{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JULZVU5FRDU76XOTGVDPCTM4KH","short_pith_number":"pith:JULZVU5F","canonical_record":{"source":{"id":"2404.09977","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T17:55:56Z","cross_cats_sorted":[],"title_canon_sha256":"fd8f84e354f1a829b06d6ed60124cde7edee43730649948b6c2660fbc853a389","abstract_canon_sha256":"2ee49abe0e59900c7511f3e773f11aed21fe665614b73395a27a0505d10148fc"},"schema_version":"1.0"},"canonical_sha256":"4d179ad3a588e9ff5dd33546f14d9c51ddd2f8d1e78966b35bc6049c28b10c7a","source":{"kind":"arxiv","id":"2404.09977","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.09977","created_at":"2026-07-05T08:08:13Z"},{"alias_kind":"arxiv_version","alias_value":"2404.09977v1","created_at":"2026-07-05T08:08:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09977","created_at":"2026-07-05T08:08:13Z"},{"alias_kind":"pith_short_12","alias_value":"JULZVU5FRDU7","created_at":"2026-07-05T08:08:13Z"},{"alias_kind":"pith_short_16","alias_value":"JULZVU5FRDU76XOT","created_at":"2026-07-05T08:08:13Z"},{"alias_kind":"pith_short_8","alias_value":"JULZVU5F","created_at":"2026-07-05T08:08:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JULZVU5FRDU76XOTGVDPCTM4KH","target":"record","payload":{"canonical_record":{"source":{"id":"2404.09977","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T17:55:56Z","cross_cats_sorted":[],"title_canon_sha256":"fd8f84e354f1a829b06d6ed60124cde7edee43730649948b6c2660fbc853a389","abstract_canon_sha256":"2ee49abe0e59900c7511f3e773f11aed21fe665614b73395a27a0505d10148fc"},"schema_version":"1.0"},"canonical_sha256":"4d179ad3a588e9ff5dd33546f14d9c51ddd2f8d1e78966b35bc6049c28b10c7a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:13.708895Z","signature_b64":"Qp3QeFgaz7X3PMEn+Y9GZdADSs3351GDIeeOgD5D6JxkriJPwsiQ6hma6sBVplFS0jubBoIGibe/hfZiajaBCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d179ad3a588e9ff5dd33546f14d9c51ddd2f8d1e78966b35bc6049c28b10c7a","last_reissued_at":"2026-07-05T08:08:13.708452Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:13.708452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.09977","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":"2026-07-05T08:08:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HlRlnKJmKQC57i1vGaIssJEYUf7+6bflcHKTMDQk32tSnTAorQ/ntrhC7SAFjkpenzhZSeK4iP7VBD05aj2ZCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T18:20:31.902369Z"},"content_sha256":"5f58ce8df116e3ed9c0848c54b73f50cc16e746b2d862d5ed835050b95615d03","schema_version":"1.0","event_id":"sha256:5f58ce8df116e3ed9c0848c54b73f50cc16e746b2d862d5ed835050b95615d03"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JULZVU5FRDU76XOTGVDPCTM4KH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MaxFusion: Plug&Play Multi-Modal Generation in Text-to-Image Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jeya Maria Jose Valanarasu, Nithin Gopalakrishnan Nair, Vishal M Patel","submitted_at":"2024-04-15T17:55:56Z","abstract_excerpt":"Large diffusion-based Text-to-Image (T2I) models have shown impressive generative powers for text-to-image generation as well as spatially conditioned image generation. For most applications, we can train the model end-toend with paired data to obtain photorealistic generation quality. However, to add an additional task, one often needs to retrain the model from scratch using paired data across all modalities to retain good generation performance. In this paper, we tackle this issue and propose a novel strategy to scale a generative model across new tasks with minimal compute. During our exper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09977","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/2404.09977/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":"2026-07-05T08:08:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7COGmK5F6JDvMwvA1P3HC/RgbElcC/hCLUv+HSF67Tx3AZyIUaSrgScmBuiC+VtGFgTF6z190OsiYF8D4ug5Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T18:20:31.902689Z"},"content_sha256":"1a0461f26769141e9d39a7d2a22222f73f109aca2111665f055c74a04f1b4c16","schema_version":"1.0","event_id":"sha256:1a0461f26769141e9d39a7d2a22222f73f109aca2111665f055c74a04f1b4c16"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JULZVU5FRDU76XOTGVDPCTM4KH/bundle.json","state_url":"https://pith.science/pith/JULZVU5FRDU76XOTGVDPCTM4KH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JULZVU5FRDU76XOTGVDPCTM4KH/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":"2026-07-31T18:20:31Z","links":{"resolver":"https://pith.science/pith/JULZVU5FRDU76XOTGVDPCTM4KH","bundle":"https://pith.science/pith/JULZVU5FRDU76XOTGVDPCTM4KH/bundle.json","state":"https://pith.science/pith/JULZVU5FRDU76XOTGVDPCTM4KH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JULZVU5FRDU76XOTGVDPCTM4KH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JULZVU5FRDU76XOTGVDPCTM4KH","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":"2ee49abe0e59900c7511f3e773f11aed21fe665614b73395a27a0505d10148fc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T17:55:56Z","title_canon_sha256":"fd8f84e354f1a829b06d6ed60124cde7edee43730649948b6c2660fbc853a389"},"schema_version":"1.0","source":{"id":"2404.09977","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.09977","created_at":"2026-07-05T08:08:13Z"},{"alias_kind":"arxiv_version","alias_value":"2404.09977v1","created_at":"2026-07-05T08:08:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09977","created_at":"2026-07-05T08:08:13Z"},{"alias_kind":"pith_short_12","alias_value":"JULZVU5FRDU7","created_at":"2026-07-05T08:08:13Z"},{"alias_kind":"pith_short_16","alias_value":"JULZVU5FRDU76XOT","created_at":"2026-07-05T08:08:13Z"},{"alias_kind":"pith_short_8","alias_value":"JULZVU5F","created_at":"2026-07-05T08:08:13Z"}],"graph_snapshots":[{"event_id":"sha256:1a0461f26769141e9d39a7d2a22222f73f109aca2111665f055c74a04f1b4c16","target":"graph","created_at":"2026-07-05T08:08:13Z","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/2404.09977/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large diffusion-based Text-to-Image (T2I) models have shown impressive generative powers for text-to-image generation as well as spatially conditioned image generation. For most applications, we can train the model end-toend with paired data to obtain photorealistic generation quality. However, to add an additional task, one often needs to retrain the model from scratch using paired data across all modalities to retain good generation performance. In this paper, we tackle this issue and propose a novel strategy to scale a generative model across new tasks with minimal compute. During our exper","authors_text":"Jeya Maria Jose Valanarasu, Nithin Gopalakrishnan Nair, Vishal M Patel","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T17:55:56Z","title":"MaxFusion: Plug&Play Multi-Modal Generation in Text-to-Image Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09977","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":"sha256:5f58ce8df116e3ed9c0848c54b73f50cc16e746b2d862d5ed835050b95615d03","target":"record","created_at":"2026-07-05T08:08:13Z","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":"2ee49abe0e59900c7511f3e773f11aed21fe665614b73395a27a0505d10148fc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T17:55:56Z","title_canon_sha256":"fd8f84e354f1a829b06d6ed60124cde7edee43730649948b6c2660fbc853a389"},"schema_version":"1.0","source":{"id":"2404.09977","kind":"arxiv","version":1}},"canonical_sha256":"4d179ad3a588e9ff5dd33546f14d9c51ddd2f8d1e78966b35bc6049c28b10c7a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d179ad3a588e9ff5dd33546f14d9c51ddd2f8d1e78966b35bc6049c28b10c7a","first_computed_at":"2026-07-05T08:08:13.708452Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:08:13.708452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Qp3QeFgaz7X3PMEn+Y9GZdADSs3351GDIeeOgD5D6JxkriJPwsiQ6hma6sBVplFS0jubBoIGibe/hfZiajaBCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:08:13.708895Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.09977","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f58ce8df116e3ed9c0848c54b73f50cc16e746b2d862d5ed835050b95615d03","sha256:1a0461f26769141e9d39a7d2a22222f73f109aca2111665f055c74a04f1b4c16"],"state_sha256":"b77ffae58dee98d58c67801cd1fee9a0dd7bab49470f0a3bf2d7a6dc0658ef0d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DzWzWPjoFzhW+ZhuEzg20aufMOrAb02tnacS2RczD1uFZo53tIVo+RxopQO7HbPkHKjw8Ch5wjK6yAfU70A1DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T18:20:31.906327Z","bundle_sha256":"72f39a2ef4e5d62db9bc8458575d737fdee277771d01f1284316b27a2b8213fb"}}