{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DESQCT66EMCTJS746HRPZAEGCL","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":"18410990e69ba400af5e54fcf7c37fb3dc19cc6d0cf9f3c27e2f2a3ef0c1d2d5","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-03T19:31:58Z","title_canon_sha256":"29923ab2748b2bb52d19119cfe339c3b9985b99b01d9ced5f470027fbb5aa5a0"},"schema_version":"1.0","source":{"id":"2401.01952","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.01952","created_at":"2026-07-05T07:30:08Z"},{"alias_kind":"arxiv_version","alias_value":"2401.01952v1","created_at":"2026-07-05T07:30:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.01952","created_at":"2026-07-05T07:30:08Z"},{"alias_kind":"pith_short_12","alias_value":"DESQCT66EMCT","created_at":"2026-07-05T07:30:08Z"},{"alias_kind":"pith_short_16","alias_value":"DESQCT66EMCTJS74","created_at":"2026-07-05T07:30:08Z"},{"alias_kind":"pith_short_8","alias_value":"DESQCT66","created_at":"2026-07-05T07:30:08Z"}],"graph_snapshots":[{"event_id":"sha256:bbcd138226b5a0efc651f457272133180d65a8a9db9d9fa7a12929e137e93c25","target":"graph","created_at":"2026-07-05T07:30:08Z","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/2401.01952/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents instruct-imagen, a model that tackles heterogeneous image generation tasks and generalizes across unseen tasks. We introduce *multi-modal instruction* for image generation, a task representation articulating a range of generation intents with precision. It uses natural language to amalgamate disparate modalities (e.g., text, edge, style, subject, etc.), such that abundant generation intents can be standardized in a uniform format.\n  We then build instruct-imagen by fine-tuning a pre-trained text-to-image diffusion model with a two-stage framework. First, we adapt the model ","authors_text":"Boqing Gong, Hexiang Hu, Kelvin C.K. Chan, Kihyuk Sohn, Ming-Wei Chang, Wenhu Chen, William Cohen, Xue Ben, Xuhui Jia, Yandong Li, Yang Zhao, Yu-Chuan Su","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-03T19:31:58Z","title":"Instruct-Imagen: Image Generation with Multi-modal Instruction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.01952","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:a8d07572f4e36008956c6e604dda77b7170d5be34cb1c1d87353aef252d1079d","target":"record","created_at":"2026-07-05T07:30:08Z","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":"18410990e69ba400af5e54fcf7c37fb3dc19cc6d0cf9f3c27e2f2a3ef0c1d2d5","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-03T19:31:58Z","title_canon_sha256":"29923ab2748b2bb52d19119cfe339c3b9985b99b01d9ced5f470027fbb5aa5a0"},"schema_version":"1.0","source":{"id":"2401.01952","kind":"arxiv","version":1}},"canonical_sha256":"1925014fde230534cbfcf1e2fc808612f0d2ef4f698f1dae8bfce9ee80b15cf4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1925014fde230534cbfcf1e2fc808612f0d2ef4f698f1dae8bfce9ee80b15cf4","first_computed_at":"2026-07-05T07:30:08.622008Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:30:08.622008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3voO+4QLxNu5H0XGnf91AsWTJmHL8N5xhcuMBe+85Mv3Up6iEBqA5zBJCvRPKXok1pElVoX/XVMmM2+FGVlMDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:30:08.622504Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.01952","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a8d07572f4e36008956c6e604dda77b7170d5be34cb1c1d87353aef252d1079d","sha256:bbcd138226b5a0efc651f457272133180d65a8a9db9d9fa7a12929e137e93c25"],"state_sha256":"179c9aafca713e29b049ad3472a7c7bfae3bb5885da54ffa4905ea26068eb0d1"}