{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KQA7E2YLSLQAC2XNABWV3ZEAQZ","short_pith_number":"pith:KQA7E2YL","canonical_record":{"source":{"id":"2403.00249","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-01T03:25:58Z","cross_cats_sorted":[],"title_canon_sha256":"26f71e1588fa4a283793245d8cd6f729f370cd3cadb32f0fb64b39bf737fd34d","abstract_canon_sha256":"b3f25440898f8e0efc305d196af61b2273d0cbeccab4fc2c8986227f7dedf843"},"schema_version":"1.0"},"canonical_sha256":"5401f26b0b92e0016aed006d5de4808673e83e906a48b5b8f8e72810b0c145ac","source":{"kind":"arxiv","id":"2403.00249","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.00249","created_at":"2026-07-05T07:51:01Z"},{"alias_kind":"arxiv_version","alias_value":"2403.00249v1","created_at":"2026-07-05T07:51:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00249","created_at":"2026-07-05T07:51:01Z"},{"alias_kind":"pith_short_12","alias_value":"KQA7E2YLSLQA","created_at":"2026-07-05T07:51:01Z"},{"alias_kind":"pith_short_16","alias_value":"KQA7E2YLSLQAC2XN","created_at":"2026-07-05T07:51:01Z"},{"alias_kind":"pith_short_8","alias_value":"KQA7E2YL","created_at":"2026-07-05T07:51:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KQA7E2YLSLQAC2XNABWV3ZEAQZ","target":"record","payload":{"canonical_record":{"source":{"id":"2403.00249","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-01T03:25:58Z","cross_cats_sorted":[],"title_canon_sha256":"26f71e1588fa4a283793245d8cd6f729f370cd3cadb32f0fb64b39bf737fd34d","abstract_canon_sha256":"b3f25440898f8e0efc305d196af61b2273d0cbeccab4fc2c8986227f7dedf843"},"schema_version":"1.0"},"canonical_sha256":"5401f26b0b92e0016aed006d5de4808673e83e906a48b5b8f8e72810b0c145ac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:01.305074Z","signature_b64":"2tzPH3DA9dJ25EyHy98riuAJOGMAGukBcilUZSkMd7EOrkN8QlA8QKR2At3ZNqNCYzFyadIR0/0vOcLDWBDtAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5401f26b0b92e0016aed006d5de4808673e83e906a48b5b8f8e72810b0c145ac","last_reissued_at":"2026-07-05T07:51:01.304464Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:01.304464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.00249","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":"2026-07-05T07:51:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ExsjAb1jlxK0OKnM5ux7IhO5iNxShMU3RE3O8Wqxcmusi7onzfJCNBmAT4CSaI79gpX8YRD0EYmnuBBoKS5QAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:51:06.129916Z"},"content_sha256":"a74f4f42876577b1ea7357faafe68cc608a8afcfe7922d78069937e041ca2c61","schema_version":"1.0","event_id":"sha256:a74f4f42876577b1ea7357faafe68cc608a8afcfe7922d78069937e041ca2c61"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KQA7E2YLSLQAC2XNABWV3ZEAQZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semantics-enhanced Cross-modal Masked Image Modeling for Vision-Language Pre-training","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Li, Chenliang Li, Chunfeng Yuan, Fei Huang, Haiyang Xu, Haowei Liu, Ji Zhang, Ming Yan, Qinghao Ye, Weiming Hu, Yaya Shi","submitted_at":"2024-03-01T03:25:58Z","abstract_excerpt":"In vision-language pre-training (VLP), masked image modeling (MIM) has recently been introduced for fine-grained cross-modal alignment. However, in most existing methods, the reconstruction targets for MIM lack high-level semantics, and text is not sufficiently involved in masked modeling. These two drawbacks limit the effect of MIM in facilitating cross-modal semantic alignment. In this work, we propose a semantics-enhanced cross-modal MIM framework (SemMIM) for vision-language representation learning. Specifically, to provide more semantically meaningful supervision for MIM, we propose a loc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00249","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/2403.00249/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":"2026-07-05T07:51:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Cy8CJglyDWXa2njWuRj8qoc15r8/Mv01u+M8mbHz8zDwTrauVI5zqwcwyAvEDnltbDc3+g1SOoxPlADhS9MfDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:51:06.130877Z"},"content_sha256":"2c1ab0bc9fe64191b56ff3d946f07db6bf1ec797b958d83ea75807cacab1305f","schema_version":"1.0","event_id":"sha256:2c1ab0bc9fe64191b56ff3d946f07db6bf1ec797b958d83ea75807cacab1305f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KQA7E2YLSLQAC2XNABWV3ZEAQZ/bundle.json","state_url":"https://pith.science/pith/KQA7E2YLSLQAC2XNABWV3ZEAQZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KQA7E2YLSLQAC2XNABWV3ZEAQZ/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":"2026-08-03T18:51:06Z","links":{"resolver":"https://pith.science/pith/KQA7E2YLSLQAC2XNABWV3ZEAQZ","bundle":"https://pith.science/pith/KQA7E2YLSLQAC2XNABWV3ZEAQZ/bundle.json","state":"https://pith.science/pith/KQA7E2YLSLQAC2XNABWV3ZEAQZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KQA7E2YLSLQAC2XNABWV3ZEAQZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KQA7E2YLSLQAC2XNABWV3ZEAQZ","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":"b3f25440898f8e0efc305d196af61b2273d0cbeccab4fc2c8986227f7dedf843","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-01T03:25:58Z","title_canon_sha256":"26f71e1588fa4a283793245d8cd6f729f370cd3cadb32f0fb64b39bf737fd34d"},"schema_version":"1.0","source":{"id":"2403.00249","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.00249","created_at":"2026-07-05T07:51:01Z"},{"alias_kind":"arxiv_version","alias_value":"2403.00249v1","created_at":"2026-07-05T07:51:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00249","created_at":"2026-07-05T07:51:01Z"},{"alias_kind":"pith_short_12","alias_value":"KQA7E2YLSLQA","created_at":"2026-07-05T07:51:01Z"},{"alias_kind":"pith_short_16","alias_value":"KQA7E2YLSLQAC2XN","created_at":"2026-07-05T07:51:01Z"},{"alias_kind":"pith_short_8","alias_value":"KQA7E2YL","created_at":"2026-07-05T07:51:01Z"}],"graph_snapshots":[{"event_id":"sha256:2c1ab0bc9fe64191b56ff3d946f07db6bf1ec797b958d83ea75807cacab1305f","target":"graph","created_at":"2026-07-05T07:51:01Z","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/2403.00249/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In vision-language pre-training (VLP), masked image modeling (MIM) has recently been introduced for fine-grained cross-modal alignment. However, in most existing methods, the reconstruction targets for MIM lack high-level semantics, and text is not sufficiently involved in masked modeling. These two drawbacks limit the effect of MIM in facilitating cross-modal semantic alignment. In this work, we propose a semantics-enhanced cross-modal MIM framework (SemMIM) for vision-language representation learning. Specifically, to provide more semantically meaningful supervision for MIM, we propose a loc","authors_text":"Bing Li, Chenliang Li, Chunfeng Yuan, Fei Huang, Haiyang Xu, Haowei Liu, Ji Zhang, Ming Yan, Qinghao Ye, Weiming Hu, Yaya Shi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-01T03:25:58Z","title":"Semantics-enhanced Cross-modal Masked Image Modeling for Vision-Language Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00249","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:a74f4f42876577b1ea7357faafe68cc608a8afcfe7922d78069937e041ca2c61","target":"record","created_at":"2026-07-05T07:51:01Z","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":"b3f25440898f8e0efc305d196af61b2273d0cbeccab4fc2c8986227f7dedf843","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-01T03:25:58Z","title_canon_sha256":"26f71e1588fa4a283793245d8cd6f729f370cd3cadb32f0fb64b39bf737fd34d"},"schema_version":"1.0","source":{"id":"2403.00249","kind":"arxiv","version":1}},"canonical_sha256":"5401f26b0b92e0016aed006d5de4808673e83e906a48b5b8f8e72810b0c145ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5401f26b0b92e0016aed006d5de4808673e83e906a48b5b8f8e72810b0c145ac","first_computed_at":"2026-07-05T07:51:01.304464Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:51:01.304464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2tzPH3DA9dJ25EyHy98riuAJOGMAGukBcilUZSkMd7EOrkN8QlA8QKR2At3ZNqNCYzFyadIR0/0vOcLDWBDtAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:51:01.305074Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.00249","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a74f4f42876577b1ea7357faafe68cc608a8afcfe7922d78069937e041ca2c61","sha256:2c1ab0bc9fe64191b56ff3d946f07db6bf1ec797b958d83ea75807cacab1305f"],"state_sha256":"a7eab1039ab2083b3d73012a3bf9128049db83d941487cdc6a1427825881cd20"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Dc/PLKB9u+dNOhbMRnhFRFUqhGTkInxr5I4L5l484uCcq3KIQ0bfN10srAyziAcLk3jV4ihFXhlqFJixr8qnCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T18:51:06.158902Z","bundle_sha256":"c6f9edb8a692ef8a3478740288eaffa105b270d79c922d92ff73e67801d5fe6d"}}