{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EH5CLYIDAU2FM762JPQRA5MF2E","short_pith_number":"pith:EH5CLYID","canonical_record":{"source":{"id":"2402.12741","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-20T06:14:30Z","cross_cats_sorted":[],"title_canon_sha256":"99db99b762afa34edc6c9e86a78af7b2c4acd1484c449a0ebc514f138f971516","abstract_canon_sha256":"a505ba1090e7ee3e297c68eb97680cab6c87bdb82cc9c756e65c2ffd254f4540"},"schema_version":"1.0"},"canonical_sha256":"21fa25e1030534567fda4be1107585d1007dcc638292391d0a5245913808c41a","source":{"kind":"arxiv","id":"2402.12741","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.12741","created_at":"2026-07-05T08:22:37Z"},{"alias_kind":"arxiv_version","alias_value":"2402.12741v2","created_at":"2026-07-05T08:22:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12741","created_at":"2026-07-05T08:22:37Z"},{"alias_kind":"pith_short_12","alias_value":"EH5CLYIDAU2F","created_at":"2026-07-05T08:22:37Z"},{"alias_kind":"pith_short_16","alias_value":"EH5CLYIDAU2FM762","created_at":"2026-07-05T08:22:37Z"},{"alias_kind":"pith_short_8","alias_value":"EH5CLYID","created_at":"2026-07-05T08:22:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EH5CLYIDAU2FM762JPQRA5MF2E","target":"record","payload":{"canonical_record":{"source":{"id":"2402.12741","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-20T06:14:30Z","cross_cats_sorted":[],"title_canon_sha256":"99db99b762afa34edc6c9e86a78af7b2c4acd1484c449a0ebc514f138f971516","abstract_canon_sha256":"a505ba1090e7ee3e297c68eb97680cab6c87bdb82cc9c756e65c2ffd254f4540"},"schema_version":"1.0"},"canonical_sha256":"21fa25e1030534567fda4be1107585d1007dcc638292391d0a5245913808c41a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:37.746361Z","signature_b64":"GeGJwrq1Zr7aZu972vQPDoHpW1vl8UE2aOMout49Y8NsihsSNBNH4Rho1t5yfUu0jTeG3UJUCHJeK0Om9t5ABA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21fa25e1030534567fda4be1107585d1007dcc638292391d0a5245913808c41a","last_reissued_at":"2026-07-05T08:22:37.745831Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:37.745831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.12741","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:22:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p1bjX0u5q8kes0GZocNZONzUzMn9/IXvPaTMEzn3fxfmLspb45GZWJD+9Kb67nwvegpXuz6URo7FAhkBqaMnDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:26:07.219244Z"},"content_sha256":"91660b031e48703ce11abe2ccfd6414d933b39a6e5a2f8cf810fbd20e65f2738","schema_version":"1.0","event_id":"sha256:91660b031e48703ce11abe2ccfd6414d933b39a6e5a2f8cf810fbd20e65f2738"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EH5CLYIDAU2FM762JPQRA5MF2E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MuLan: Multimodal-LLM Agent for Progressive and Interactive Multi-Object Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cho-Jui Hsieh, Minhao Cheng, Ruochen Wang, Sen Li, Tianyi Zhou","submitted_at":"2024-02-20T06:14:30Z","abstract_excerpt":"Existing text-to-image models still struggle to generate images of multiple objects, especially in handling their spatial positions, relative sizes, overlapping, and attribute bindings. To efficiently address these challenges, we develop a training-free Multimodal-LLM agent (MuLan), as a human painter, that can progressively generate multi-object with intricate planning and feedback control. MuLan harnesses a large language model (LLM) to decompose a prompt to a sequence of sub-tasks, each generating only one object by stable diffusion, conditioned on previously generated objects. Unlike exist"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12741","kind":"arxiv","version":2},"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/2402.12741/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":"2026-07-05T08:22:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pWqoMRbrVd/cVo8G8s0eXsgANi5wobBrPUfRAUyumvLKcCoKZsp7YDSwitnV6xoAWoDOpRf39h9DXvG435qtCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:26:07.219806Z"},"content_sha256":"74484dabc874c4bd0529c3ad4ebfcfacb2a1d8436fc4f719ebc059c0bc9ed74e","schema_version":"1.0","event_id":"sha256:74484dabc874c4bd0529c3ad4ebfcfacb2a1d8436fc4f719ebc059c0bc9ed74e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EH5CLYIDAU2FM762JPQRA5MF2E/bundle.json","state_url":"https://pith.science/pith/EH5CLYIDAU2FM762JPQRA5MF2E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EH5CLYIDAU2FM762JPQRA5MF2E/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":"2026-08-05T02:26:07Z","links":{"resolver":"https://pith.science/pith/EH5CLYIDAU2FM762JPQRA5MF2E","bundle":"https://pith.science/pith/EH5CLYIDAU2FM762JPQRA5MF2E/bundle.json","state":"https://pith.science/pith/EH5CLYIDAU2FM762JPQRA5MF2E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EH5CLYIDAU2FM762JPQRA5MF2E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EH5CLYIDAU2FM762JPQRA5MF2E","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":"a505ba1090e7ee3e297c68eb97680cab6c87bdb82cc9c756e65c2ffd254f4540","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-20T06:14:30Z","title_canon_sha256":"99db99b762afa34edc6c9e86a78af7b2c4acd1484c449a0ebc514f138f971516"},"schema_version":"1.0","source":{"id":"2402.12741","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.12741","created_at":"2026-07-05T08:22:37Z"},{"alias_kind":"arxiv_version","alias_value":"2402.12741v2","created_at":"2026-07-05T08:22:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12741","created_at":"2026-07-05T08:22:37Z"},{"alias_kind":"pith_short_12","alias_value":"EH5CLYIDAU2F","created_at":"2026-07-05T08:22:37Z"},{"alias_kind":"pith_short_16","alias_value":"EH5CLYIDAU2FM762","created_at":"2026-07-05T08:22:37Z"},{"alias_kind":"pith_short_8","alias_value":"EH5CLYID","created_at":"2026-07-05T08:22:37Z"}],"graph_snapshots":[{"event_id":"sha256:74484dabc874c4bd0529c3ad4ebfcfacb2a1d8436fc4f719ebc059c0bc9ed74e","target":"graph","created_at":"2026-07-05T08:22:37Z","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/2402.12741/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing text-to-image models still struggle to generate images of multiple objects, especially in handling their spatial positions, relative sizes, overlapping, and attribute bindings. To efficiently address these challenges, we develop a training-free Multimodal-LLM agent (MuLan), as a human painter, that can progressively generate multi-object with intricate planning and feedback control. MuLan harnesses a large language model (LLM) to decompose a prompt to a sequence of sub-tasks, each generating only one object by stable diffusion, conditioned on previously generated objects. Unlike exist","authors_text":"Cho-Jui Hsieh, Minhao Cheng, Ruochen Wang, Sen Li, Tianyi Zhou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-20T06:14:30Z","title":"MuLan: Multimodal-LLM Agent for Progressive and Interactive Multi-Object Diffusion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12741","kind":"arxiv","version":2},"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":"sha256:91660b031e48703ce11abe2ccfd6414d933b39a6e5a2f8cf810fbd20e65f2738","target":"record","created_at":"2026-07-05T08:22:37Z","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":"a505ba1090e7ee3e297c68eb97680cab6c87bdb82cc9c756e65c2ffd254f4540","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-20T06:14:30Z","title_canon_sha256":"99db99b762afa34edc6c9e86a78af7b2c4acd1484c449a0ebc514f138f971516"},"schema_version":"1.0","source":{"id":"2402.12741","kind":"arxiv","version":2}},"canonical_sha256":"21fa25e1030534567fda4be1107585d1007dcc638292391d0a5245913808c41a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"21fa25e1030534567fda4be1107585d1007dcc638292391d0a5245913808c41a","first_computed_at":"2026-07-05T08:22:37.745831Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:22:37.745831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GeGJwrq1Zr7aZu972vQPDoHpW1vl8UE2aOMout49Y8NsihsSNBNH4Rho1t5yfUu0jTeG3UJUCHJeK0Om9t5ABA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:22:37.746361Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.12741","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:91660b031e48703ce11abe2ccfd6414d933b39a6e5a2f8cf810fbd20e65f2738","sha256:74484dabc874c4bd0529c3ad4ebfcfacb2a1d8436fc4f719ebc059c0bc9ed74e"],"state_sha256":"12f26040c609e7e37fa18daa71433608aa0e5c40a97cec2cce4b2adfa4e6c4dc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mmzhJzjX8VagT4pLDL8uF5HKrwP2xorWHMVEnBg/+oYb+6typpiSQTCzOcq/El8hnnwTwyaqGoU0OislHCdpCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T02:26:07.223293Z","bundle_sha256":"b9effecebd20e59179a223a4d8a88fa4d9eb3c525ffb1fcc9fc0eded1f5db7d0"}}