{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:X3R5VFAUEJF2SEX5R4MOBAJXKH","short_pith_number":"pith:X3R5VFAU","schema_version":"1.0","canonical_sha256":"bee3da9414224ba912fd8f18e0813751eba16f963bbc63ff37129bcaff75381a","source":{"kind":"arxiv","id":"2402.04292","version":2},"attestation_state":"computed","paper":{"title":"AdaFlow: Imitation Learning with Variance-Adaptive Flow-Based Policies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bo Liu, Qiang Liu, Xingchao Liu, Xixi Hu","submitted_at":"2024-02-06T10:15:38Z","abstract_excerpt":"Diffusion-based imitation learning improves Behavioral Cloning (BC) on multi-modal decision-making, but comes at the cost of significantly slower inference due to the recursion in the diffusion process. It urges us to design efficient policy generators while keeping the ability to generate diverse actions. To address this challenge, we propose AdaFlow, an imitation learning framework based on flow-based generative modeling. AdaFlow represents the policy with state-conditioned ordinary differential equations (ODEs), which are known as probability flows. We reveal an intriguing connection betwee"},"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":"2402.04292","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-06T10:15:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"67b8804160e0833e3dc7854bd364b9ced4ceb159658586b19b6869ddb1f20e7f","abstract_canon_sha256":"0422da0c5f258dce4da9c4b955b59de5f49d76a92e6d986b02e72ed74c62f0fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:05.279517Z","signature_b64":"ahZdU7DTFtD4X/qvL45Yl7XIPlcLy6vOlRYxAPGH978fOfpQlKcEnqrRp846qT7F1/M+YnMm0IL24eG2GMvyCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bee3da9414224ba912fd8f18e0813751eba16f963bbc63ff37129bcaff75381a","last_reissued_at":"2026-07-05T09:39:05.278944Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:05.278944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AdaFlow: Imitation Learning with Variance-Adaptive Flow-Based Policies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bo Liu, Qiang Liu, Xingchao Liu, Xixi Hu","submitted_at":"2024-02-06T10:15:38Z","abstract_excerpt":"Diffusion-based imitation learning improves Behavioral Cloning (BC) on multi-modal decision-making, but comes at the cost of significantly slower inference due to the recursion in the diffusion process. It urges us to design efficient policy generators while keeping the ability to generate diverse actions. To address this challenge, we propose AdaFlow, an imitation learning framework based on flow-based generative modeling. AdaFlow represents the policy with state-conditioned ordinary differential equations (ODEs), which are known as probability flows. We reveal an intriguing connection betwee"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04292","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/2402.04292/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":"2402.04292","created_at":"2026-07-05T09:39:05.279009+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.04292v2","created_at":"2026-07-05T09:39:05.279009+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04292","created_at":"2026-07-05T09:39:05.279009+00:00"},{"alias_kind":"pith_short_12","alias_value":"X3R5VFAUEJF2","created_at":"2026-07-05T09:39:05.279009+00:00"},{"alias_kind":"pith_short_16","alias_value":"X3R5VFAUEJF2SEX5","created_at":"2026-07-05T09:39:05.279009+00:00"},{"alias_kind":"pith_short_8","alias_value":"X3R5VFAU","created_at":"2026-07-05T09:39:05.279009+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27724","citing_title":"HumanoidMimicGen: Data Generation for Loco-Manipulation via Whole-Body Planning","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14598","citing_title":"DSSP: Diffusion State Space Policy with Full-History Encoding","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13428","citing_title":"SID: Sliding into Distribution for Robust Few-Demonstration Manipulation","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2503.14734","citing_title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X3R5VFAUEJF2SEX5R4MOBAJXKH","json":"https://pith.science/pith/X3R5VFAUEJF2SEX5R4MOBAJXKH.json","graph_json":"https://pith.science/api/pith-number/X3R5VFAUEJF2SEX5R4MOBAJXKH/graph.json","events_json":"https://pith.science/api/pith-number/X3R5VFAUEJF2SEX5R4MOBAJXKH/events.json","paper":"https://pith.science/paper/X3R5VFAU"},"agent_actions":{"view_html":"https://pith.science/pith/X3R5VFAUEJF2SEX5R4MOBAJXKH","download_json":"https://pith.science/pith/X3R5VFAUEJF2SEX5R4MOBAJXKH.json","view_paper":"https://pith.science/paper/X3R5VFAU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.04292&json=true","fetch_graph":"https://pith.science/api/pith-number/X3R5VFAUEJF2SEX5R4MOBAJXKH/graph.json","fetch_events":"https://pith.science/api/pith-number/X3R5VFAUEJF2SEX5R4MOBAJXKH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X3R5VFAUEJF2SEX5R4MOBAJXKH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X3R5VFAUEJF2SEX5R4MOBAJXKH/action/storage_attestation","attest_author":"https://pith.science/pith/X3R5VFAUEJF2SEX5R4MOBAJXKH/action/author_attestation","sign_citation":"https://pith.science/pith/X3R5VFAUEJF2SEX5R4MOBAJXKH/action/citation_signature","submit_replication":"https://pith.science/pith/X3R5VFAUEJF2SEX5R4MOBAJXKH/action/replication_record"}},"created_at":"2026-07-05T09:39:05.279009+00:00","updated_at":"2026-07-05T09:39:05.279009+00:00"}