{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:AEKKJVUQRRMZIGOOCP2VA3KZUU","short_pith_number":"pith:AEKKJVUQ","canonical_record":{"source":{"id":"2406.04337","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-06T17:59:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7b517d3945350ff53b649abf7cfa6e547dd4aa4e849f8db9c5132dfea372c650","abstract_canon_sha256":"d75d49613b1ff931da458421346743e6daacc242972a177070d7df11ec0c4649"},"schema_version":"1.0"},"canonical_sha256":"0114a4d6908c599419ce13f5506d59a520625abff4afd2328472ec3f3f76719c","source":{"kind":"arxiv","id":"2406.04337","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04337","created_at":"2026-07-05T08:29:01Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04337v2","created_at":"2026-07-05T08:29:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04337","created_at":"2026-07-05T08:29:01Z"},{"alias_kind":"pith_short_12","alias_value":"AEKKJVUQRRMZ","created_at":"2026-07-05T08:29:01Z"},{"alias_kind":"pith_short_16","alias_value":"AEKKJVUQRRMZIGOO","created_at":"2026-07-05T08:29:01Z"},{"alias_kind":"pith_short_8","alias_value":"AEKKJVUQ","created_at":"2026-07-05T08:29:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:AEKKJVUQRRMZIGOOCP2VA3KZUU","target":"record","payload":{"canonical_record":{"source":{"id":"2406.04337","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-06T17:59:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7b517d3945350ff53b649abf7cfa6e547dd4aa4e849f8db9c5132dfea372c650","abstract_canon_sha256":"d75d49613b1ff931da458421346743e6daacc242972a177070d7df11ec0c4649"},"schema_version":"1.0"},"canonical_sha256":"0114a4d6908c599419ce13f5506d59a520625abff4afd2328472ec3f3f76719c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:01.389151Z","signature_b64":"grGvYzuHqefy2HonVZ5GBTOj6uws8pailOQjyOLEZXTXRufbQavmaMQnTrw7iYKFMTne3ooPL+XhK9GktAF3Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0114a4d6908c599419ce13f5506d59a520625abff4afd2328472ec3f3f76719c","last_reissued_at":"2026-07-05T08:29:01.388671Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:01.388671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.04337","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":"2026-07-05T08:29:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JrkL9hnGvAycMo++ELInnWSEhv003G/67qH3HcNPCrLyxZhdVOCkogmJ6MannoCYTMCBGVqfPbB82BCkwlGPDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T17:21:06.410300Z"},"content_sha256":"0d3a5bbbf1791a0b893f2602f8e32aebdb1d050765cb00356210948233494e0a","schema_version":"1.0","event_id":"sha256:0d3a5bbbf1791a0b893f2602f8e32aebdb1d050765cb00356210948233494e0a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:AEKKJVUQRRMZIGOOCP2VA3KZUU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Coherent Zero-Shot Visual Instruction Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jia-Bin Huang, Quynh Phung, Songwei Ge","submitted_at":"2024-06-06T17:59:44Z","abstract_excerpt":"Despite the advances in text-to-image synthesis, particularly with diffusion models, generating visual instructions that require consistent representation and smooth state transitions of objects across sequential steps remains a formidable challenge. This paper introduces a simple, training-free framework to tackle the issues, capitalizing on the advancements in diffusion models and large language models (LLMs). Our approach systematically integrates text comprehension and image generation to ensure visual instructions are visually appealing and maintain consistency and accuracy throughout the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04337","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/2406.04337/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":"2026-07-05T08:29:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jTSC/ACYx2BpqgDiqvcODlxZWU1WOEtvd53N7dJjUNabeNuJlSwAd/dyDC0M2TAt4LQv2Nk/8JTPfHmxc3DNAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T17:21:06.411215Z"},"content_sha256":"fa8e051239bd0e828341ddd06198c988a6c9fda3e41366b6b3d5c0d5fdf864b0","schema_version":"1.0","event_id":"sha256:fa8e051239bd0e828341ddd06198c988a6c9fda3e41366b6b3d5c0d5fdf864b0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AEKKJVUQRRMZIGOOCP2VA3KZUU/bundle.json","state_url":"https://pith.science/pith/AEKKJVUQRRMZIGOOCP2VA3KZUU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AEKKJVUQRRMZIGOOCP2VA3KZUU/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":"2026-08-13T17:21:06Z","links":{"resolver":"https://pith.science/pith/AEKKJVUQRRMZIGOOCP2VA3KZUU","bundle":"https://pith.science/pith/AEKKJVUQRRMZIGOOCP2VA3KZUU/bundle.json","state":"https://pith.science/pith/AEKKJVUQRRMZIGOOCP2VA3KZUU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AEKKJVUQRRMZIGOOCP2VA3KZUU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AEKKJVUQRRMZIGOOCP2VA3KZUU","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":"d75d49613b1ff931da458421346743e6daacc242972a177070d7df11ec0c4649","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-06T17:59:44Z","title_canon_sha256":"7b517d3945350ff53b649abf7cfa6e547dd4aa4e849f8db9c5132dfea372c650"},"schema_version":"1.0","source":{"id":"2406.04337","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04337","created_at":"2026-07-05T08:29:01Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04337v2","created_at":"2026-07-05T08:29:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04337","created_at":"2026-07-05T08:29:01Z"},{"alias_kind":"pith_short_12","alias_value":"AEKKJVUQRRMZ","created_at":"2026-07-05T08:29:01Z"},{"alias_kind":"pith_short_16","alias_value":"AEKKJVUQRRMZIGOO","created_at":"2026-07-05T08:29:01Z"},{"alias_kind":"pith_short_8","alias_value":"AEKKJVUQ","created_at":"2026-07-05T08:29:01Z"}],"graph_snapshots":[{"event_id":"sha256:fa8e051239bd0e828341ddd06198c988a6c9fda3e41366b6b3d5c0d5fdf864b0","target":"graph","created_at":"2026-07-05T08:29:01Z","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/2406.04337/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the advances in text-to-image synthesis, particularly with diffusion models, generating visual instructions that require consistent representation and smooth state transitions of objects across sequential steps remains a formidable challenge. This paper introduces a simple, training-free framework to tackle the issues, capitalizing on the advancements in diffusion models and large language models (LLMs). Our approach systematically integrates text comprehension and image generation to ensure visual instructions are visually appealing and maintain consistency and accuracy throughout the","authors_text":"Jia-Bin Huang, Quynh Phung, Songwei Ge","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-06T17:59:44Z","title":"Coherent Zero-Shot Visual Instruction Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04337","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":"sha256:0d3a5bbbf1791a0b893f2602f8e32aebdb1d050765cb00356210948233494e0a","target":"record","created_at":"2026-07-05T08:29:01Z","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":"d75d49613b1ff931da458421346743e6daacc242972a177070d7df11ec0c4649","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-06T17:59:44Z","title_canon_sha256":"7b517d3945350ff53b649abf7cfa6e547dd4aa4e849f8db9c5132dfea372c650"},"schema_version":"1.0","source":{"id":"2406.04337","kind":"arxiv","version":2}},"canonical_sha256":"0114a4d6908c599419ce13f5506d59a520625abff4afd2328472ec3f3f76719c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0114a4d6908c599419ce13f5506d59a520625abff4afd2328472ec3f3f76719c","first_computed_at":"2026-07-05T08:29:01.388671Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:29:01.388671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"grGvYzuHqefy2HonVZ5GBTOj6uws8pailOQjyOLEZXTXRufbQavmaMQnTrw7iYKFMTne3ooPL+XhK9GktAF3Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:29:01.389151Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.04337","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0d3a5bbbf1791a0b893f2602f8e32aebdb1d050765cb00356210948233494e0a","sha256:fa8e051239bd0e828341ddd06198c988a6c9fda3e41366b6b3d5c0d5fdf864b0"],"state_sha256":"88cbaf5f88ae21434bdf2c2cfcd03080ae110d36be6dcd6b82978da9f7797197"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iAkCHbN+yY454D404di1pHG9HWojiwbnL1Qx2CIfZmDYOIa95ox4BGMSTPByIs5bL2344tcQMcN9bnj9AegrCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T17:21:06.424590Z","bundle_sha256":"2d74263f9fca03fdec031913f51011a48df45843880db7ccdd090a9f6e404b6f"}}