{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WPUBCVUOXSGVS4IKMHWFHO6ILI","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":"9903a51cd98d2fe47e0706171f1dd8d53f8e33a5bf23b2be418e43ec3bdb644a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-03T05:25:53Z","title_canon_sha256":"98e9b9aa6e78cd52536c9d1b1572893530eb7bc8ad6fcab8c4500f6a7401784d"},"schema_version":"1.0","source":{"id":"2507.02321","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.02321","created_at":"2026-07-05T11:31:15Z"},{"alias_kind":"arxiv_version","alias_value":"2507.02321v1","created_at":"2026-07-05T11:31:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02321","created_at":"2026-07-05T11:31:15Z"},{"alias_kind":"pith_short_12","alias_value":"WPUBCVUOXSGV","created_at":"2026-07-05T11:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"WPUBCVUOXSGVS4IK","created_at":"2026-07-05T11:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"WPUBCVUO","created_at":"2026-07-05T11:31:15Z"}],"graph_snapshots":[{"event_id":"sha256:dbf6cdf9a85287e5191ae81af79cd2969701f85e2fc983080f6038b6a2799f28","target":"graph","created_at":"2026-07-05T11:31:15Z","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/2507.02321/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite significant progress in text-to-image diffusion models, achieving precise spatial control over generated outputs remains challenging. ControlNet addresses this by introducing an auxiliary conditioning module, while ControlNet++ further refines alignment through a cycle consistency loss applied only to the final denoising steps. However, this approach neglects intermediate generation stages, limiting its effectiveness. We propose InnerControl, a training strategy that enforces spatial consistency across all diffusion steps. Our method trains lightweight convolutional probes to reconstru","authors_text":"Aibek Alanov, Andrey Kuznetsov, Maxim Nikolaev, Nina Konovalova","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-03T05:25:53Z","title":"Heeding the Inner Voice: Aligning ControlNet Training via Intermediate Features Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02321","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":"sha256:030178c2cf65742041744be9165dc2e2abbe63c84873cb7caceb52cf00045361","target":"record","created_at":"2026-07-05T11:31:15Z","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":"9903a51cd98d2fe47e0706171f1dd8d53f8e33a5bf23b2be418e43ec3bdb644a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-03T05:25:53Z","title_canon_sha256":"98e9b9aa6e78cd52536c9d1b1572893530eb7bc8ad6fcab8c4500f6a7401784d"},"schema_version":"1.0","source":{"id":"2507.02321","kind":"arxiv","version":1}},"canonical_sha256":"b3e811568ebc8d59710a61ec53bbc85a07f3ae7f8f2207e6a21d1aa499bac994","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b3e811568ebc8d59710a61ec53bbc85a07f3ae7f8f2207e6a21d1aa499bac994","first_computed_at":"2026-07-05T11:31:15.987548Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:31:15.987548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"emTRmborx2aexV4SYHiDdceZeHNIkLusyQkLgxQG2m4qLoRya74gHqT29MdEia4DHuJPOO9AKa0FQReUjpC5AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:31:15.987960Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.02321","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:030178c2cf65742041744be9165dc2e2abbe63c84873cb7caceb52cf00045361","sha256:dbf6cdf9a85287e5191ae81af79cd2969701f85e2fc983080f6038b6a2799f28"],"state_sha256":"f38df158bb6b4110878f4dcce984728304ea20ec1dc3cb00028bd04ab507e5ac"}