{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:76E3XFVKT57PQCSLUXHYIFJGLZ","short_pith_number":"pith:76E3XFVK","schema_version":"1.0","canonical_sha256":"ff89bb96aa9f7ef80a4ba5cf8415265e45f72d9be0767c73cc9a67f7f059c2a8","source":{"kind":"arxiv","id":"2606.27192","version":1},"attestation_state":"computed","paper":{"title":"LISA: Likelihood Score Alignment for Visual-condition Controllable Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongxu Chen, Jiazhen Liu, Long Chen, Rui Liu, Yanghao Wang, Zhenqi He, Zhen Wang","submitted_at":"2026-06-25T15:52:39Z","abstract_excerpt":"The prevalent dual-branch paradigm, i.e., training a side network to encode visual conditions and fusing its intermediate-layer features to a frozen pretrained main network, has shown remarkable success in visual-condition controllable generation. Despite its widespread adoption, the role of the side branch and its training efficiency remain underexplored. In this paper, we first revisit this mainstream paradigm through the lens of score-based generative modeling: 1) The main network preserves visual perceptual quality by providing a prior unconditional score. 2) The side network steers condit"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.27192","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-25T15:52:39Z","cross_cats_sorted":[],"title_canon_sha256":"0c53fd9b65e279b1cd1e970660d362dc6c1d983cd87013cd4d4198000c53331b","abstract_canon_sha256":"707e8f52aa77c443d30285c9563212f1e3bc79675a13ce879a10cbb9cc242cd2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:16:13.164509Z","signature_b64":"olxkGDvJuajJsxs61e+EuM4AnEkjS5Uj0oyhzIPpdrBAZ6YHDiv4HWo3Alxswkr3qgsvnCUEL0oZJrbfeTbuCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff89bb96aa9f7ef80a4ba5cf8415265e45f72d9be0767c73cc9a67f7f059c2a8","last_reissued_at":"2026-06-26T01:16:13.164154Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:16:13.164154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LISA: Likelihood Score Alignment for Visual-condition Controllable Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongxu Chen, Jiazhen Liu, Long Chen, Rui Liu, Yanghao Wang, Zhenqi He, Zhen Wang","submitted_at":"2026-06-25T15:52:39Z","abstract_excerpt":"The prevalent dual-branch paradigm, i.e., training a side network to encode visual conditions and fusing its intermediate-layer features to a frozen pretrained main network, has shown remarkable success in visual-condition controllable generation. Despite its widespread adoption, the role of the side branch and its training efficiency remain underexplored. In this paper, we first revisit this mainstream paradigm through the lens of score-based generative modeling: 1) The main network preserves visual perceptual quality by providing a prior unconditional score. 2) The side network steers condit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27192","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/2606.27192/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.27192","created_at":"2026-06-26T01:16:13.164207+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.27192v1","created_at":"2026-06-26T01:16:13.164207+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27192","created_at":"2026-06-26T01:16:13.164207+00:00"},{"alias_kind":"pith_short_12","alias_value":"76E3XFVKT57P","created_at":"2026-06-26T01:16:13.164207+00:00"},{"alias_kind":"pith_short_16","alias_value":"76E3XFVKT57PQCSL","created_at":"2026-06-26T01:16:13.164207+00:00"},{"alias_kind":"pith_short_8","alias_value":"76E3XFVK","created_at":"2026-06-26T01:16:13.164207+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.23041","citing_title":"SPAR: Semantic-Pixel Self-Alignment and Adaptive Routing for Unified Multimodal Models","ref_index":55,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/76E3XFVKT57PQCSLUXHYIFJGLZ","json":"https://pith.science/pith/76E3XFVKT57PQCSLUXHYIFJGLZ.json","graph_json":"https://pith.science/api/pith-number/76E3XFVKT57PQCSLUXHYIFJGLZ/graph.json","events_json":"https://pith.science/api/pith-number/76E3XFVKT57PQCSLUXHYIFJGLZ/events.json","paper":"https://pith.science/paper/76E3XFVK"},"agent_actions":{"view_html":"https://pith.science/pith/76E3XFVKT57PQCSLUXHYIFJGLZ","download_json":"https://pith.science/pith/76E3XFVKT57PQCSLUXHYIFJGLZ.json","view_paper":"https://pith.science/paper/76E3XFVK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.27192&json=true","fetch_graph":"https://pith.science/api/pith-number/76E3XFVKT57PQCSLUXHYIFJGLZ/graph.json","fetch_events":"https://pith.science/api/pith-number/76E3XFVKT57PQCSLUXHYIFJGLZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/76E3XFVKT57PQCSLUXHYIFJGLZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/76E3XFVKT57PQCSLUXHYIFJGLZ/action/storage_attestation","attest_author":"https://pith.science/pith/76E3XFVKT57PQCSLUXHYIFJGLZ/action/author_attestation","sign_citation":"https://pith.science/pith/76E3XFVKT57PQCSLUXHYIFJGLZ/action/citation_signature","submit_replication":"https://pith.science/pith/76E3XFVKT57PQCSLUXHYIFJGLZ/action/replication_record"}},"created_at":"2026-06-26T01:16:13.164207+00:00","updated_at":"2026-06-26T01:16:13.164207+00:00"}