{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JXRU7YJY4IWIOWCUW4BYQWQNP6","short_pith_number":"pith:JXRU7YJY","schema_version":"1.0","canonical_sha256":"4de34fe138e22c875854b703885a0d7f84881a8c16c36740da9c76a978e73593","source":{"kind":"arxiv","id":"2607.08877","version":1},"attestation_state":"computed","paper":{"title":"FlowDAgger: Human-in-the-Loop Adaptation of Generative Robot Policies in Latent Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Andrey Kolobov, Daphne Chen, Dean Fortier, Galen Mullins, Harshavardhan Gajarla, Maya Cakmak, Michael Murray, Oier Mees, Simran Bagaria, Tess Hellebrekers","submitted_at":"2026-07-09T19:07:33Z","abstract_excerpt":"Pretrained generative robot policies based on flow matching and diffusion have achieved impressive results across a wide range of manipulation tasks. Yet real-world deployments routinely expose failure modes outside the pretraining distribution. Closing these gaps typically requires large-scale data collection or online reinforcement learning on physical hardware, which is impractical for rapid and safe adaptation. We present FlowDAgger, a sample- and compute-efficient method for adapting frozen generative robot policies from human interventions in latent space. Our key idea is action inversio"},"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":"2607.08877","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-09T19:07:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"06b2a2527dbc554b52ff87f8925c616da975c22a99b33fa7a8a07a9ab46ffdd0","abstract_canon_sha256":"bc4ea1864da9080457a65f8c4d5e99903b74f59d816e39696b55106f72355b7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-13T00:17:24.092733Z","signature_b64":"3Pcs6yZFxMZXN3NlaTYJ9xFdHCZE485hZLokPrKjCyWAh2a9JXZ9HAba07mQWvzLK9xqL9npYUMGW/2XsCHGAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4de34fe138e22c875854b703885a0d7f84881a8c16c36740da9c76a978e73593","last_reissued_at":"2026-07-13T00:17:24.091671Z","signature_status":"signed_v1","first_computed_at":"2026-07-13T00:17:24.091671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FlowDAgger: Human-in-the-Loop Adaptation of Generative Robot Policies in Latent Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Andrey Kolobov, Daphne Chen, Dean Fortier, Galen Mullins, Harshavardhan Gajarla, Maya Cakmak, Michael Murray, Oier Mees, Simran Bagaria, Tess Hellebrekers","submitted_at":"2026-07-09T19:07:33Z","abstract_excerpt":"Pretrained generative robot policies based on flow matching and diffusion have achieved impressive results across a wide range of manipulation tasks. Yet real-world deployments routinely expose failure modes outside the pretraining distribution. Closing these gaps typically requires large-scale data collection or online reinforcement learning on physical hardware, which is impractical for rapid and safe adaptation. We present FlowDAgger, a sample- and compute-efficient method for adapting frozen generative robot policies from human interventions in latent space. Our key idea is action inversio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08877","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/2607.08877/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":"2607.08877","created_at":"2026-07-13T00:17:24.092215+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.08877v1","created_at":"2026-07-13T00:17:24.092215+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08877","created_at":"2026-07-13T00:17:24.092215+00:00"},{"alias_kind":"pith_short_12","alias_value":"JXRU7YJY4IWI","created_at":"2026-07-13T00:17:24.092215+00:00"},{"alias_kind":"pith_short_16","alias_value":"JXRU7YJY4IWIOWCU","created_at":"2026-07-13T00:17:24.092215+00:00"},{"alias_kind":"pith_short_8","alias_value":"JXRU7YJY","created_at":"2026-07-13T00:17:24.092215+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/JXRU7YJY4IWIOWCUW4BYQWQNP6","json":"https://pith.science/pith/JXRU7YJY4IWIOWCUW4BYQWQNP6.json","graph_json":"https://pith.science/api/pith-number/JXRU7YJY4IWIOWCUW4BYQWQNP6/graph.json","events_json":"https://pith.science/api/pith-number/JXRU7YJY4IWIOWCUW4BYQWQNP6/events.json","paper":"https://pith.science/paper/JXRU7YJY"},"agent_actions":{"view_html":"https://pith.science/pith/JXRU7YJY4IWIOWCUW4BYQWQNP6","download_json":"https://pith.science/pith/JXRU7YJY4IWIOWCUW4BYQWQNP6.json","view_paper":"https://pith.science/paper/JXRU7YJY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.08877&json=true","fetch_graph":"https://pith.science/api/pith-number/JXRU7YJY4IWIOWCUW4BYQWQNP6/graph.json","fetch_events":"https://pith.science/api/pith-number/JXRU7YJY4IWIOWCUW4BYQWQNP6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JXRU7YJY4IWIOWCUW4BYQWQNP6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JXRU7YJY4IWIOWCUW4BYQWQNP6/action/storage_attestation","attest_author":"https://pith.science/pith/JXRU7YJY4IWIOWCUW4BYQWQNP6/action/author_attestation","sign_citation":"https://pith.science/pith/JXRU7YJY4IWIOWCUW4BYQWQNP6/action/citation_signature","submit_replication":"https://pith.science/pith/JXRU7YJY4IWIOWCUW4BYQWQNP6/action/replication_record"}},"created_at":"2026-07-13T00:17:24.092215+00:00","updated_at":"2026-07-13T00:17:24.092215+00:00"}