities heavily depend on the excessively large labeled image datasets. In order to reduce the reliance on large labeled datasets, reconstruction based masked autoencoders are gaining popularity, which learn high quality transferable representations from unlabeled images. For the same purpose, recent weakly supervised image pretraining methods explore language supervision from text captions accompanying the images. In this work, we propose masked image pretraining","authors_text":"Fei Sun, Sun-Yuan Kung, Yen-Kuang Chen, Yuan Xie, Zejiang Hou","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-08-11T21:58:36Z","title":"MILAN: Masked Image Pretraining on Language Assisted Representation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.06049","kind":"arxiv","version":3},"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:e404dd1c88d14e05dd1bd56335a3a255419de12af748f72dd2192266578e8020","target":"record","created_at":"2026-07-05T05:26:46Z","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":"48df178bab7f32759a8825636d2befe98b223086b16b047c8f190f02ff81aaf2","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-08-11T21:58:36Z","title_canon_sha256":"911714e6f1374fd2853a02badc922a206c4232f1b9c3a5928525eb1c60f9316f"},"schema_version":"1.0","source":{"id":"2208.06049","kind":"arxiv","version":3}},"canonical_sha256":"6fa115e555281398e1f9f17cdadca8e4067741291ef42e31cb5573852c12f825","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6fa115e555281398e1f9f17cdadca8e4067741291ef42e31cb5573852c12f825","first_computed_at":"2026-07-05T05:26:46.936627Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:26:46.936627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/pVaR9B04Hl+x6M3GL+hUOTO4X5JQ5vvyKsest/tuwLJi68hdJo8v2mF90IWGDcRDZSQNMz5yuIe8NZlBuh6AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:26:46.937037Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.06049","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e404dd1c88d14e05dd1bd56335a3a255419de12af748f72dd2192266578e8020","sha256:edc40808cb4c9941c2abeeb3a3b2b57d34e2407240599a629234b1dd5264465c"],"state_sha256":"97adb5539a0971a649994e57b9898a1c5246b35073a54e5a8950e26f976fc260"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M7tNAfG3tnQIiRxtJTQaTj+owkHq7IVdBNFtiqHdXELx3iIP1ja7YdRyPYK4GNXuI2I2tY/pL2hbXIO1TpaTDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T03:27:21.321654Z","bundle_sha256":"bf252a7092b4906a248def6f9985149b23f1ed85c94d381f1b92885981f4294d"}}