{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GUK4JKAGNISNGJ2GE5IPHO5BWU","short_pith_number":"pith:GUK4JKAG","canonical_record":{"source":{"id":"2503.19312","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T03:18:46Z","cross_cats_sorted":[],"title_canon_sha256":"19950665b6f24c201066dc5a358f3e17ce3ea35e0856207850d95032b18424fb","abstract_canon_sha256":"44765dec9978ca7780e809cb38e66480f2c1be9788d438a672aa8c345919117d"},"schema_version":"1.0"},"canonical_sha256":"3515c4a8066a24d327462750f3bba1b51cc07756051c927c85d4954bfb0f12f9","source":{"kind":"arxiv","id":"2503.19312","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.19312","created_at":"2026-07-05T10:38:53Z"},{"alias_kind":"arxiv_version","alias_value":"2503.19312v1","created_at":"2026-07-05T10:38:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19312","created_at":"2026-07-05T10:38:53Z"},{"alias_kind":"pith_short_12","alias_value":"GUK4JKAGNISN","created_at":"2026-07-05T10:38:53Z"},{"alias_kind":"pith_short_16","alias_value":"GUK4JKAGNISNGJ2G","created_at":"2026-07-05T10:38:53Z"},{"alias_kind":"pith_short_8","alias_value":"GUK4JKAG","created_at":"2026-07-05T10:38:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GUK4JKAGNISNGJ2GE5IPHO5BWU","target":"record","payload":{"canonical_record":{"source":{"id":"2503.19312","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T03:18:46Z","cross_cats_sorted":[],"title_canon_sha256":"19950665b6f24c201066dc5a358f3e17ce3ea35e0856207850d95032b18424fb","abstract_canon_sha256":"44765dec9978ca7780e809cb38e66480f2c1be9788d438a672aa8c345919117d"},"schema_version":"1.0"},"canonical_sha256":"3515c4a8066a24d327462750f3bba1b51cc07756051c927c85d4954bfb0f12f9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:53.043519Z","signature_b64":"CmZEztc+7HhDd55EkrFavXcGPLG29vcCkaOSNuJosuo22HK4YL5cz/Q+2IQX3ax+c+W/kNgfGRQWtC66gFq0Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3515c4a8066a24d327462750f3bba1b51cc07756051c927c85d4954bfb0f12f9","last_reissued_at":"2026-07-05T10:38:53.043068Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:53.043068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.19312","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":"2026-07-05T10:38:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hfyupmN4zynyB28nqEcKBm0hFwUaR8TyW3sP1OzF9k7wb+Ax93ogaRtHkvJwhOS/xspBmSlGX0C4lZC1m3G2DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:34:39.029725Z"},"content_sha256":"86ed69b303b47c1edeee18a42ced24976db479e19e436990e28cc4f28b3a64ec","schema_version":"1.0","event_id":"sha256:86ed69b303b47c1edeee18a42ced24976db479e19e436990e28cc4f28b3a64ec"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GUK4JKAGNISNGJ2GE5IPHO5BWU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ImageGen-CoT: Enhancing Text-to-Image In-context Learning with Chain-of-Thought Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dianqi Li, Jiaqi Liao, Kevin Lin, Lijuan Wang, Linjie Li, Yu Cheng, Zhengyuan Yang","submitted_at":"2025-03-25T03:18:46Z","abstract_excerpt":"In this work, we study the problem of Text-to-Image In-Context Learning (T2I-ICL). While Unified Multimodal LLMs (MLLMs) have advanced rapidly in recent years, they struggle with contextual reasoning in T2I-ICL scenarios. To address this limitation, we propose a novel framework that incorporates a thought process called ImageGen-CoT prior to image generation. To avoid generating unstructured ineffective reasoning steps, we develop an automatic pipeline to curate a high-quality ImageGen-CoT dataset. We then fine-tune MLLMs using this dataset to enhance their contextual reasoning capabilities. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.19312","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/2503.19312/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":"2026-07-05T10:38:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bBU8erQy2A9Rn5CIdCHP+nqcnbBiIuIgAMZPeLmi/eloQYfeUHXi+ZzMrKvNraMUOcOImBReOlantDWr/5k+Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:34:39.030238Z"},"content_sha256":"2700a8e98de47758e5d57ed708ad3780d9b9a26c0723cfea2dbb3405f59c9735","schema_version":"1.0","event_id":"sha256:2700a8e98de47758e5d57ed708ad3780d9b9a26c0723cfea2dbb3405f59c9735"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GUK4JKAGNISNGJ2GE5IPHO5BWU/bundle.json","state_url":"https://pith.science/pith/GUK4JKAGNISNGJ2GE5IPHO5BWU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GUK4JKAGNISNGJ2GE5IPHO5BWU/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":"2026-08-03T22:34:39Z","links":{"resolver":"https://pith.science/pith/GUK4JKAGNISNGJ2GE5IPHO5BWU","bundle":"https://pith.science/pith/GUK4JKAGNISNGJ2GE5IPHO5BWU/bundle.json","state":"https://pith.science/pith/GUK4JKAGNISNGJ2GE5IPHO5BWU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GUK4JKAGNISNGJ2GE5IPHO5BWU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GUK4JKAGNISNGJ2GE5IPHO5BWU","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":"44765dec9978ca7780e809cb38e66480f2c1be9788d438a672aa8c345919117d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T03:18:46Z","title_canon_sha256":"19950665b6f24c201066dc5a358f3e17ce3ea35e0856207850d95032b18424fb"},"schema_version":"1.0","source":{"id":"2503.19312","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.19312","created_at":"2026-07-05T10:38:53Z"},{"alias_kind":"arxiv_version","alias_value":"2503.19312v1","created_at":"2026-07-05T10:38:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19312","created_at":"2026-07-05T10:38:53Z"},{"alias_kind":"pith_short_12","alias_value":"GUK4JKAGNISN","created_at":"2026-07-05T10:38:53Z"},{"alias_kind":"pith_short_16","alias_value":"GUK4JKAGNISNGJ2G","created_at":"2026-07-05T10:38:53Z"},{"alias_kind":"pith_short_8","alias_value":"GUK4JKAG","created_at":"2026-07-05T10:38:53Z"}],"graph_snapshots":[{"event_id":"sha256:2700a8e98de47758e5d57ed708ad3780d9b9a26c0723cfea2dbb3405f59c9735","target":"graph","created_at":"2026-07-05T10:38:53Z","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/2503.19312/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we study the problem of Text-to-Image In-Context Learning (T2I-ICL). While Unified Multimodal LLMs (MLLMs) have advanced rapidly in recent years, they struggle with contextual reasoning in T2I-ICL scenarios. To address this limitation, we propose a novel framework that incorporates a thought process called ImageGen-CoT prior to image generation. To avoid generating unstructured ineffective reasoning steps, we develop an automatic pipeline to curate a high-quality ImageGen-CoT dataset. We then fine-tune MLLMs using this dataset to enhance their contextual reasoning capabilities. T","authors_text":"Dianqi Li, Jiaqi Liao, Kevin Lin, Lijuan Wang, Linjie Li, Yu Cheng, Zhengyuan Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T03:18:46Z","title":"ImageGen-CoT: Enhancing Text-to-Image In-context Learning with Chain-of-Thought Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.19312","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":"sha256:86ed69b303b47c1edeee18a42ced24976db479e19e436990e28cc4f28b3a64ec","target":"record","created_at":"2026-07-05T10:38:53Z","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":"44765dec9978ca7780e809cb38e66480f2c1be9788d438a672aa8c345919117d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T03:18:46Z","title_canon_sha256":"19950665b6f24c201066dc5a358f3e17ce3ea35e0856207850d95032b18424fb"},"schema_version":"1.0","source":{"id":"2503.19312","kind":"arxiv","version":1}},"canonical_sha256":"3515c4a8066a24d327462750f3bba1b51cc07756051c927c85d4954bfb0f12f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3515c4a8066a24d327462750f3bba1b51cc07756051c927c85d4954bfb0f12f9","first_computed_at":"2026-07-05T10:38:53.043068Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:38:53.043068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CmZEztc+7HhDd55EkrFavXcGPLG29vcCkaOSNuJosuo22HK4YL5cz/Q+2IQX3ax+c+W/kNgfGRQWtC66gFq0Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:38:53.043519Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.19312","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86ed69b303b47c1edeee18a42ced24976db479e19e436990e28cc4f28b3a64ec","sha256:2700a8e98de47758e5d57ed708ad3780d9b9a26c0723cfea2dbb3405f59c9735"],"state_sha256":"b7d49035d0794e082d366fa7a0cd3eefeabc764d5e8ebf955218f7cd79b00e08"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m7AmAGSIALSqeMbwpFJcQCDMA6htCdjiRZTeBIH4UlZoo9fkh1wpSJBu8r232y5ooeMDV26Jz0+/aMzEFGn1Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T22:34:39.035642Z","bundle_sha256":"3997e7c5ff7a571aca4fd3e9febb487c09fe7f8bc1f60038fb35a44f0d39f6d3"}}