{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:LUFL67K4F6BJF5CWL4NYCJ2NAY","short_pith_number":"pith:LUFL67K4","canonical_record":{"source":{"id":"2109.12178","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-24T20:25:40Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0e5e44711c152324c5e0c30d19760d6a05ff6f2f0b5c3a38909cac95ee3b5861","abstract_canon_sha256":"55ebc9e96bd25080c315a685189bd9eba3bfaf0a4019845bed56682b26289d21"},"schema_version":"1.0"},"canonical_sha256":"5d0abf7d5c2f8292f4565f1b81274d060a08df844efa79fce0bc5f14e2971c53","source":{"kind":"arxiv","id":"2109.12178","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.12178","created_at":"2026-07-05T03:17:17Z"},{"alias_kind":"arxiv_version","alias_value":"2109.12178v1","created_at":"2026-07-05T03:17:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.12178","created_at":"2026-07-05T03:17:17Z"},{"alias_kind":"pith_short_12","alias_value":"LUFL67K4F6BJ","created_at":"2026-07-05T03:17:17Z"},{"alias_kind":"pith_short_16","alias_value":"LUFL67K4F6BJF5CW","created_at":"2026-07-05T03:17:17Z"},{"alias_kind":"pith_short_8","alias_value":"LUFL67K4","created_at":"2026-07-05T03:17:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:LUFL67K4F6BJF5CWL4NYCJ2NAY","target":"record","payload":{"canonical_record":{"source":{"id":"2109.12178","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-24T20:25:40Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0e5e44711c152324c5e0c30d19760d6a05ff6f2f0b5c3a38909cac95ee3b5861","abstract_canon_sha256":"55ebc9e96bd25080c315a685189bd9eba3bfaf0a4019845bed56682b26289d21"},"schema_version":"1.0"},"canonical_sha256":"5d0abf7d5c2f8292f4565f1b81274d060a08df844efa79fce0bc5f14e2971c53","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:17:17.387146Z","signature_b64":"PdCuUvDyo1XAcVMUwUuA5LhtO8ykdoKb/WvWcxs7znROilJvAG1vdyLX4XIBhKBRT+PisGj50y83yDC5DFOYDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d0abf7d5c2f8292f4565f1b81274d060a08df844efa79fce0bc5f14e2971c53","last_reissued_at":"2026-07-05T03:17:17.386632Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:17:17.386632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.12178","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":"2026-07-05T03:17:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t0d9Ta4s2+fulvr0WIynCgW/vTDEN3JXuV4l09JAEVGzzDmbiYY4lQ1NGB7z8bk/ToV3ZvpB/EOwBme9p/5HAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:16:39.040347Z"},"content_sha256":"8bb954d298b2ec6d4b6541d0d2a3be0e01d8da4a1130092d9e1372417507c312","schema_version":"1.0","event_id":"sha256:8bb954d298b2ec6d4b6541d0d2a3be0e01d8da4a1130092d9e1372417507c312"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:LUFL67K4F6BJF5CWL4NYCJ2NAY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MLIM: Vision-and-Language Model Pre-training with Masked Language and Image Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Belinda Zeng, Ismail Tutar, Mehmet Saygin Seyfioglu, Son Train, Tal Neiman, Tarik Arici, Trishul Chilimbi, Yi Xu","submitted_at":"2021-09-24T20:25:40Z","abstract_excerpt":"Vision-and-Language Pre-training (VLP) improves model performance for downstream tasks that require image and text inputs. Current VLP approaches differ on (i) model architecture (especially image embedders), (ii) loss functions, and (iii) masking policies. Image embedders are either deep models like ResNet or linear projections that directly feed image-pixels into the transformer. Typically, in addition to the Masked Language Modeling (MLM) loss, alignment-based objectives are used for cross-modality interaction, and RoI feature regression and classification tasks for Masked Image-Region Mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.12178","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/2109.12178/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":"2026-07-05T03:17:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tk0AKBeszenR3Loeych1+wOV3rsxCX7byC0ICC3ZdedMIMC74ODmWk6vcIEG8xKJnAyke0DEpnVu+/HYNPBdBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:16:39.040813Z"},"content_sha256":"4e6a7fddf4d8f98c60c6170c01416af61c3bfec2944ade1fee7aa4c5d7f97199","schema_version":"1.0","event_id":"sha256:4e6a7fddf4d8f98c60c6170c01416af61c3bfec2944ade1fee7aa4c5d7f97199"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LUFL67K4F6BJF5CWL4NYCJ2NAY/bundle.json","state_url":"https://pith.science/pith/LUFL67K4F6BJF5CWL4NYCJ2NAY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LUFL67K4F6BJF5CWL4NYCJ2NAY/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":"2026-07-07T05:16:39Z","links":{"resolver":"https://pith.science/pith/LUFL67K4F6BJF5CWL4NYCJ2NAY","bundle":"https://pith.science/pith/LUFL67K4F6BJF5CWL4NYCJ2NAY/bundle.json","state":"https://pith.science/pith/LUFL67K4F6BJF5CWL4NYCJ2NAY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LUFL67K4F6BJF5CWL4NYCJ2NAY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:LUFL67K4F6BJF5CWL4NYCJ2NAY","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":"55ebc9e96bd25080c315a685189bd9eba3bfaf0a4019845bed56682b26289d21","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-24T20:25:40Z","title_canon_sha256":"0e5e44711c152324c5e0c30d19760d6a05ff6f2f0b5c3a38909cac95ee3b5861"},"schema_version":"1.0","source":{"id":"2109.12178","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.12178","created_at":"2026-07-05T03:17:17Z"},{"alias_kind":"arxiv_version","alias_value":"2109.12178v1","created_at":"2026-07-05T03:17:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.12178","created_at":"2026-07-05T03:17:17Z"},{"alias_kind":"pith_short_12","alias_value":"LUFL67K4F6BJ","created_at":"2026-07-05T03:17:17Z"},{"alias_kind":"pith_short_16","alias_value":"LUFL67K4F6BJF5CW","created_at":"2026-07-05T03:17:17Z"},{"alias_kind":"pith_short_8","alias_value":"LUFL67K4","created_at":"2026-07-05T03:17:17Z"}],"graph_snapshots":[{"event_id":"sha256:4e6a7fddf4d8f98c60c6170c01416af61c3bfec2944ade1fee7aa4c5d7f97199","target":"graph","created_at":"2026-07-05T03:17:17Z","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/2109.12178/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-and-Language Pre-training (VLP) improves model performance for downstream tasks that require image and text inputs. Current VLP approaches differ on (i) model architecture (especially image embedders), (ii) loss functions, and (iii) masking policies. Image embedders are either deep models like ResNet or linear projections that directly feed image-pixels into the transformer. Typically, in addition to the Masked Language Modeling (MLM) loss, alignment-based objectives are used for cross-modality interaction, and RoI feature regression and classification tasks for Masked Image-Region Mode","authors_text":"Belinda Zeng, Ismail Tutar, Mehmet Saygin Seyfioglu, Son Train, Tal Neiman, Tarik Arici, Trishul Chilimbi, Yi Xu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-24T20:25:40Z","title":"MLIM: Vision-and-Language Model Pre-training with Masked Language and Image Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.12178","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":"sha256:8bb954d298b2ec6d4b6541d0d2a3be0e01d8da4a1130092d9e1372417507c312","target":"record","created_at":"2026-07-05T03:17:17Z","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":"55ebc9e96bd25080c315a685189bd9eba3bfaf0a4019845bed56682b26289d21","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-24T20:25:40Z","title_canon_sha256":"0e5e44711c152324c5e0c30d19760d6a05ff6f2f0b5c3a38909cac95ee3b5861"},"schema_version":"1.0","source":{"id":"2109.12178","kind":"arxiv","version":1}},"canonical_sha256":"5d0abf7d5c2f8292f4565f1b81274d060a08df844efa79fce0bc5f14e2971c53","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5d0abf7d5c2f8292f4565f1b81274d060a08df844efa79fce0bc5f14e2971c53","first_computed_at":"2026-07-05T03:17:17.386632Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:17:17.386632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PdCuUvDyo1XAcVMUwUuA5LhtO8ykdoKb/WvWcxs7znROilJvAG1vdyLX4XIBhKBRT+PisGj50y83yDC5DFOYDw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:17:17.387146Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.12178","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8bb954d298b2ec6d4b6541d0d2a3be0e01d8da4a1130092d9e1372417507c312","sha256:4e6a7fddf4d8f98c60c6170c01416af61c3bfec2944ade1fee7aa4c5d7f97199"],"state_sha256":"7cec15eaaf65e6fc15363a9e87a819043794a1a5843f49e47844bf09ddb49ac0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Px7JF9Xylq1jWDQ+DLnt4optqs7X7NuX3QseTfDwruGYCACs63hSD3fPsdvM8aSMSAJbBz3FupUAN5pTA5KqBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T05:16:39.044039Z","bundle_sha256":"0eb0705507491eee64c3c94efd0eac4c87ada012676cb6aad869812fbd3b8b20"}}