{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RXQIGNLNOIR6KZYSAQ3IVQLYKS","short_pith_number":"pith:RXQIGNLN","schema_version":"1.0","canonical_sha256":"8de083356d7223e5671204368ac17854b6db62c5afb0f17ecd482c3b06fbd707","source":{"kind":"arxiv","id":"2606.09381","version":1},"attestation_state":"computed","paper":{"title":"ReGIL: Retrieval-Guided Imitation Learning from a Single Demonstration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Francesco Verdoja, Ville Kyrki, Wenyan Yang, Yuying Zhang","submitted_at":"2026-06-08T11:57:17Z","abstract_excerpt":"Learning robot manipulation policies with deep neural networks from a single demonstration remains highly challenging, as even small deviations from the demonstrated trajectory can quickly compound into failure, while collecting substantial online interaction data is costly. We propose ReGIL, a retrieval-guided imitation learning framework that treats a single demonstration as an external memory. ReGIL repeatedly queries this static memory throughout training to simultaneously guide exploration, generate the regularization buffer, and construct rewards. Specifically, it computes rewards throug"},"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":"2606.09381","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-08T11:57:17Z","cross_cats_sorted":[],"title_canon_sha256":"5be944c75176fe5e5ea6d4a5d5c775d3858cb2a8734a1ec745efc9ea090e1d83","abstract_canon_sha256":"c9dc56473c733b2451b39233459af7a1aba5d131160aa55e8d479d9b5a4b5f59"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:08:18.936894Z","signature_b64":"lj2qFZ8a5gCcF7LuEzFmNfqT4KP7gp/A14YnlxcEHQAGxK43b2DEqnsyI+VzG/qxI4CEno0XWSF5n0hAe3QEBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8de083356d7223e5671204368ac17854b6db62c5afb0f17ecd482c3b06fbd707","last_reissued_at":"2026-06-09T02:08:18.935632Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:08:18.935632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReGIL: Retrieval-Guided Imitation Learning from a Single Demonstration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Francesco Verdoja, Ville Kyrki, Wenyan Yang, Yuying Zhang","submitted_at":"2026-06-08T11:57:17Z","abstract_excerpt":"Learning robot manipulation policies with deep neural networks from a single demonstration remains highly challenging, as even small deviations from the demonstrated trajectory can quickly compound into failure, while collecting substantial online interaction data is costly. We propose ReGIL, a retrieval-guided imitation learning framework that treats a single demonstration as an external memory. ReGIL repeatedly queries this static memory throughout training to simultaneously guide exploration, generate the regularization buffer, and construct rewards. Specifically, it computes rewards throug"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09381","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/2606.09381/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":"2606.09381","created_at":"2026-06-09T02:08:18.935861+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09381v1","created_at":"2026-06-09T02:08:18.935861+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09381","created_at":"2026-06-09T02:08:18.935861+00:00"},{"alias_kind":"pith_short_12","alias_value":"RXQIGNLNOIR6","created_at":"2026-06-09T02:08:18.935861+00:00"},{"alias_kind":"pith_short_16","alias_value":"RXQIGNLNOIR6KZYS","created_at":"2026-06-09T02:08:18.935861+00:00"},{"alias_kind":"pith_short_8","alias_value":"RXQIGNLN","created_at":"2026-06-09T02:08:18.935861+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/RXQIGNLNOIR6KZYSAQ3IVQLYKS","json":"https://pith.science/pith/RXQIGNLNOIR6KZYSAQ3IVQLYKS.json","graph_json":"https://pith.science/api/pith-number/RXQIGNLNOIR6KZYSAQ3IVQLYKS/graph.json","events_json":"https://pith.science/api/pith-number/RXQIGNLNOIR6KZYSAQ3IVQLYKS/events.json","paper":"https://pith.science/paper/RXQIGNLN"},"agent_actions":{"view_html":"https://pith.science/pith/RXQIGNLNOIR6KZYSAQ3IVQLYKS","download_json":"https://pith.science/pith/RXQIGNLNOIR6KZYSAQ3IVQLYKS.json","view_paper":"https://pith.science/paper/RXQIGNLN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09381&json=true","fetch_graph":"https://pith.science/api/pith-number/RXQIGNLNOIR6KZYSAQ3IVQLYKS/graph.json","fetch_events":"https://pith.science/api/pith-number/RXQIGNLNOIR6KZYSAQ3IVQLYKS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RXQIGNLNOIR6KZYSAQ3IVQLYKS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RXQIGNLNOIR6KZYSAQ3IVQLYKS/action/storage_attestation","attest_author":"https://pith.science/pith/RXQIGNLNOIR6KZYSAQ3IVQLYKS/action/author_attestation","sign_citation":"https://pith.science/pith/RXQIGNLNOIR6KZYSAQ3IVQLYKS/action/citation_signature","submit_replication":"https://pith.science/pith/RXQIGNLNOIR6KZYSAQ3IVQLYKS/action/replication_record"}},"created_at":"2026-06-09T02:08:18.935861+00:00","updated_at":"2026-06-09T02:08:18.935861+00:00"}