{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6TOAJNELJHQE6GMGBR3F6ZG266","short_pith_number":"pith:6TOAJNEL","canonical_record":{"source":{"id":"2604.03156","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-03T16:27:02Z","cross_cats_sorted":[],"title_canon_sha256":"3c43939a444b0ab08c82942010c9148132e4c26bf361a2931d433c38b2881479","abstract_canon_sha256":"cdd56530fb30d21a3131bc0ab0966acd7c7790757f409c2e6534c0547ac466d9"},"schema_version":"1.0"},"canonical_sha256":"f4dc04b48b49e04f19860c765f64daf7991dc664d542d6b7b095ab04913b2bcb","source":{"kind":"arxiv","id":"2604.03156","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.03156","created_at":"2026-06-19T16:11:22Z"},{"alias_kind":"arxiv_version","alias_value":"2604.03156v2","created_at":"2026-06-19T16:11:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.03156","created_at":"2026-06-19T16:11:22Z"},{"alias_kind":"pith_short_12","alias_value":"6TOAJNELJHQE","created_at":"2026-06-19T16:11:22Z"},{"alias_kind":"pith_short_16","alias_value":"6TOAJNELJHQE6GMG","created_at":"2026-06-19T16:11:22Z"},{"alias_kind":"pith_short_8","alias_value":"6TOAJNEL","created_at":"2026-06-19T16:11:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6TOAJNELJHQE6GMGBR3F6ZG266","target":"record","payload":{"canonical_record":{"source":{"id":"2604.03156","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-03T16:27:02Z","cross_cats_sorted":[],"title_canon_sha256":"3c43939a444b0ab08c82942010c9148132e4c26bf361a2931d433c38b2881479","abstract_canon_sha256":"cdd56530fb30d21a3131bc0ab0966acd7c7790757f409c2e6534c0547ac466d9"},"schema_version":"1.0"},"canonical_sha256":"f4dc04b48b49e04f19860c765f64daf7991dc664d542d6b7b095ab04913b2bcb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:22.777682Z","signature_b64":"Ayga5oX3eFiRf7XAwycsK3tJzG9bTnOT6DKUYc7xk+oeCkxV6jCEzGZIUxGAcAT/dF4WQMweRqifNZsvmdPCAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4dc04b48b49e04f19860c765f64daf7991dc664d542d6b7b095ab04913b2bcb","last_reissued_at":"2026-06-19T16:11:22.777263Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:22.777263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.03156","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":"2026-06-19T16:11:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MxeM8VzRK7MeJyGOiLVV5zMG7x+4InJ6xgX7R1BX7BZpyax+BjlCoMrJlDHCE3ey7qRK1j9Vpb5mU2r3lLNQCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T00:08:12.960029Z"},"content_sha256":"5c6cd658ef98010fa5c9feb53cb9ad251547cf613ab95e7eded0df0d18bed656","schema_version":"1.0","event_id":"sha256:5c6cd658ef98010fa5c9feb53cb9ad251547cf613ab95e7eded0df0d18bed656"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6TOAJNELJHQE6GMGBR3F6ZG266","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CAMEO: A Conditional and Quality-Aware Multi-Agent Image Editing Orchestrator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"CAMEO turns conditional image editing into a feedback-driven multi-agent process that raises win rates by 20 percent over single-step models.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Zheng, Hill Zhang, Jiaheng Wei, Shuhong Wu, Tianyi Fan, Yuhan Pu, Ziqian Mo, Zirui Pang","submitted_at":"2026-04-03T16:27:02Z","abstract_excerpt":"Conditional image editing aims to modify a source image according to textual prompts and optional reference guidance. Such editing is crucial in scenarios requiring strict structural control (i.e., anomaly insertion in driving scenes and complex human pose transformation). Despite recent advances in large-scale editing models (i.e., Seedream, Nano Banana, etc), most approaches rely on single-step generation. This paradigm often lacks explicit quality control, may introduce excessive deviation from the original image, and frequently produces structural artifacts or environment-inconsistent modi"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"CAMEO consistently achieves 20% more win rate on average compared to multiple state-of-the-art models, demonstrating improved robustness, controllability, and structural reliability in conditional image editing.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the multi-agent decomposition with embedded evaluation will reliably detect and correct structural and contextual inconsistencies without introducing new artifacts or requiring impractical computation, and that comparisons against independent evaluation models are unbiased and comprehensive.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CAMEO uses coordinated agents for planning, prompting, generation, and quality feedback to achieve higher structural reliability in conditional image editing than single-step models.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"CAMEO turns conditional image editing into a feedback-driven multi-agent process that raises win rates by 20 percent over single-step models.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"7c00677cda35be4688a3c5ec5fba39e5f49cbbc22ab5c02b8cc9b04acedaa8ba"},"source":{"id":"2604.03156","kind":"arxiv","version":2},"verdict":{"id":"87c3743f-79f5-4fb7-a953-4acb23ffcb5b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T20:55:38.502782Z","strongest_claim":"CAMEO consistently achieves 20% more win rate on average compared to multiple state-of-the-art models, demonstrating improved robustness, controllability, and structural reliability in conditional image editing.","one_line_summary":"CAMEO uses coordinated agents for planning, prompting, generation, and quality feedback to achieve higher structural reliability in conditional image editing than single-step models.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the multi-agent decomposition with embedded evaluation will reliably detect and correct structural and contextual inconsistencies without introducing new artifacts or requiring impractical computation, and that comparisons against independent evaluation models are unbiased and comprehensive.","pith_extraction_headline":"CAMEO turns conditional image editing into a feedback-driven multi-agent process that raises win rates by 20 percent over single-step models."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.03156/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":"87c3743f-79f5-4fb7-a953-4acb23ffcb5b"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-19T16:11:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VhOkQheM11tKZ6Jozp6+XGcmYtvSQ9NGtk8d1gqmCbheRoiWLhdWTDsW0vNfSC169GupYeaoySSboe0QlSfvAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T00:08:12.960489Z"},"content_sha256":"f9c40674f06667c6cb295f4ed3bd4dd613a330be76186c49cb1e43053241568f","schema_version":"1.0","event_id":"sha256:f9c40674f06667c6cb295f4ed3bd4dd613a330be76186c49cb1e43053241568f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6TOAJNELJHQE6GMGBR3F6ZG266/bundle.json","state_url":"https://pith.science/pith/6TOAJNELJHQE6GMGBR3F6ZG266/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6TOAJNELJHQE6GMGBR3F6ZG266/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":"2026-06-30T00:08:12Z","links":{"resolver":"https://pith.science/pith/6TOAJNELJHQE6GMGBR3F6ZG266","bundle":"https://pith.science/pith/6TOAJNELJHQE6GMGBR3F6ZG266/bundle.json","state":"https://pith.science/pith/6TOAJNELJHQE6GMGBR3F6ZG266/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6TOAJNELJHQE6GMGBR3F6ZG266/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6TOAJNELJHQE6GMGBR3F6ZG266","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":"cdd56530fb30d21a3131bc0ab0966acd7c7790757f409c2e6534c0547ac466d9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-03T16:27:02Z","title_canon_sha256":"3c43939a444b0ab08c82942010c9148132e4c26bf361a2931d433c38b2881479"},"schema_version":"1.0","source":{"id":"2604.03156","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.03156","created_at":"2026-06-19T16:11:22Z"},{"alias_kind":"arxiv_version","alias_value":"2604.03156v2","created_at":"2026-06-19T16:11:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.03156","created_at":"2026-06-19T16:11:22Z"},{"alias_kind":"pith_short_12","alias_value":"6TOAJNELJHQE","created_at":"2026-06-19T16:11:22Z"},{"alias_kind":"pith_short_16","alias_value":"6TOAJNELJHQE6GMG","created_at":"2026-06-19T16:11:22Z"},{"alias_kind":"pith_short_8","alias_value":"6TOAJNEL","created_at":"2026-06-19T16:11:22Z"}],"graph_snapshots":[{"event_id":"sha256:f9c40674f06667c6cb295f4ed3bd4dd613a330be76186c49cb1e43053241568f","target":"graph","created_at":"2026-06-19T16:11:22Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"CAMEO consistently achieves 20% more win rate on average compared to multiple state-of-the-art models, demonstrating improved robustness, controllability, and structural reliability in conditional image editing."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the multi-agent decomposition with embedded evaluation will reliably detect and correct structural and contextual inconsistencies without introducing new artifacts or requiring impractical computation, and that comparisons against independent evaluation models are unbiased and comprehensive."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"CAMEO uses coordinated agents for planning, prompting, generation, and quality feedback to achieve higher structural reliability in conditional image editing than single-step models."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"CAMEO turns conditional image editing into a feedback-driven multi-agent process that raises win rates by 20 percent over single-step models."}],"snapshot_sha256":"7c00677cda35be4688a3c5ec5fba39e5f49cbbc22ab5c02b8cc9b04acedaa8ba"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.03156/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Conditional image editing aims to modify a source image according to textual prompts and optional reference guidance. Such editing is crucial in scenarios requiring strict structural control (i.e., anomaly insertion in driving scenes and complex human pose transformation). Despite recent advances in large-scale editing models (i.e., Seedream, Nano Banana, etc), most approaches rely on single-step generation. This paradigm often lacks explicit quality control, may introduce excessive deviation from the original image, and frequently produces structural artifacts or environment-inconsistent modi","authors_text":"Hao Zheng, Hill Zhang, Jiaheng Wei, Shuhong Wu, Tianyi Fan, Yuhan Pu, Ziqian Mo, Zirui Pang","cross_cats":[],"headline":"CAMEO turns conditional image editing into a feedback-driven multi-agent process that raises win rates by 20 percent over single-step models.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-03T16:27:02Z","title":"CAMEO: A Conditional and Quality-Aware Multi-Agent Image Editing Orchestrator"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.03156","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-13T20:55:38.502782Z","id":"87c3743f-79f5-4fb7-a953-4acb23ffcb5b","model_set":{"reader":"grok-4.3"},"one_line_summary":"CAMEO uses coordinated agents for planning, prompting, generation, and quality feedback to achieve higher structural reliability in conditional image editing than single-step models.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"CAMEO turns conditional image editing into a feedback-driven multi-agent process that raises win rates by 20 percent over single-step models.","strongest_claim":"CAMEO consistently achieves 20% more win rate on average compared to multiple state-of-the-art models, demonstrating improved robustness, controllability, and structural reliability in conditional image editing.","weakest_assumption":"That the multi-agent decomposition with embedded evaluation will reliably detect and correct structural and contextual inconsistencies without introducing new artifacts or requiring impractical computation, and that comparisons against independent evaluation models are unbiased and comprehensive."}},"verdict_id":"87c3743f-79f5-4fb7-a953-4acb23ffcb5b"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5c6cd658ef98010fa5c9feb53cb9ad251547cf613ab95e7eded0df0d18bed656","target":"record","created_at":"2026-06-19T16:11:22Z","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":"cdd56530fb30d21a3131bc0ab0966acd7c7790757f409c2e6534c0547ac466d9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-03T16:27:02Z","title_canon_sha256":"3c43939a444b0ab08c82942010c9148132e4c26bf361a2931d433c38b2881479"},"schema_version":"1.0","source":{"id":"2604.03156","kind":"arxiv","version":2}},"canonical_sha256":"f4dc04b48b49e04f19860c765f64daf7991dc664d542d6b7b095ab04913b2bcb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f4dc04b48b49e04f19860c765f64daf7991dc664d542d6b7b095ab04913b2bcb","first_computed_at":"2026-06-19T16:11:22.777263Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:11:22.777263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ayga5oX3eFiRf7XAwycsK3tJzG9bTnOT6DKUYc7xk+oeCkxV6jCEzGZIUxGAcAT/dF4WQMweRqifNZsvmdPCAA==","signature_status":"signed_v1","signed_at":"2026-06-19T16:11:22.777682Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.03156","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5c6cd658ef98010fa5c9feb53cb9ad251547cf613ab95e7eded0df0d18bed656","sha256:f9c40674f06667c6cb295f4ed3bd4dd613a330be76186c49cb1e43053241568f"],"state_sha256":"45a03b73acdd7d4278a19f476c5c3202adcb61d0f546f33e8cc74d6bbbb6af23"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5Dk/k/HjYWBZ7Lx8y3iFCmAKI6vuFgYC7wMaJ7giWs0FKr0332E3UB69AQHvd/AH0cZK4Qngz6F0B9zYnECqDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T00:08:12.962664Z","bundle_sha256":"b265a3f8771fe93c4da6600207ba2b06042c2c92d34c5feac3cc7ab55f60cc2c"}}