{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:42OGERYIADRK2RGSUOBQXDOZOB","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":"7bc8f2a6ab07e740b45f6dadd1e40e48db78dfe34057af6fd589e7681f35d36b","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-11T05:14:35Z","title_canon_sha256":"dae0f59bcd5b5a3ede47c8154dce499b5f4391e803e6d3292e6e5d473bf6498b"},"schema_version":"1.0","source":{"id":"2006.06195","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.06195","created_at":"2026-07-05T01:45:27Z"},{"alias_kind":"arxiv_version","alias_value":"2006.06195v2","created_at":"2026-07-05T01:45:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.06195","created_at":"2026-07-05T01:45:27Z"},{"alias_kind":"pith_short_12","alias_value":"42OGERYIADRK","created_at":"2026-07-05T01:45:27Z"},{"alias_kind":"pith_short_16","alias_value":"42OGERYIADRK2RGS","created_at":"2026-07-05T01:45:27Z"},{"alias_kind":"pith_short_8","alias_value":"42OGERYI","created_at":"2026-07-05T01:45:27Z"}],"graph_snapshots":[{"event_id":"sha256:d9764ac5be410aba26fdbcfb3704a71eabdad02f501661da9521c527ef414d8f","target":"graph","created_at":"2026-07-05T01:45:27Z","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/2006.06195/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present VILLA, the first known effort on large-scale adversarial training for vision-and-language (V+L) representation learning. VILLA consists of two training stages: (i) task-agnostic adversarial pre-training; followed by (ii) task-specific adversarial finetuning. Instead of adding adversarial perturbations on image pixels and textual tokens, we propose to perform adversarial training in the embedding space of each modality. To enable large-scale training, we adopt the \"free\" adversarial training strategy, and combine it with KL-divergence-based regularization to promote higher invariance","authors_text":"Chen Zhu, Jingjing Liu, Linjie Li, Yen-Chun Chen, Yu Cheng, Zhe Gan","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-11T05:14:35Z","title":"Large-Scale Adversarial Training for Vision-and-Language Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.06195","kind":"arxiv","version":2},"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":"sha256:03aa3825cf1e32d50121382f40d1f8d27648e793ef69f766d4d478f349b7f273","target":"record","created_at":"2026-07-05T01:45:27Z","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":"7bc8f2a6ab07e740b45f6dadd1e40e48db78dfe34057af6fd589e7681f35d36b","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-11T05:14:35Z","title_canon_sha256":"dae0f59bcd5b5a3ede47c8154dce499b5f4391e803e6d3292e6e5d473bf6498b"},"schema_version":"1.0","source":{"id":"2006.06195","kind":"arxiv","version":2}},"canonical_sha256":"e69c62470800e2ad44d2a3830b8dd97057b856f633579bfa2b033320b6d2a080","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e69c62470800e2ad44d2a3830b8dd97057b856f633579bfa2b033320b6d2a080","first_computed_at":"2026-07-05T01:45:27.519232Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:45:27.519232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yn0zoBYF1aWoXeYr1kck7MgZYQvbqZI/dZ10P33Qs6FiNcTqCkvCUzzyzwMcsi5P1ae/IkpGLBh3eFxaFz6iCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:45:27.519896Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.06195","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03aa3825cf1e32d50121382f40d1f8d27648e793ef69f766d4d478f349b7f273","sha256:d9764ac5be410aba26fdbcfb3704a71eabdad02f501661da9521c527ef414d8f"],"state_sha256":"fc2adb723f81d77bb94aa786719750819348b73b18fd2f457c00cda2b230d56d"}