{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FKOYVUCJYSOQOULXYZPSRECYBM","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":"b9ae54f1c09482395ea6334fbd209991057ab6b33e1082564e5978a10c91ecdc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-03T05:07:49Z","title_canon_sha256":"5842bae0a4212874937a524f108e19ce15d5fd783f21f8dec03fb63f4cfb8a0d"},"schema_version":"1.0","source":{"id":"2304.00719","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.00719","created_at":"2026-07-05T05:57:21Z"},{"alias_kind":"arxiv_version","alias_value":"2304.00719v1","created_at":"2026-07-05T05:57:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.00719","created_at":"2026-07-05T05:57:21Z"},{"alias_kind":"pith_short_12","alias_value":"FKOYVUCJYSOQ","created_at":"2026-07-05T05:57:21Z"},{"alias_kind":"pith_short_16","alias_value":"FKOYVUCJYSOQOULX","created_at":"2026-07-05T05:57:21Z"},{"alias_kind":"pith_short_8","alias_value":"FKOYVUCJ","created_at":"2026-07-05T05:57:21Z"}],"graph_snapshots":[{"event_id":"sha256:7cce311913ac4eb7fb43bf1705d9b35aa01fa77091c4ffc1d75b6ff379b66b41","target":"graph","created_at":"2026-07-05T05:57:21Z","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/2304.00719/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a visual-linguistic representation learning approach within a self-supervised learning framework by introducing a new operation, loss, and data augmentation strategy. First, we generate diverse features for the image-text matching (ITM) task via soft-masking the regions in an image, which are most relevant to a certain word in the corresponding caption, instead of completely removing them. Since our framework relies only on image-caption pairs with no fine-grained annotations, we identify the relevant regions to each word by computing the word-conditional visual attention using mult","authors_text":"Bohyung Han, Jaeyoo Park","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-03T05:07:49Z","title":"Multi-Modal Representation Learning with Text-Driven Soft Masks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.00719","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":"sha256:7021a93de36a81fed48d92cfc4c85db7c153d79f793f0a357062035bf2e5759d","target":"record","created_at":"2026-07-05T05:57:21Z","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":"b9ae54f1c09482395ea6334fbd209991057ab6b33e1082564e5978a10c91ecdc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-03T05:07:49Z","title_canon_sha256":"5842bae0a4212874937a524f108e19ce15d5fd783f21f8dec03fb63f4cfb8a0d"},"schema_version":"1.0","source":{"id":"2304.00719","kind":"arxiv","version":1}},"canonical_sha256":"2a9d8ad049c49d075177c65f2890580b24832cda132fb048a0ed634ac3cb050f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a9d8ad049c49d075177c65f2890580b24832cda132fb048a0ed634ac3cb050f","first_computed_at":"2026-07-05T05:57:21.376042Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:57:21.376042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ko6FPAQLKQX8BDcAKdttcPZ06TW3CaJkW7bpsFlG9r5ivk9JyBlfMTDji6rN2+MQxdfkhqHMWCvtWdFqCaWXCg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:57:21.376565Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.00719","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7021a93de36a81fed48d92cfc4c85db7c153d79f793f0a357062035bf2e5759d","sha256:7cce311913ac4eb7fb43bf1705d9b35aa01fa77091c4ffc1d75b6ff379b66b41"],"state_sha256":"45cb9158df1fc2222ac725a1f2c23ef185db068091be6b74f90edc3a7987f2dc"}