{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:AJCWOPLWTUP7MMDFYSUU3T32LQ","short_pith_number":"pith:AJCWOPLW","canonical_record":{"source":{"id":"2407.15488","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-22T09:05:16Z","cross_cats_sorted":[],"title_canon_sha256":"f52be173d670cd186748b11eaaaa16f4b16358bddbc65373c032503a59c62839","abstract_canon_sha256":"481cdf70eb9512778849d72ce39638c9b9df3aabb589f3991008c4bfea6bb696"},"schema_version":"1.0"},"canonical_sha256":"0245673d769d1ff63065c4a94dcf7a5c298fcb0e0fd8ad7a1e6924648b5e994c","source":{"kind":"arxiv","id":"2407.15488","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.15488","created_at":"2026-07-05T09:23:09Z"},{"alias_kind":"arxiv_version","alias_value":"2407.15488v5","created_at":"2026-07-05T09:23:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15488","created_at":"2026-07-05T09:23:09Z"},{"alias_kind":"pith_short_12","alias_value":"AJCWOPLWTUP7","created_at":"2026-07-05T09:23:09Z"},{"alias_kind":"pith_short_16","alias_value":"AJCWOPLWTUP7MMDF","created_at":"2026-07-05T09:23:09Z"},{"alias_kind":"pith_short_8","alias_value":"AJCWOPLW","created_at":"2026-07-05T09:23:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:AJCWOPLWTUP7MMDFYSUU3T32LQ","target":"record","payload":{"canonical_record":{"source":{"id":"2407.15488","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-22T09:05:16Z","cross_cats_sorted":[],"title_canon_sha256":"f52be173d670cd186748b11eaaaa16f4b16358bddbc65373c032503a59c62839","abstract_canon_sha256":"481cdf70eb9512778849d72ce39638c9b9df3aabb589f3991008c4bfea6bb696"},"schema_version":"1.0"},"canonical_sha256":"0245673d769d1ff63065c4a94dcf7a5c298fcb0e0fd8ad7a1e6924648b5e994c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:09.063987Z","signature_b64":"x24FZFHldf8aFxO5K9t33by53swLZ+O1ZXb5s5XIqS16yGRy/h9ML0x14bJE1aBBvxE1AIzmmfxIiH/verTpDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0245673d769d1ff63065c4a94dcf7a5c298fcb0e0fd8ad7a1e6924648b5e994c","last_reissued_at":"2026-07-05T09:23:09.063558Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:09.063558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.15488","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":"2026-07-05T09:23:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eAlAXf9WSvaADldgVrOdLZrM6ob2nS80Rj0Y7KBpt0rM1tuePU4N2i7q1RJcNeh2rr5mzExWxzm9vBoNxCvNBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T15:46:59.994982Z"},"content_sha256":"4eca71e3cfd7f1d09f8c476b713c262ef8219d3f38e7f32abe9c0cfe67c7849b","schema_version":"1.0","event_id":"sha256:4eca71e3cfd7f1d09f8c476b713c262ef8219d3f38e7f32abe9c0cfe67c7849b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:AJCWOPLWTUP7MMDFYSUU3T32LQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DiffX: Guide Your Layout to Cross-Modal Generative Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bosong Chai, Cunjian Chen, Jingyu Lin, Juncan Deng, Kejie Huang, Lan Du, Qu Yang, Shicen Tian, Yifei Qian, Yi Huang, Zeyu Wang","submitted_at":"2024-07-22T09:05:16Z","abstract_excerpt":"Diffusion models have made significant strides in language-driven and layout-driven image generation. However, most diffusion models are limited to visible RGB image generation. In fact, human perception of the world is enriched by diverse viewpoints, such as chromatic contrast, thermal illumination, and depth information. In this paper, we introduce a novel diffusion model for general layout-guided cross-modal generation, called DiffX. Notably, our DiffX presents a compact and effective cross-modal generative modeling pipeline, which conducts diffusion and denoising processes in the modality-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15488","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/2407.15488/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":"2026-07-05T09:23:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y7qlSu6vYtfkXD3nVVrwMuGTa1zLki4pO/rtbRuoSyEtP/fTtI2ww1Xtbbd1mUrkQFJgsLURkXLc9Ir2HsSBBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T15:46:59.995754Z"},"content_sha256":"31bc534407397407f58cdff12635fa94a890ce1e73af32dc0aff5f862ee81457","schema_version":"1.0","event_id":"sha256:31bc534407397407f58cdff12635fa94a890ce1e73af32dc0aff5f862ee81457"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AJCWOPLWTUP7MMDFYSUU3T32LQ/bundle.json","state_url":"https://pith.science/pith/AJCWOPLWTUP7MMDFYSUU3T32LQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AJCWOPLWTUP7MMDFYSUU3T32LQ/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":"2026-08-12T15:46:59Z","links":{"resolver":"https://pith.science/pith/AJCWOPLWTUP7MMDFYSUU3T32LQ","bundle":"https://pith.science/pith/AJCWOPLWTUP7MMDFYSUU3T32LQ/bundle.json","state":"https://pith.science/pith/AJCWOPLWTUP7MMDFYSUU3T32LQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AJCWOPLWTUP7MMDFYSUU3T32LQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AJCWOPLWTUP7MMDFYSUU3T32LQ","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":"481cdf70eb9512778849d72ce39638c9b9df3aabb589f3991008c4bfea6bb696","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-22T09:05:16Z","title_canon_sha256":"f52be173d670cd186748b11eaaaa16f4b16358bddbc65373c032503a59c62839"},"schema_version":"1.0","source":{"id":"2407.15488","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.15488","created_at":"2026-07-05T09:23:09Z"},{"alias_kind":"arxiv_version","alias_value":"2407.15488v5","created_at":"2026-07-05T09:23:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15488","created_at":"2026-07-05T09:23:09Z"},{"alias_kind":"pith_short_12","alias_value":"AJCWOPLWTUP7","created_at":"2026-07-05T09:23:09Z"},{"alias_kind":"pith_short_16","alias_value":"AJCWOPLWTUP7MMDF","created_at":"2026-07-05T09:23:09Z"},{"alias_kind":"pith_short_8","alias_value":"AJCWOPLW","created_at":"2026-07-05T09:23:09Z"}],"graph_snapshots":[{"event_id":"sha256:31bc534407397407f58cdff12635fa94a890ce1e73af32dc0aff5f862ee81457","target":"graph","created_at":"2026-07-05T09:23:09Z","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/2407.15488/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion models have made significant strides in language-driven and layout-driven image generation. However, most diffusion models are limited to visible RGB image generation. In fact, human perception of the world is enriched by diverse viewpoints, such as chromatic contrast, thermal illumination, and depth information. In this paper, we introduce a novel diffusion model for general layout-guided cross-modal generation, called DiffX. Notably, our DiffX presents a compact and effective cross-modal generative modeling pipeline, which conducts diffusion and denoising processes in the modality-","authors_text":"Bosong Chai, Cunjian Chen, Jingyu Lin, Juncan Deng, Kejie Huang, Lan Du, Qu Yang, Shicen Tian, Yifei Qian, Yi Huang, Zeyu Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-22T09:05:16Z","title":"DiffX: Guide Your Layout to Cross-Modal Generative Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15488","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":"sha256:4eca71e3cfd7f1d09f8c476b713c262ef8219d3f38e7f32abe9c0cfe67c7849b","target":"record","created_at":"2026-07-05T09:23:09Z","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":"481cdf70eb9512778849d72ce39638c9b9df3aabb589f3991008c4bfea6bb696","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-22T09:05:16Z","title_canon_sha256":"f52be173d670cd186748b11eaaaa16f4b16358bddbc65373c032503a59c62839"},"schema_version":"1.0","source":{"id":"2407.15488","kind":"arxiv","version":5}},"canonical_sha256":"0245673d769d1ff63065c4a94dcf7a5c298fcb0e0fd8ad7a1e6924648b5e994c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0245673d769d1ff63065c4a94dcf7a5c298fcb0e0fd8ad7a1e6924648b5e994c","first_computed_at":"2026-07-05T09:23:09.063558Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:23:09.063558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x24FZFHldf8aFxO5K9t33by53swLZ+O1ZXb5s5XIqS16yGRy/h9ML0x14bJE1aBBvxE1AIzmmfxIiH/verTpDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:23:09.063987Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.15488","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4eca71e3cfd7f1d09f8c476b713c262ef8219d3f38e7f32abe9c0cfe67c7849b","sha256:31bc534407397407f58cdff12635fa94a890ce1e73af32dc0aff5f862ee81457"],"state_sha256":"24a1c872c6ca0c65210c32efbf05b0e8c5561e0449b5f3dbf7d6662d95c8be16"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s++ccE4dbrvr2EmXUbalNmsq/GKEMbp6KV1pdob6BCv7BiI7oUjX+V3ahul701jeXcqKqR6l+TcWkegM0oUOBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T15:47:00.002887Z","bundle_sha256":"a6a25a9cbbdb21d17d0a616a21b4ff37c486891c67f61f3ecba732f6d9f13490"}}