{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JYYMHYVW7SJVI75UGCLTNV7INZ","short_pith_number":"pith:JYYMHYVW","schema_version":"1.0","canonical_sha256":"4e30c3e2b6fc93547fb4309736d7e86e5670d86790eb385f7d66a54d3871f658","source":{"kind":"arxiv","id":"2605.28267","version":1},"attestation_state":"computed","paper":{"title":"Parameter-Efficient Generative Modeling with Controlled Vector Fields","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Peyman Morteza","submitted_at":"2026-05-27T10:14:29Z","abstract_excerpt":"We introduce a continuous-time generative modeling framework, motivated by the Chow-Rashevskii theorem, that builds expressive flows from a small set of fixed vector fields and learned scalar controls. Instead of learning an unconstrained high-dimensional vector field, our framework constructs the velocity by modulating fixed vector fields with learned scalar control functions. When the fixed fields are bracket-generating, their Lie algebra spans the ambient space, providing a mechanism for expressive transport with only a small number of learned control channels and offering a parameter-effic"},"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":"2605.28267","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T10:14:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"44ef75eece26136cb4062dd8b2add08b3b193c64b5665ad89d805c44e742e4c2","abstract_canon_sha256":"371e8a1e89f02e36019467c43afa2d2e2c102b7d7451ea585321e2c7b5734188"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:05:04.651676Z","signature_b64":"bOoYtRrTvCj8L58tu95s+lxasD10xHAVXsa9BBcye5+y1O50EpYtH4na6IE6RcEwAFRvPUGYOWgovcDH2/8OBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e30c3e2b6fc93547fb4309736d7e86e5670d86790eb385f7d66a54d3871f658","last_reissued_at":"2026-05-28T01:05:04.651226Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:05:04.651226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parameter-Efficient Generative Modeling with Controlled Vector Fields","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Peyman Morteza","submitted_at":"2026-05-27T10:14:29Z","abstract_excerpt":"We introduce a continuous-time generative modeling framework, motivated by the Chow-Rashevskii theorem, that builds expressive flows from a small set of fixed vector fields and learned scalar controls. Instead of learning an unconstrained high-dimensional vector field, our framework constructs the velocity by modulating fixed vector fields with learned scalar control functions. When the fixed fields are bracket-generating, their Lie algebra spans the ambient space, providing a mechanism for expressive transport with only a small number of learned control channels and offering a parameter-effic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28267","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/2605.28267/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":"2605.28267","created_at":"2026-05-28T01:05:04.651287+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28267v1","created_at":"2026-05-28T01:05:04.651287+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28267","created_at":"2026-05-28T01:05:04.651287+00:00"},{"alias_kind":"pith_short_12","alias_value":"JYYMHYVW7SJV","created_at":"2026-05-28T01:05:04.651287+00:00"},{"alias_kind":"pith_short_16","alias_value":"JYYMHYVW7SJVI75U","created_at":"2026-05-28T01:05:04.651287+00:00"},{"alias_kind":"pith_short_8","alias_value":"JYYMHYVW","created_at":"2026-05-28T01:05:04.651287+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/JYYMHYVW7SJVI75UGCLTNV7INZ","json":"https://pith.science/pith/JYYMHYVW7SJVI75UGCLTNV7INZ.json","graph_json":"https://pith.science/api/pith-number/JYYMHYVW7SJVI75UGCLTNV7INZ/graph.json","events_json":"https://pith.science/api/pith-number/JYYMHYVW7SJVI75UGCLTNV7INZ/events.json","paper":"https://pith.science/paper/JYYMHYVW"},"agent_actions":{"view_html":"https://pith.science/pith/JYYMHYVW7SJVI75UGCLTNV7INZ","download_json":"https://pith.science/pith/JYYMHYVW7SJVI75UGCLTNV7INZ.json","view_paper":"https://pith.science/paper/JYYMHYVW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28267&json=true","fetch_graph":"https://pith.science/api/pith-number/JYYMHYVW7SJVI75UGCLTNV7INZ/graph.json","fetch_events":"https://pith.science/api/pith-number/JYYMHYVW7SJVI75UGCLTNV7INZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JYYMHYVW7SJVI75UGCLTNV7INZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JYYMHYVW7SJVI75UGCLTNV7INZ/action/storage_attestation","attest_author":"https://pith.science/pith/JYYMHYVW7SJVI75UGCLTNV7INZ/action/author_attestation","sign_citation":"https://pith.science/pith/JYYMHYVW7SJVI75UGCLTNV7INZ/action/citation_signature","submit_replication":"https://pith.science/pith/JYYMHYVW7SJVI75UGCLTNV7INZ/action/replication_record"}},"created_at":"2026-05-28T01:05:04.651287+00:00","updated_at":"2026-05-28T01:05:04.651287+00:00"}