{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JP4GN6WR2H4HK2JEYMBDM2W7JL","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":"354cfba2220db73fe22bf3e76b365043fbef9ec456ed18ece6e21b9722bac2d5","cross_cats_sorted":["cs.AI","cs.GR","cs.HC","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-10T23:12:37Z","title_canon_sha256":"c802ad03716e6f3260d24a90dcef2626bcb68f2f1371aaab7f3fa8d320eb8edb"},"schema_version":"1.0","source":{"id":"2302.05543","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.05543","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"arxiv_version","alias_value":"2302.05543v3","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.05543","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"pith_short_12","alias_value":"JP4GN6WR2H4H","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"JP4GN6WR2H4HK2JE","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"JP4GN6WR","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:189b8270ccd33c2db502764a0ddaadeb55b0a48e2a044eb625a6d61fdb7491d8","target":"graph","created_at":"2026-05-17T23:38:46Z","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":"We present ControlNet, a neural network architecture to add spatial conditioning controls to large, pretrained text-to-image diffusion models. ControlNet locks the production-ready large diffusion models, and reuses their deep and robust encoding layers pretrained with billions of images as a strong backbone to learn a diverse set of conditional controls."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The zero convolutions progressively grow parameters from zero and ensure that no harmful noise could affect the finetuning, allowing the pretrained backbone to remain intact while learning new controls."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"ControlNet adds spatial conditioning controls to pretrained text-to-image diffusion models via zero convolutions for stable fine-tuning on small or large datasets."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"ControlNet adds spatial controls like edges, depth, and human poses to pretrained text-to-image diffusion models."}],"snapshot_sha256":"ceb25131b2b913ce597fef9e72bf1b4d5aeb174d0fbc78ad74f35388a5233deb"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"46cd962887c3ef1518d72b679115b5e163ec5ad7c99142f28815d4356d358d27"},"paper":{"abstract_excerpt":"We present ControlNet, a neural network architecture to add spatial conditioning controls to large, pretrained text-to-image diffusion models. ControlNet locks the production-ready large diffusion models, and reuses their deep and robust encoding layers pretrained with billions of images as a strong backbone to learn a diverse set of conditional controls. The neural architecture is connected with \"zero convolutions\" (zero-initialized convolution layers) that progressively grow the parameters from zero and ensure that no harmful noise could affect the finetuning. We test various conditioning co","authors_text":"Anyi Rao, Lvmin Zhang, Maneesh Agrawala","cross_cats":["cs.AI","cs.GR","cs.HC","cs.MM"],"headline":"ControlNet adds spatial controls like edges, depth, and human poses to pretrained text-to-image diffusion models.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-10T23:12:37Z","title":"Adding Conditional Control to Text-to-Image Diffusion Models"},"references":{"count":99,"internal_anchors":6,"resolved_work":99,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Weight initialization in neural network, inspired by andrew ng, https://medium.com/@safrin1128/weight- initialization-in-neural-network-inspired-by-andrew-ng- e0066dc4a566, 2020","work_id":"3f9ca0ba-f454-40c9-b7c4-a550dd074663","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"In- trinsic dimensionality explains the effectiveness of language model fine-tuning","work_id":"59996242-57e2-4905-a5ee-ddff83d2fc2f","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Only a matter of style: Age transformation using a style-based regression model","work_id":"f567145e-0ca7-4163-94d8-e24ef8c8b91a","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Hyperstyle: Stylegan inversion with hypernetworks for real image editing","work_id":"e058da51-899a-4555-b751-ec1e90b69a02","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Disco diffusion, https://github.com/alembics/disco- diffusion, 2022","work_id":"203b3fb8-4921-487f-9110-dda3201afe51","year":2022}],"snapshot_sha256":"0d6aa2f2d7e538e47c146e68c5e68fa5c1befbc4ff90b938d64e90da34937a3d"},"source":{"id":"2302.05543","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-16T22:38:53.240545Z","id":"c291990c-fe75-4b25-b563-e900c875fbcb","model_set":{"reader":"grok-4.3"},"one_line_summary":"ControlNet adds spatial conditioning controls to pretrained text-to-image diffusion models via zero convolutions for stable fine-tuning on small or large datasets.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"ControlNet adds spatial controls like edges, depth, and human poses to pretrained text-to-image diffusion models.","strongest_claim":"We present ControlNet, a neural network architecture to add spatial conditioning controls to large, pretrained text-to-image diffusion models. ControlNet locks the production-ready large diffusion models, and reuses their deep and robust encoding layers pretrained with billions of images as a strong backbone to learn a diverse set of conditional controls.","weakest_assumption":"The zero convolutions progressively grow parameters from zero and ensure that no harmful noise could affect the finetuning, allowing the pretrained backbone to remain intact while learning new controls."}},"verdict_id":"c291990c-fe75-4b25-b563-e900c875fbcb"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ba4512957835e450df28e438112b483dfb30bbfba11368e7caceec6a8275906a","target":"record","created_at":"2026-05-17T23:38:46Z","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":"354cfba2220db73fe22bf3e76b365043fbef9ec456ed18ece6e21b9722bac2d5","cross_cats_sorted":["cs.AI","cs.GR","cs.HC","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-10T23:12:37Z","title_canon_sha256":"c802ad03716e6f3260d24a90dcef2626bcb68f2f1371aaab7f3fa8d320eb8edb"},"schema_version":"1.0","source":{"id":"2302.05543","kind":"arxiv","version":3}},"canonical_sha256":"4bf866fad1d1f8756924c302366adf4ad0805b0a40be1eb3b7ca51069681aa14","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4bf866fad1d1f8756924c302366adf4ad0805b0a40be1eb3b7ca51069681aa14","first_computed_at":"2026-05-17T23:38:46.350422Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:46.350422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H1q84TvsDCzvljbeHt4Mphtqe1IQXW2d00eFe2vBtBvQhOzi9XE5b2BqSy8yeQvVvRtE4nJ8ANR5oXgD5qbdDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:46.351011Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.05543","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba4512957835e450df28e438112b483dfb30bbfba11368e7caceec6a8275906a","sha256:189b8270ccd33c2db502764a0ddaadeb55b0a48e2a044eb625a6d61fdb7491d8"],"state_sha256":"e55bd4e05a4fbfee1b4250beb13ec9691020dec5c9a5ee24e8160dc03ed762b5"}