{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3OLGQ7V7IFJ6Z5AQHLXQMSNKDK","short_pith_number":"pith:3OLGQ7V7","canonical_record":{"source":{"id":"2405.17661","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-27T21:23:20Z","cross_cats_sorted":[],"title_canon_sha256":"525176e44ca8597fa31939f1b69d39bfd91618964ec8827c21adc203deb11d18","abstract_canon_sha256":"5709e74c580d44bd8aea6a6ada4036b551b8da6d295a313df6f1b250637d5185"},"schema_version":"1.0"},"canonical_sha256":"db96687ebf4153ecf4103aef0649aa1a90e6cfb1d77b8127e8938054df25f2e0","source":{"kind":"arxiv","id":"2405.17661","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17661","created_at":"2026-07-05T08:24:09Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17661v1","created_at":"2026-07-05T08:24:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17661","created_at":"2026-07-05T08:24:09Z"},{"alias_kind":"pith_short_12","alias_value":"3OLGQ7V7IFJ6","created_at":"2026-07-05T08:24:09Z"},{"alias_kind":"pith_short_16","alias_value":"3OLGQ7V7IFJ6Z5AQ","created_at":"2026-07-05T08:24:09Z"},{"alias_kind":"pith_short_8","alias_value":"3OLGQ7V7","created_at":"2026-07-05T08:24:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3OLGQ7V7IFJ6Z5AQHLXQMSNKDK","target":"record","payload":{"canonical_record":{"source":{"id":"2405.17661","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-27T21:23:20Z","cross_cats_sorted":[],"title_canon_sha256":"525176e44ca8597fa31939f1b69d39bfd91618964ec8827c21adc203deb11d18","abstract_canon_sha256":"5709e74c580d44bd8aea6a6ada4036b551b8da6d295a313df6f1b250637d5185"},"schema_version":"1.0"},"canonical_sha256":"db96687ebf4153ecf4103aef0649aa1a90e6cfb1d77b8127e8938054df25f2e0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:09.497652Z","signature_b64":"zkc4NOPd+cbAohI0rEqDVqg9uU4PZ9NXTJQCu06pQQnvsW9sFAGLffN904Do2K6zVioUUWwqhP4APAjdJBIrCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db96687ebf4153ecf4103aef0649aa1a90e6cfb1d77b8127e8938054df25f2e0","last_reissued_at":"2026-07-05T08:24:09.497166Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:09.497166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.17661","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":"2026-07-05T08:24:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NRg04g/6+rvMNKmSsKTvF26xTsPJ036gVQPNUA/P73C8y+WX1uWmQt7Nl9SfOntVXhgxqO2nms+RXGJMVlysDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T20:08:21.777813Z"},"content_sha256":"d6ace10691550362ca8623b5e0134367266a70be27cb636f9b5991de7f6cd65b","schema_version":"1.0","event_id":"sha256:d6ace10691550362ca8623b5e0134367266a70be27cb636f9b5991de7f6cd65b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3OLGQ7V7IFJ6Z5AQHLXQMSNKDK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RefDrop: Controllable Consistency in Image or Video Generation via Reference Feature Guidance","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haotian Xue, Jiaojiao Fan, Qinsheng Zhang, Yongxin Chen","submitted_at":"2024-05-27T21:23:20Z","abstract_excerpt":"There is a rapidly growing interest in controlling consistency across multiple generated images using diffusion models. Among various methods, recent works have found that simply manipulating attention modules by concatenating features from multiple reference images provides an efficient approach to enhancing consistency without fine-tuning. Despite its popularity and success, few studies have elucidated the underlying mechanisms that contribute to its effectiveness. In this work, we reveal that the popular approach is a linear interpolation of image self-attention and cross-attention between "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17661","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/2405.17661/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":"2026-07-05T08:24:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KkH92gosvRJP5iTNkPjTZvvdikM0oxB298KChxC5ZpBCJAE7P4A0tnhkILZGNCaLu7r/0nKBaifcQpMCxximCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T20:08:21.778325Z"},"content_sha256":"cd1c2e61d53738194a5d91aff39b4f07f7d12528923dc6590981d20e47d1575d","schema_version":"1.0","event_id":"sha256:cd1c2e61d53738194a5d91aff39b4f07f7d12528923dc6590981d20e47d1575d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3OLGQ7V7IFJ6Z5AQHLXQMSNKDK/bundle.json","state_url":"https://pith.science/pith/3OLGQ7V7IFJ6Z5AQHLXQMSNKDK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3OLGQ7V7IFJ6Z5AQHLXQMSNKDK/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":"2026-08-06T20:08:21Z","links":{"resolver":"https://pith.science/pith/3OLGQ7V7IFJ6Z5AQHLXQMSNKDK","bundle":"https://pith.science/pith/3OLGQ7V7IFJ6Z5AQHLXQMSNKDK/bundle.json","state":"https://pith.science/pith/3OLGQ7V7IFJ6Z5AQHLXQMSNKDK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3OLGQ7V7IFJ6Z5AQHLXQMSNKDK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3OLGQ7V7IFJ6Z5AQHLXQMSNKDK","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":"5709e74c580d44bd8aea6a6ada4036b551b8da6d295a313df6f1b250637d5185","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-27T21:23:20Z","title_canon_sha256":"525176e44ca8597fa31939f1b69d39bfd91618964ec8827c21adc203deb11d18"},"schema_version":"1.0","source":{"id":"2405.17661","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17661","created_at":"2026-07-05T08:24:09Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17661v1","created_at":"2026-07-05T08:24:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17661","created_at":"2026-07-05T08:24:09Z"},{"alias_kind":"pith_short_12","alias_value":"3OLGQ7V7IFJ6","created_at":"2026-07-05T08:24:09Z"},{"alias_kind":"pith_short_16","alias_value":"3OLGQ7V7IFJ6Z5AQ","created_at":"2026-07-05T08:24:09Z"},{"alias_kind":"pith_short_8","alias_value":"3OLGQ7V7","created_at":"2026-07-05T08:24:09Z"}],"graph_snapshots":[{"event_id":"sha256:cd1c2e61d53738194a5d91aff39b4f07f7d12528923dc6590981d20e47d1575d","target":"graph","created_at":"2026-07-05T08:24:09Z","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/2405.17661/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There is a rapidly growing interest in controlling consistency across multiple generated images using diffusion models. Among various methods, recent works have found that simply manipulating attention modules by concatenating features from multiple reference images provides an efficient approach to enhancing consistency without fine-tuning. Despite its popularity and success, few studies have elucidated the underlying mechanisms that contribute to its effectiveness. In this work, we reveal that the popular approach is a linear interpolation of image self-attention and cross-attention between ","authors_text":"Haotian Xue, Jiaojiao Fan, Qinsheng Zhang, Yongxin Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-27T21:23:20Z","title":"RefDrop: Controllable Consistency in Image or Video Generation via Reference Feature Guidance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17661","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:d6ace10691550362ca8623b5e0134367266a70be27cb636f9b5991de7f6cd65b","target":"record","created_at":"2026-07-05T08:24:09Z","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":"5709e74c580d44bd8aea6a6ada4036b551b8da6d295a313df6f1b250637d5185","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-27T21:23:20Z","title_canon_sha256":"525176e44ca8597fa31939f1b69d39bfd91618964ec8827c21adc203deb11d18"},"schema_version":"1.0","source":{"id":"2405.17661","kind":"arxiv","version":1}},"canonical_sha256":"db96687ebf4153ecf4103aef0649aa1a90e6cfb1d77b8127e8938054df25f2e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db96687ebf4153ecf4103aef0649aa1a90e6cfb1d77b8127e8938054df25f2e0","first_computed_at":"2026-07-05T08:24:09.497166Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:24:09.497166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zkc4NOPd+cbAohI0rEqDVqg9uU4PZ9NXTJQCu06pQQnvsW9sFAGLffN904Do2K6zVioUUWwqhP4APAjdJBIrCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:24:09.497652Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.17661","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6ace10691550362ca8623b5e0134367266a70be27cb636f9b5991de7f6cd65b","sha256:cd1c2e61d53738194a5d91aff39b4f07f7d12528923dc6590981d20e47d1575d"],"state_sha256":"99cfef720ff738331fed383ab89e63ebf576aa0fd8077126895437a10bce713f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LQ/mIPqpLhbOvg5lH0MKG+7ZYvRh7Z+PTHq09V4xbCgAvz2hIioacLZNtY31TCLyPLmmlpdP+/5tlMVLOl5cCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T20:08:21.784542Z","bundle_sha256":"8bb9a1993feb075151ec1383d5cfeef39d6c85a3865fd3ff32351197a03c6fca"}}