{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LHZARPLUMWABAQQ3S5DL4J7JX3","short_pith_number":"pith:LHZARPLU","schema_version":"1.0","canonical_sha256":"59f208bd74658010421b9746be27e9beedd78ca8c3a8e700399c932b0c9d62fc","source":{"kind":"arxiv","id":"2605.16603","version":1},"attestation_state":"computed","paper":{"title":"Controlla: Learning Controllability via Graph-Constrained Latent Geometry","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amin Karimi Monsefi, Jamuna S. Murthy, Rajiv Ramnath","submitted_at":"2026-05-15T20:06:02Z","abstract_excerpt":"Controllable multimodal generation is commonly formulated as an inference-time conditioning problem using prompts, guidance, or auxiliary modules. While effective, such approaches do not explicitly structure how semantic attributes evolve, which can lead to identity drift and inconsistent cross-modal behavior. We propose Controlla, a modular factorized-control framework that treats controllability as a property of structured latent geometry. Controlla learns identity and attribute factors from multimodal inputs and aligns them with graph priors using graph-constrained optimal transport, encour"},"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":"2605.16603","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-15T20:06:02Z","cross_cats_sorted":[],"title_canon_sha256":"2f92292032bea41651bf7562c7a8d00f151841412bf7a1a5d2b19e65e4fca341","abstract_canon_sha256":"139a19954ddba4cd72277ba5fa4ab36fe11ddede224ffebd5a7ca9be53aee5a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:32.023971Z","signature_b64":"xszI4uQ/p3avTgLO0M5pQWkZQ77Slh3Zu45KNPv5JxI6aFN0fCYzIeayS4VoNr9a5usOt0DQTKgdO2CeZAwMBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59f208bd74658010421b9746be27e9beedd78ca8c3a8e700399c932b0c9d62fc","last_reissued_at":"2026-05-20T00:02:32.023101Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:32.023101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Controlla: Learning Controllability via Graph-Constrained Latent Geometry","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amin Karimi Monsefi, Jamuna S. Murthy, Rajiv Ramnath","submitted_at":"2026-05-15T20:06:02Z","abstract_excerpt":"Controllable multimodal generation is commonly formulated as an inference-time conditioning problem using prompts, guidance, or auxiliary modules. While effective, such approaches do not explicitly structure how semantic attributes evolve, which can lead to identity drift and inconsistent cross-modal behavior. We propose Controlla, a modular factorized-control framework that treats controllability as a property of structured latent geometry. Controlla learns identity and attribute factors from multimodal inputs and aligns them with graph priors using graph-constrained optimal transport, encour"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16603","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/2605.16603/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-19T19:21:56.809467Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.599615Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"54603b1759eed644901a03c1bbd4bdd5b059505f79533bd450583918866bf00b"},"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":"2605.16603","created_at":"2026-05-20T00:02:32.023238+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.16603v1","created_at":"2026-05-20T00:02:32.023238+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16603","created_at":"2026-05-20T00:02:32.023238+00:00"},{"alias_kind":"pith_short_12","alias_value":"LHZARPLUMWAB","created_at":"2026-05-20T00:02:32.023238+00:00"},{"alias_kind":"pith_short_16","alias_value":"LHZARPLUMWABAQQ3","created_at":"2026-05-20T00:02:32.023238+00:00"},{"alias_kind":"pith_short_8","alias_value":"LHZARPLU","created_at":"2026-05-20T00:02:32.023238+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LHZARPLUMWABAQQ3S5DL4J7JX3","json":"https://pith.science/pith/LHZARPLUMWABAQQ3S5DL4J7JX3.json","graph_json":"https://pith.science/api/pith-number/LHZARPLUMWABAQQ3S5DL4J7JX3/graph.json","events_json":"https://pith.science/api/pith-number/LHZARPLUMWABAQQ3S5DL4J7JX3/events.json","paper":"https://pith.science/paper/LHZARPLU"},"agent_actions":{"view_html":"https://pith.science/pith/LHZARPLUMWABAQQ3S5DL4J7JX3","download_json":"https://pith.science/pith/LHZARPLUMWABAQQ3S5DL4J7JX3.json","view_paper":"https://pith.science/paper/LHZARPLU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.16603&json=true","fetch_graph":"https://pith.science/api/pith-number/LHZARPLUMWABAQQ3S5DL4J7JX3/graph.json","fetch_events":"https://pith.science/api/pith-number/LHZARPLUMWABAQQ3S5DL4J7JX3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LHZARPLUMWABAQQ3S5DL4J7JX3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LHZARPLUMWABAQQ3S5DL4J7JX3/action/storage_attestation","attest_author":"https://pith.science/pith/LHZARPLUMWABAQQ3S5DL4J7JX3/action/author_attestation","sign_citation":"https://pith.science/pith/LHZARPLUMWABAQQ3S5DL4J7JX3/action/citation_signature","submit_replication":"https://pith.science/pith/LHZARPLUMWABAQQ3S5DL4J7JX3/action/replication_record"}},"created_at":"2026-05-20T00:02:32.023238+00:00","updated_at":"2026-05-20T00:02:32.023238+00:00"}