{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:RWEYYSO4YR7RLIPDV7GXGBHMPJ","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":"0b1f1f96d6e46c43faead283a7e7b061e84b3e8f63c819b1dbce1b02b9737a1e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-08-14T22:48:36Z","title_canon_sha256":"35283d4786aeb5e0fdc57fb47d71773adf82d2c6d57b6625e2e846da2deeb161"},"schema_version":"1.0","source":{"id":"2008.06597","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.06597","created_at":"2026-07-05T01:27:30Z"},{"alias_kind":"arxiv_version","alias_value":"2008.06597v1","created_at":"2026-07-05T01:27:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.06597","created_at":"2026-07-05T01:27:30Z"},{"alias_kind":"pith_short_12","alias_value":"RWEYYSO4YR7R","created_at":"2026-07-05T01:27:30Z"},{"alias_kind":"pith_short_16","alias_value":"RWEYYSO4YR7RLIPD","created_at":"2026-07-05T01:27:30Z"},{"alias_kind":"pith_short_8","alias_value":"RWEYYSO4","created_at":"2026-07-05T01:27:30Z"}],"graph_snapshots":[{"event_id":"sha256:71f420c5b34c5a7c373cd6a40281c87431a34b8c96aa3ec7b8660521ad9e0013","target":"graph","created_at":"2026-07-05T01:27:30Z","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/2008.06597/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cross-domain alignment between image objects and text sequences is key to many visual-language tasks, and it poses a fundamental challenge to both computer vision and natural language processing. This paper investigates a novel approach for the identification and optimization of fine-grained semantic similarities between image and text entities, under a weakly-supervised setup, improving performance over state-of-the-art solutions. Our method builds upon recent advances in optimal transport (OT) to resolve the cross-domain matching problem in a principled manner. Formulated as a drop-in regula","authors_text":"Chenyang Tao, Chunyuan Li, Guoyin Wang, Ke Bai, Lawrence Carin, Liqun Chen, Ricardo Henao, Siyang Yuan, Yizhe Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-08-14T22:48:36Z","title":"Weakly supervised cross-domain alignment with optimal transport"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.06597","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":"sha256:18dc03ff704e4cb5920f27e4813eba1012d464df54a0227fecfca8c5df694dd9","target":"record","created_at":"2026-07-05T01:27:30Z","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":"0b1f1f96d6e46c43faead283a7e7b061e84b3e8f63c819b1dbce1b02b9737a1e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-08-14T22:48:36Z","title_canon_sha256":"35283d4786aeb5e0fdc57fb47d71773adf82d2c6d57b6625e2e846da2deeb161"},"schema_version":"1.0","source":{"id":"2008.06597","kind":"arxiv","version":1}},"canonical_sha256":"8d898c49dcc47f15a1e3afcd7304ec7a4967c0636c951b74857d832d99238453","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d898c49dcc47f15a1e3afcd7304ec7a4967c0636c951b74857d832d99238453","first_computed_at":"2026-07-05T01:27:30.085558Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:27:30.085558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DsFrfk7Rf5slr3W+3cey1uMShe8Km8j4oDMGdwfuQZ4hJfGPI9NkQDBABHImUxrcyauppH1CqsPYOHv0kjyzAw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:27:30.086008Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.06597","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:18dc03ff704e4cb5920f27e4813eba1012d464df54a0227fecfca8c5df694dd9","sha256:71f420c5b34c5a7c373cd6a40281c87431a34b8c96aa3ec7b8660521ad9e0013"],"state_sha256":"311f6c2ecbe89f53a7d0f4bfffd40deca096ec97564bf142c1f22bea72af2f83"}