{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WYI4UJ5SK7JLQHKPY66QQLUIQ7","short_pith_number":"pith:WYI4UJ5S","schema_version":"1.0","canonical_sha256":"b611ca27b257d2b81d4fc7bd082e8887fd1cfc5c57d36a6a364d08d32aac5fed","source":{"kind":"arxiv","id":"2511.08583","version":2},"attestation_state":"computed","paper":{"title":"SeFA-Policy: Fast and Accurate Visuomotor Policy Learning with Selective Flow Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Jiageng Mao, Mingtong Zhang, Rong Xue, Yue Wang","submitted_at":"2025-11-11T18:59:39Z","abstract_excerpt":"Developing efficient and accurate visuomotor policies poses a central challenge in robotic imitation learning. While recent rectified flow approaches have advanced visuomotor policy learning, they suffer from a key limitation: After iterative distillation, generated actions may deviate from the ground-truth actions corresponding to the current visual observation, leading to accumulated error as the reflow process repeats and unstable task execution. We present Selective Flow Alignment (SeFA), an efficient and accurate visuomotor policy learning framework. SeFA resolves this challenge by a sele"},"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":"2511.08583","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-11-11T18:59:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d6107bf4880dc895a526453a8c6becb8c75987710d239524fdef7b534df70d8a","abstract_canon_sha256":"2916a24343c7d76106b99141b23ef0ca49ae5c945827fb6bde45fe064d1a31e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-10T01:18:56.337325Z","signature_b64":"QyEieabuPxnslWjVWW8opVr/a9fDllO0mFg/QSglVuv9yAMAnFxxBdBgWaQoTXAM05OaPEWi0C5+WEG+Scr5Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b611ca27b257d2b81d4fc7bd082e8887fd1cfc5c57d36a6a364d08d32aac5fed","last_reissued_at":"2026-07-10T01:18:56.336828Z","signature_status":"signed_v1","first_computed_at":"2026-07-10T01:18:56.336828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SeFA-Policy: Fast and Accurate Visuomotor Policy Learning with Selective Flow Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Jiageng Mao, Mingtong Zhang, Rong Xue, Yue Wang","submitted_at":"2025-11-11T18:59:39Z","abstract_excerpt":"Developing efficient and accurate visuomotor policies poses a central challenge in robotic imitation learning. While recent rectified flow approaches have advanced visuomotor policy learning, they suffer from a key limitation: After iterative distillation, generated actions may deviate from the ground-truth actions corresponding to the current visual observation, leading to accumulated error as the reflow process repeats and unstable task execution. We present Selective Flow Alignment (SeFA), an efficient and accurate visuomotor policy learning framework. SeFA resolves this challenge by a sele"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.08583","kind":"arxiv","version":2},"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/2511.08583/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":"2511.08583","created_at":"2026-07-10T01:18:56.336887+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.08583v2","created_at":"2026-07-10T01:18:56.336887+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.08583","created_at":"2026-07-10T01:18:56.336887+00:00"},{"alias_kind":"pith_short_12","alias_value":"WYI4UJ5SK7JL","created_at":"2026-07-10T01:18:56.336887+00:00"},{"alias_kind":"pith_short_16","alias_value":"WYI4UJ5SK7JLQHKP","created_at":"2026-07-10T01:18:56.336887+00:00"},{"alias_kind":"pith_short_8","alias_value":"WYI4UJ5S","created_at":"2026-07-10T01:18:56.336887+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/WYI4UJ5SK7JLQHKPY66QQLUIQ7","json":"https://pith.science/pith/WYI4UJ5SK7JLQHKPY66QQLUIQ7.json","graph_json":"https://pith.science/api/pith-number/WYI4UJ5SK7JLQHKPY66QQLUIQ7/graph.json","events_json":"https://pith.science/api/pith-number/WYI4UJ5SK7JLQHKPY66QQLUIQ7/events.json","paper":"https://pith.science/paper/WYI4UJ5S"},"agent_actions":{"view_html":"https://pith.science/pith/WYI4UJ5SK7JLQHKPY66QQLUIQ7","download_json":"https://pith.science/pith/WYI4UJ5SK7JLQHKPY66QQLUIQ7.json","view_paper":"https://pith.science/paper/WYI4UJ5S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.08583&json=true","fetch_graph":"https://pith.science/api/pith-number/WYI4UJ5SK7JLQHKPY66QQLUIQ7/graph.json","fetch_events":"https://pith.science/api/pith-number/WYI4UJ5SK7JLQHKPY66QQLUIQ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WYI4UJ5SK7JLQHKPY66QQLUIQ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WYI4UJ5SK7JLQHKPY66QQLUIQ7/action/storage_attestation","attest_author":"https://pith.science/pith/WYI4UJ5SK7JLQHKPY66QQLUIQ7/action/author_attestation","sign_citation":"https://pith.science/pith/WYI4UJ5SK7JLQHKPY66QQLUIQ7/action/citation_signature","submit_replication":"https://pith.science/pith/WYI4UJ5SK7JLQHKPY66QQLUIQ7/action/replication_record"}},"created_at":"2026-07-10T01:18:56.336887+00:00","updated_at":"2026-07-10T01:18:56.336887+00:00"}