{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:6DKRFHICFFMRVLK5XUTVX7ZLYT","short_pith_number":"pith:6DKRFHIC","canonical_record":{"source":{"id":"2303.01000","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-02T06:33:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"db4dfebc47ec245495ada7cf8afd07516a66899f7167ebd8c3c71aa767f36108","abstract_canon_sha256":"ffbcc4365dde7ca7826ed37de283e70aeb367a6fae4c862de381a5026eb61835"},"schema_version":"1.0"},"canonical_sha256":"f0d5129d0229591aad5dbd275bff2bc4db46c2d9b5979523db82dd4928772f84","source":{"kind":"arxiv","id":"2303.01000","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.01000","created_at":"2026-07-05T05:47:25Z"},{"alias_kind":"arxiv_version","alias_value":"2303.01000v1","created_at":"2026-07-05T05:47:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.01000","created_at":"2026-07-05T05:47:25Z"},{"alias_kind":"pith_short_12","alias_value":"6DKRFHICFFMR","created_at":"2026-07-05T05:47:25Z"},{"alias_kind":"pith_short_16","alias_value":"6DKRFHICFFMRVLK5","created_at":"2026-07-05T05:47:25Z"},{"alias_kind":"pith_short_8","alias_value":"6DKRFHIC","created_at":"2026-07-05T05:47:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:6DKRFHICFFMRVLK5XUTVX7ZLYT","target":"record","payload":{"canonical_record":{"source":{"id":"2303.01000","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-02T06:33:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"db4dfebc47ec245495ada7cf8afd07516a66899f7167ebd8c3c71aa767f36108","abstract_canon_sha256":"ffbcc4365dde7ca7826ed37de283e70aeb367a6fae4c862de381a5026eb61835"},"schema_version":"1.0"},"canonical_sha256":"f0d5129d0229591aad5dbd275bff2bc4db46c2d9b5979523db82dd4928772f84","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:47:25.543966Z","signature_b64":"GuRyZQPdJySFI6Ys6KX1AlO15pbAqmiXSHIQhaO5XZZSE0B74NVUojNCkCT0kOUW8N61klRwOjlLeQ6cCy/4DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0d5129d0229591aad5dbd275bff2bc4db46c2d9b5979523db82dd4928772f84","last_reissued_at":"2026-07-05T05:47:25.543524Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:47:25.543524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.01000","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:47:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"35LzEGmzOZspMcdmWK5E9q/z6tgWWFx2h0Yfl3mU4dCO2XukiAT+dtpoR75XY0OB0vmP4BqjOWmp2MC4kvp0AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T17:40:55.990424Z"},"content_sha256":"b77cb5d2824f10e14478c1345c16b305705d392269863bbbe45a47ef4d6ee359","schema_version":"1.0","event_id":"sha256:b77cb5d2824f10e14478c1345c16b305705d392269863bbbe45a47ef4d6ee359"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:6DKRFHICFFMRVLK5XUTVX7ZLYT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"X&Fuse: Fusing Visual Information in Text-to-Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Adam Polyak, Omer Levy, Yuval Kirstain","submitted_at":"2023-03-02T06:33:33Z","abstract_excerpt":"We introduce X&Fuse, a general approach for conditioning on visual information when generating images from text. We demonstrate the potential of X&Fuse in three different text-to-image generation scenarios. (i) When a bank of images is available, we retrieve and condition on a related image (Retrieve&Fuse), resulting in significant improvements on the MS-COCO benchmark, gaining a state-of-the-art FID score of 6.65 in zero-shot settings. (ii) When cropped-object images are at hand, we utilize them and perform subject-driven generation (Crop&Fuse), outperforming the textual inversion method whil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.01000","kind":"arxiv","version":1},"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/2303.01000/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":"2026-07-05T05:47:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8k09hWAtWHsm0DyQK7/FYUJzVns6P9bQZmJYLChwJta4J90nee8mtnBaSr2NuK+qqh8E8XzAThsoQqrIrNE0Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T17:40:55.991042Z"},"content_sha256":"bb09cfef30e759b4e637593e5ff7b87feb498213bbf47e71e2a31d419a5e3197","schema_version":"1.0","event_id":"sha256:bb09cfef30e759b4e637593e5ff7b87feb498213bbf47e71e2a31d419a5e3197"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6DKRFHICFFMRVLK5XUTVX7ZLYT/bundle.json","state_url":"https://pith.science/pith/6DKRFHICFFMRVLK5XUTVX7ZLYT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6DKRFHICFFMRVLK5XUTVX7ZLYT/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":"2026-08-18T17:40:55Z","links":{"resolver":"https://pith.science/pith/6DKRFHICFFMRVLK5XUTVX7ZLYT","bundle":"https://pith.science/pith/6DKRFHICFFMRVLK5XUTVX7ZLYT/bundle.json","state":"https://pith.science/pith/6DKRFHICFFMRVLK5XUTVX7ZLYT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6DKRFHICFFMRVLK5XUTVX7ZLYT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6DKRFHICFFMRVLK5XUTVX7ZLYT","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":"ffbcc4365dde7ca7826ed37de283e70aeb367a6fae4c862de381a5026eb61835","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-02T06:33:33Z","title_canon_sha256":"db4dfebc47ec245495ada7cf8afd07516a66899f7167ebd8c3c71aa767f36108"},"schema_version":"1.0","source":{"id":"2303.01000","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.01000","created_at":"2026-07-05T05:47:25Z"},{"alias_kind":"arxiv_version","alias_value":"2303.01000v1","created_at":"2026-07-05T05:47:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.01000","created_at":"2026-07-05T05:47:25Z"},{"alias_kind":"pith_short_12","alias_value":"6DKRFHICFFMR","created_at":"2026-07-05T05:47:25Z"},{"alias_kind":"pith_short_16","alias_value":"6DKRFHICFFMRVLK5","created_at":"2026-07-05T05:47:25Z"},{"alias_kind":"pith_short_8","alias_value":"6DKRFHIC","created_at":"2026-07-05T05:47:25Z"}],"graph_snapshots":[{"event_id":"sha256:bb09cfef30e759b4e637593e5ff7b87feb498213bbf47e71e2a31d419a5e3197","target":"graph","created_at":"2026-07-05T05:47:25Z","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/2303.01000/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce X&Fuse, a general approach for conditioning on visual information when generating images from text. We demonstrate the potential of X&Fuse in three different text-to-image generation scenarios. (i) When a bank of images is available, we retrieve and condition on a related image (Retrieve&Fuse), resulting in significant improvements on the MS-COCO benchmark, gaining a state-of-the-art FID score of 6.65 in zero-shot settings. (ii) When cropped-object images are at hand, we utilize them and perform subject-driven generation (Crop&Fuse), outperforming the textual inversion method whil","authors_text":"Adam Polyak, Omer Levy, Yuval Kirstain","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-02T06:33:33Z","title":"X&Fuse: Fusing Visual Information in Text-to-Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.01000","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:b77cb5d2824f10e14478c1345c16b305705d392269863bbbe45a47ef4d6ee359","target":"record","created_at":"2026-07-05T05:47:25Z","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":"ffbcc4365dde7ca7826ed37de283e70aeb367a6fae4c862de381a5026eb61835","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-02T06:33:33Z","title_canon_sha256":"db4dfebc47ec245495ada7cf8afd07516a66899f7167ebd8c3c71aa767f36108"},"schema_version":"1.0","source":{"id":"2303.01000","kind":"arxiv","version":1}},"canonical_sha256":"f0d5129d0229591aad5dbd275bff2bc4db46c2d9b5979523db82dd4928772f84","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f0d5129d0229591aad5dbd275bff2bc4db46c2d9b5979523db82dd4928772f84","first_computed_at":"2026-07-05T05:47:25.543524Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:47:25.543524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GuRyZQPdJySFI6Ys6KX1AlO15pbAqmiXSHIQhaO5XZZSE0B74NVUojNCkCT0kOUW8N61klRwOjlLeQ6cCy/4DA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:47:25.543966Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.01000","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b77cb5d2824f10e14478c1345c16b305705d392269863bbbe45a47ef4d6ee359","sha256:bb09cfef30e759b4e637593e5ff7b87feb498213bbf47e71e2a31d419a5e3197"],"state_sha256":"757bd3c06fc8c52b3426ac0ab9b9c579971096642aa6250b52c69118b9da0a66"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kUfi8Yr30VDdVIgHwRaHpyImjOAZzCoQSH1wETTxTD7CiJI86mwJXLxjQkL00XQveXnA0jGKGXNSpHfTv0q+AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T17:40:56.000812Z","bundle_sha256":"17619bb7633e872d78e140d85cbc86b8e2a4a0b2126eb9beb3a04bc74bea0116"}}