{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:FBQ6YNIEF6IWAJVVY5GNUXAM6C","short_pith_number":"pith:FBQ6YNIE","canonical_record":{"source":{"id":"2101.04702","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-12T19:16:51Z","cross_cats_sorted":[],"title_canon_sha256":"eb28c0ed9d6003bb4fe5e689a10ae6fdd3f7b385906053fa33950508b53be8d2","abstract_canon_sha256":"e30ce8bb8797516d62a17732c1a6d014e76f9719787c7b6902eeddbfb7d5db4a"},"schema_version":"1.0"},"canonical_sha256":"2861ec35042f916026b5c74cda5c0cf0aa2bcf785cca04a115dc55bd311446c5","source":{"kind":"arxiv","id":"2101.04702","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:FBQ6YNIEF6IWAJVVY5GNUXAM6C","target":"record","payload":{"canonical_record":{"source":{"id":"2101.04702","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-12T19:16:51Z","cross_cats_sorted":[],"title_canon_sha256":"eb28c0ed9d6003bb4fe5e689a10ae6fdd3f7b385906053fa33950508b53be8d2","abstract_canon_sha256":"e30ce8bb8797516d62a17732c1a6d014e76f9719787c7b6902eeddbfb7d5db4a"},"schema_version":"1.0"},"canonical_sha256":"2861ec35042f916026b5c74cda5c0cf0aa2bcf785cca04a115dc55bd311446c5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:14:36.532745Z","signature_b64":"tP3/TTPLq0NpiIpiBezLkWSfvRVB0SJ+Nh2y3cqASA/fOJo6IwlNGSBUML6AvA6XTHlpXJfHSDpUNzE1S1J+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2861ec35042f916026b5c74cda5c0cf0aa2bcf785cca04a115dc55bd311446c5","last_reissued_at":"2026-07-05T04:14:36.532263Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:14:36.532263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2101.04702","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:14:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T7cNF/HSYvQomYNfC+g9r5OIsSbXi9QKgxORcdZYXeUFtFVGO1g4fAJ6Vejn30ORmw5YucCRBHhvOW0c44J0BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T19:55:05.814464Z"},"content_sha256":"6cb959b9c4e0efcd6e0747a90d932cb818d5705c098d542825a3cb80000936f9","schema_version":"1.0","event_id":"sha256:6cb959b9c4e0efcd6e0747a90d932cb818d5705c098d542825a3cb80000936f9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:FBQ6YNIEF6IWAJVVY5GNUXAM6C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cross-Modal Contrastive Learning for Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Han Zhang, Honglak Lee, Jason Baldridge, Jing Yu Koh, Yinfei Yang","submitted_at":"2021-01-12T19:16:51Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.04702","kind":"arxiv","version":5},"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/2101.04702/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":"2026-07-05T04:14:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tzmc4SIK8JTD+FPrwEtYyo1reE5WaJoeY0PwdgGWkk8pkK/CNRcxnfNKh6Q5LADqCuu2/UQkY9RyoXQtKduODg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T19:55:05.814975Z"},"content_sha256":"46938a6d962d372f297889e97ace57c7e796f7e611b942c8187c3a12ee5e03a5","schema_version":"1.0","event_id":"sha256:46938a6d962d372f297889e97ace57c7e796f7e611b942c8187c3a12ee5e03a5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FBQ6YNIEF6IWAJVVY5GNUXAM6C/bundle.json","state_url":"https://pith.science/pith/FBQ6YNIEF6IWAJVVY5GNUXAM6C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FBQ6YNIEF6IWAJVVY5GNUXAM6C/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":"2026-08-15T19:55:05Z","links":{"resolver":"https://pith.science/pith/FBQ6YNIEF6IWAJVVY5GNUXAM6C","bundle":"https://pith.science/pith/FBQ6YNIEF6IWAJVVY5GNUXAM6C/bundle.json","state":"https://pith.science/pith/FBQ6YNIEF6IWAJVVY5GNUXAM6C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FBQ6YNIEF6IWAJVVY5GNUXAM6C/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aj5Z5t2zd3CDRrtes1vSMZ4uWwpZSY6aaPEEQS7DrSk6CrfDRw8mvIAboQj3H2h93yRUl9ivxB3Q6VqTTtVlAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T19:55:05.818398Z","bundle_sha256":"b7266f3361a886a0f9e51f9fd8c46b2e6840a8905866dd11a7310caa7c611492"}}