{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:3FPFRXEMULCUQJG4H2JB2X2BAQ","short_pith_number":"pith:3FPFRXEM","canonical_record":{"source":{"id":"2105.14211","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-29T04:42:07Z","cross_cats_sorted":[],"title_canon_sha256":"26424a5d588b3e85a685ff84152cb7a512833319b80737b1cb66af64418fab62","abstract_canon_sha256":"e8019c78bc1746180f8bc42b7d955349e589cab20602a36f0eee8f11157edbb6"},"schema_version":"1.0"},"canonical_sha256":"d95e58dc8ca2c54824dc3e921d5f410428df2787747500e97c2b2bc98e020bd6","source":{"kind":"arxiv","id":"2105.14211","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.14211","created_at":"2026-07-05T03:58:16Z"},{"alias_kind":"arxiv_version","alias_value":"2105.14211v4","created_at":"2026-07-05T03:58:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.14211","created_at":"2026-07-05T03:58:16Z"},{"alias_kind":"pith_short_12","alias_value":"3FPFRXEMULCU","created_at":"2026-07-05T03:58:16Z"},{"alias_kind":"pith_short_16","alias_value":"3FPFRXEMULCUQJG4","created_at":"2026-07-05T03:58:16Z"},{"alias_kind":"pith_short_8","alias_value":"3FPFRXEM","created_at":"2026-07-05T03:58:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:3FPFRXEMULCUQJG4H2JB2X2BAQ","target":"record","payload":{"canonical_record":{"source":{"id":"2105.14211","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-29T04:42:07Z","cross_cats_sorted":[],"title_canon_sha256":"26424a5d588b3e85a685ff84152cb7a512833319b80737b1cb66af64418fab62","abstract_canon_sha256":"e8019c78bc1746180f8bc42b7d955349e589cab20602a36f0eee8f11157edbb6"},"schema_version":"1.0"},"canonical_sha256":"d95e58dc8ca2c54824dc3e921d5f410428df2787747500e97c2b2bc98e020bd6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:58:16.057228Z","signature_b64":"nRWLY2RrJqtb+xyLGMui5jPi8nStzrgD32kNfX7WKoCb7dWvTPHKI5Ej/dC/owduaw1hQeiFjHNYzvObsdzIBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d95e58dc8ca2c54824dc3e921d5f410428df2787747500e97c2b2bc98e020bd6","last_reissued_at":"2026-07-05T03:58:16.056772Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:58:16.056772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.14211","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:58:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cVKoBmIqYsPn4f/ikR+iSPLpg2oUDaUK12avb+AVve5celXwLMWtaJFgII2QzGbFRmqa6gYo+74yw+lsD7mCAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:15:52.486617Z"},"content_sha256":"05f16645e01909a3dac049bc85a5d08a6c944284fa73e9b05c26f26ad97f1152","schema_version":"1.0","event_id":"sha256:05f16645e01909a3dac049bc85a5d08a6c944284fa73e9b05c26f26ad97f1152"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:3FPFRXEMULCUQJG4H2JB2X2BAQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"M6-UFC: Unifying Multi-Modal Controls for Conditional Image Synthesis via Non-Autoregressive Generative Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Zhou, Hongxia Yang, Jianxin Ma, Jie Tang, Jingren Zhou, Ming Ding, Rui Men, Zhikang Li, Zhu Zhang","submitted_at":"2021-05-29T04:42:07Z","abstract_excerpt":"Conditional image synthesis aims to create an image according to some multi-modal guidance in the forms of textual descriptions, reference images, and image blocks to preserve, as well as their combinations. In this paper, instead of investigating these control signals separately, we propose a new two-stage architecture, M6-UFC, to unify any number of multi-modal controls. In M6-UFC, both the diverse control signals and the synthesized image are uniformly represented as a sequence of discrete tokens to be processed by Transformer. Different from existing two-stage autoregressive approaches suc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.14211","kind":"arxiv","version":4},"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/2105.14211/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":"2026-07-05T03:58:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c7BMDwDG9UdwStURL/bhOwi7zGspCkFX3v00riWw7Ldfrfq9qcqodVrT3Nf0okeqNJn4yQupSy7sG9cMeoouCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:15:52.487088Z"},"content_sha256":"aca20321d78fd5f022983bf1c3b6e43cb8ce43487d1b6f8817d9246fee3d00f8","schema_version":"1.0","event_id":"sha256:aca20321d78fd5f022983bf1c3b6e43cb8ce43487d1b6f8817d9246fee3d00f8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3FPFRXEMULCUQJG4H2JB2X2BAQ/bundle.json","state_url":"https://pith.science/pith/3FPFRXEMULCUQJG4H2JB2X2BAQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3FPFRXEMULCUQJG4H2JB2X2BAQ/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":"2026-08-08T02:15:52Z","links":{"resolver":"https://pith.science/pith/3FPFRXEMULCUQJG4H2JB2X2BAQ","bundle":"https://pith.science/pith/3FPFRXEMULCUQJG4H2JB2X2BAQ/bundle.json","state":"https://pith.science/pith/3FPFRXEMULCUQJG4H2JB2X2BAQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3FPFRXEMULCUQJG4H2JB2X2BAQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:3FPFRXEMULCUQJG4H2JB2X2BAQ","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":"e8019c78bc1746180f8bc42b7d955349e589cab20602a36f0eee8f11157edbb6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-29T04:42:07Z","title_canon_sha256":"26424a5d588b3e85a685ff84152cb7a512833319b80737b1cb66af64418fab62"},"schema_version":"1.0","source":{"id":"2105.14211","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.14211","created_at":"2026-07-05T03:58:16Z"},{"alias_kind":"arxiv_version","alias_value":"2105.14211v4","created_at":"2026-07-05T03:58:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.14211","created_at":"2026-07-05T03:58:16Z"},{"alias_kind":"pith_short_12","alias_value":"3FPFRXEMULCU","created_at":"2026-07-05T03:58:16Z"},{"alias_kind":"pith_short_16","alias_value":"3FPFRXEMULCUQJG4","created_at":"2026-07-05T03:58:16Z"},{"alias_kind":"pith_short_8","alias_value":"3FPFRXEM","created_at":"2026-07-05T03:58:16Z"}],"graph_snapshots":[{"event_id":"sha256:aca20321d78fd5f022983bf1c3b6e43cb8ce43487d1b6f8817d9246fee3d00f8","target":"graph","created_at":"2026-07-05T03:58:16Z","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/2105.14211/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Conditional image synthesis aims to create an image according to some multi-modal guidance in the forms of textual descriptions, reference images, and image blocks to preserve, as well as their combinations. In this paper, instead of investigating these control signals separately, we propose a new two-stage architecture, M6-UFC, to unify any number of multi-modal controls. In M6-UFC, both the diverse control signals and the synthesized image are uniformly represented as a sequence of discrete tokens to be processed by Transformer. Different from existing two-stage autoregressive approaches suc","authors_text":"Chang Zhou, Hongxia Yang, Jianxin Ma, Jie Tang, Jingren Zhou, Ming Ding, Rui Men, Zhikang Li, Zhu Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-29T04:42:07Z","title":"M6-UFC: Unifying Multi-Modal Controls for Conditional Image Synthesis via Non-Autoregressive Generative Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.14211","kind":"arxiv","version":4},"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":"sha256:05f16645e01909a3dac049bc85a5d08a6c944284fa73e9b05c26f26ad97f1152","target":"record","created_at":"2026-07-05T03:58:16Z","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":"e8019c78bc1746180f8bc42b7d955349e589cab20602a36f0eee8f11157edbb6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-29T04:42:07Z","title_canon_sha256":"26424a5d588b3e85a685ff84152cb7a512833319b80737b1cb66af64418fab62"},"schema_version":"1.0","source":{"id":"2105.14211","kind":"arxiv","version":4}},"canonical_sha256":"d95e58dc8ca2c54824dc3e921d5f410428df2787747500e97c2b2bc98e020bd6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d95e58dc8ca2c54824dc3e921d5f410428df2787747500e97c2b2bc98e020bd6","first_computed_at":"2026-07-05T03:58:16.056772Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:58:16.056772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nRWLY2RrJqtb+xyLGMui5jPi8nStzrgD32kNfX7WKoCb7dWvTPHKI5Ej/dC/owduaw1hQeiFjHNYzvObsdzIBw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:58:16.057228Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.14211","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05f16645e01909a3dac049bc85a5d08a6c944284fa73e9b05c26f26ad97f1152","sha256:aca20321d78fd5f022983bf1c3b6e43cb8ce43487d1b6f8817d9246fee3d00f8"],"state_sha256":"cb5e0d23eb5e75cdd50f547b69b75a0f5cd091dc93adc4c968926a52d8891253"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RmSoyU0iCdNElcd44R74GPOFnSS1MdW/OmYRG0kkdyvZJT++1mb6mt8kUVEMl1tLnm3JnEPyK4Es5O1ULkbrBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T02:15:52.511880Z","bundle_sha256":"f75ee18138b94a767c2cd94a58aca2a8ebefb42d5d3f89073da5ceaa32fb4fdb"}}