{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KI5HY24RIIOV7Y7HG57MZVN6HP","short_pith_number":"pith:KI5HY24R","canonical_record":{"source":{"id":"2411.18301","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T12:47:06Z","cross_cats_sorted":[],"title_canon_sha256":"ca566f4d19124194e29d6263d849b1c92137d0ae5792dab80344e45db22097dd","abstract_canon_sha256":"3586ced53fc72842e9af29b4885a73f1bad1e01f4e1e890a80ec64f757101012"},"schema_version":"1.0"},"canonical_sha256":"523a7c6b91421d5fe3e7377eccd5be3bf1e9c1e9e8d312a4dcae2f81dd1bba97","source":{"kind":"arxiv","id":"2411.18301","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.18301","created_at":"2026-07-05T09:41:14Z"},{"alias_kind":"arxiv_version","alias_value":"2411.18301v1","created_at":"2026-07-05T09:41:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18301","created_at":"2026-07-05T09:41:14Z"},{"alias_kind":"pith_short_12","alias_value":"KI5HY24RIIOV","created_at":"2026-07-05T09:41:14Z"},{"alias_kind":"pith_short_16","alias_value":"KI5HY24RIIOV7Y7H","created_at":"2026-07-05T09:41:14Z"},{"alias_kind":"pith_short_8","alias_value":"KI5HY24R","created_at":"2026-07-05T09:41:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KI5HY24RIIOV7Y7HG57MZVN6HP","target":"record","payload":{"canonical_record":{"source":{"id":"2411.18301","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T12:47:06Z","cross_cats_sorted":[],"title_canon_sha256":"ca566f4d19124194e29d6263d849b1c92137d0ae5792dab80344e45db22097dd","abstract_canon_sha256":"3586ced53fc72842e9af29b4885a73f1bad1e01f4e1e890a80ec64f757101012"},"schema_version":"1.0"},"canonical_sha256":"523a7c6b91421d5fe3e7377eccd5be3bf1e9c1e9e8d312a4dcae2f81dd1bba97","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:14.570942Z","signature_b64":"3737mAftlY+agbmk3htItbPl4HsNb5aed3kfMkrTdzG30raTXEePg088jol7wtDCvu2Bcb72yVIRuF0QKQzJCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"523a7c6b91421d5fe3e7377eccd5be3bf1e9c1e9e8d312a4dcae2f81dd1bba97","last_reissued_at":"2026-07-05T09:41:14.570482Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:14.570482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.18301","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":"2026-07-05T09:41:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/wB27+L+rK0gtNBxrWbaPoXYC7iggFEPIahEp9XUFPUMlguKRtY3M47UA543QtIFcc5tGS4dTwVzm4KbuAaQCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T08:03:24.857131Z"},"content_sha256":"2f291ce95c51d45f7a85daff402a5986ca9eae0701b95cb0f5d0c3378992f7ef","schema_version":"1.0","event_id":"sha256:2f291ce95c51d45f7a85daff402a5986ca9eae0701b95cb0f5d0c3378992f7ef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KI5HY24RIIOV7Y7HG57MZVN6HP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing MMDiT-Based Text-to-Image Models for Similar Subject Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongdong Chen, Tianyi Wei, Xingang Pan, Yifan Zhou","submitted_at":"2024-11-27T12:47:06Z","abstract_excerpt":"Representing the cutting-edge technique of text-to-image models, the latest Multimodal Diffusion Transformer (MMDiT) largely mitigates many generation issues existing in previous models. However, we discover that it still suffers from subject neglect or mixing when the input text prompt contains multiple subjects of similar semantics or appearance. We identify three possible ambiguities within the MMDiT architecture that cause this problem: Inter-block Ambiguity, Text Encoder Ambiguity, and Semantic Ambiguity. To address these issues, we propose to repair the ambiguous latent on-the-fly by tes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18301","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/2411.18301/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":"2026-07-05T09:41:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bvTNruTXFgmmY28sS4qfHxTHipwUeRESkKnln8VMtWQIEWEfmNveXMDRrwkxpqvmMaCEopIvFmBdw63+1XrRDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T08:03:24.858022Z"},"content_sha256":"c28fc1bea54bc57e314aa2934513f4ff975241940d7c38f4a570e28b4ae7adb5","schema_version":"1.0","event_id":"sha256:c28fc1bea54bc57e314aa2934513f4ff975241940d7c38f4a570e28b4ae7adb5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KI5HY24RIIOV7Y7HG57MZVN6HP/bundle.json","state_url":"https://pith.science/pith/KI5HY24RIIOV7Y7HG57MZVN6HP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KI5HY24RIIOV7Y7HG57MZVN6HP/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":"2026-08-10T08:03:24Z","links":{"resolver":"https://pith.science/pith/KI5HY24RIIOV7Y7HG57MZVN6HP","bundle":"https://pith.science/pith/KI5HY24RIIOV7Y7HG57MZVN6HP/bundle.json","state":"https://pith.science/pith/KI5HY24RIIOV7Y7HG57MZVN6HP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KI5HY24RIIOV7Y7HG57MZVN6HP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KI5HY24RIIOV7Y7HG57MZVN6HP","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":"3586ced53fc72842e9af29b4885a73f1bad1e01f4e1e890a80ec64f757101012","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T12:47:06Z","title_canon_sha256":"ca566f4d19124194e29d6263d849b1c92137d0ae5792dab80344e45db22097dd"},"schema_version":"1.0","source":{"id":"2411.18301","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.18301","created_at":"2026-07-05T09:41:14Z"},{"alias_kind":"arxiv_version","alias_value":"2411.18301v1","created_at":"2026-07-05T09:41:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18301","created_at":"2026-07-05T09:41:14Z"},{"alias_kind":"pith_short_12","alias_value":"KI5HY24RIIOV","created_at":"2026-07-05T09:41:14Z"},{"alias_kind":"pith_short_16","alias_value":"KI5HY24RIIOV7Y7H","created_at":"2026-07-05T09:41:14Z"},{"alias_kind":"pith_short_8","alias_value":"KI5HY24R","created_at":"2026-07-05T09:41:14Z"}],"graph_snapshots":[{"event_id":"sha256:c28fc1bea54bc57e314aa2934513f4ff975241940d7c38f4a570e28b4ae7adb5","target":"graph","created_at":"2026-07-05T09:41:14Z","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/2411.18301/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Representing the cutting-edge technique of text-to-image models, the latest Multimodal Diffusion Transformer (MMDiT) largely mitigates many generation issues existing in previous models. However, we discover that it still suffers from subject neglect or mixing when the input text prompt contains multiple subjects of similar semantics or appearance. We identify three possible ambiguities within the MMDiT architecture that cause this problem: Inter-block Ambiguity, Text Encoder Ambiguity, and Semantic Ambiguity. To address these issues, we propose to repair the ambiguous latent on-the-fly by tes","authors_text":"Dongdong Chen, Tianyi Wei, Xingang Pan, Yifan Zhou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T12:47:06Z","title":"Enhancing MMDiT-Based Text-to-Image Models for Similar Subject Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18301","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":"sha256:2f291ce95c51d45f7a85daff402a5986ca9eae0701b95cb0f5d0c3378992f7ef","target":"record","created_at":"2026-07-05T09:41:14Z","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":"3586ced53fc72842e9af29b4885a73f1bad1e01f4e1e890a80ec64f757101012","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T12:47:06Z","title_canon_sha256":"ca566f4d19124194e29d6263d849b1c92137d0ae5792dab80344e45db22097dd"},"schema_version":"1.0","source":{"id":"2411.18301","kind":"arxiv","version":1}},"canonical_sha256":"523a7c6b91421d5fe3e7377eccd5be3bf1e9c1e9e8d312a4dcae2f81dd1bba97","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"523a7c6b91421d5fe3e7377eccd5be3bf1e9c1e9e8d312a4dcae2f81dd1bba97","first_computed_at":"2026-07-05T09:41:14.570482Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:41:14.570482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3737mAftlY+agbmk3htItbPl4HsNb5aed3kfMkrTdzG30raTXEePg088jol7wtDCvu2Bcb72yVIRuF0QKQzJCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:41:14.570942Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.18301","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2f291ce95c51d45f7a85daff402a5986ca9eae0701b95cb0f5d0c3378992f7ef","sha256:c28fc1bea54bc57e314aa2934513f4ff975241940d7c38f4a570e28b4ae7adb5"],"state_sha256":"5231dd4c9e0755f250205e9ba71d7825ae5223e6e1c891416926f07510e9c4f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aH0UBH9S0GI9Fp9X8Bwv1pr8B7I3p8v8IerTea7vBaoXlyXuFO245+79L0ru4x1D7Us1MhPLeZVp0xMXkTz7Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T08:03:24.863755Z","bundle_sha256":"f2d8bbe51b6d9905c3e4bd5bdad2931c656ca2c36b2c12dddf0725767e4dbb95"}}