{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FBQ6YNIEF6IWAJVVY5GNUXAM6C","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":"e30ce8bb8797516d62a17732c1a6d014e76f9719787c7b6902eeddbfb7d5db4a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-12T19:16:51Z","title_canon_sha256":"eb28c0ed9d6003bb4fe5e689a10ae6fdd3f7b385906053fa33950508b53be8d2"},"schema_version":"1.0","source":{"id":"2101.04702","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.04702","created_at":"2026-07-05T04:14:36Z"},{"alias_kind":"arxiv_version","alias_value":"2101.04702v5","created_at":"2026-07-05T04:14:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.04702","created_at":"2026-07-05T04:14:36Z"},{"alias_kind":"pith_short_12","alias_value":"FBQ6YNIEF6IW","created_at":"2026-07-05T04:14:36Z"},{"alias_kind":"pith_short_16","alias_value":"FBQ6YNIEF6IWAJVV","created_at":"2026-07-05T04:14:36Z"},{"alias_kind":"pith_short_8","alias_value":"FBQ6YNIE","created_at":"2026-07-05T04:14:36Z"}],"graph_snapshots":[{"event_id":"sha256:46938a6d962d372f297889e97ace57c7e796f7e611b942c8187c3a12ee5e03a5","target":"graph","created_at":"2026-07-05T04:14:36Z","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/2101.04702/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The output of text-to-image synthesis systems should be coherent, clear, photo-realistic scenes with high semantic fidelity to their conditioned text descriptions. Our Cross-Modal Contrastive Generative Adversarial Network (XMC-GAN) addresses this challenge by maximizing the mutual information between image and text. It does this via multiple contrastive losses which capture inter-modality and intra-modality correspondences. XMC-GAN uses an attentional self-modulation generator, which enforces strong text-image correspondence, and a contrastive discriminator, which acts as a critic as well as ","authors_text":"Han Zhang, Honglak Lee, Jason Baldridge, Jing Yu Koh, Yinfei Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-12T19:16:51Z","title":"Cross-Modal Contrastive Learning for Text-to-Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.04702","kind":"arxiv","version":5},"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":"sha256:6cb959b9c4e0efcd6e0747a90d932cb818d5705c098d542825a3cb80000936f9","target":"record","created_at":"2026-07-05T04:14:36Z","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":"e30ce8bb8797516d62a17732c1a6d014e76f9719787c7b6902eeddbfb7d5db4a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-12T19:16:51Z","title_canon_sha256":"eb28c0ed9d6003bb4fe5e689a10ae6fdd3f7b385906053fa33950508b53be8d2"},"schema_version":"1.0","source":{"id":"2101.04702","kind":"arxiv","version":5}},"canonical_sha256":"2861ec35042f916026b5c74cda5c0cf0aa2bcf785cca04a115dc55bd311446c5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2861ec35042f916026b5c74cda5c0cf0aa2bcf785cca04a115dc55bd311446c5","first_computed_at":"2026-07-05T04:14:36.532263Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:14:36.532263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tP3/TTPLq0NpiIpiBezLkWSfvRVB0SJ+Nh2y3cqASA/fOJo6IwlNGSBUML6AvA6XTHlpXJfHSDpUNzE1S1J+Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:14:36.532745Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.04702","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6cb959b9c4e0efcd6e0747a90d932cb818d5705c098d542825a3cb80000936f9","sha256:46938a6d962d372f297889e97ace57c7e796f7e611b942c8187c3a12ee5e03a5"],"state_sha256":"1a127664dde008ead1dcda4089064a052c663b17075d5c46f21422c3eff58808"}