{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3OIEEXP6PCPMJ76XQV5OVW433K","short_pith_number":"pith:3OIEEXP6","schema_version":"1.0","canonical_sha256":"db90425dfe789ec4ffd7857aeadb9bda9b9fb52f462fc718c1065fb48c80f4b9","source":{"kind":"arxiv","id":"2607.13436","version":1},"attestation_state":"computed","paper":{"title":"Distributionally Robust and Safe Imitation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Ahmed Aboudonia, Naira Hovakimyan","submitted_at":"2026-07-15T04:40:09Z","abstract_excerpt":"Imitation learning (IL) has achieved remarkable success in complex decision-making tasks. However, its performance is highly sensitive to distribution shifts, which can pose significant safety risks. We propose a distributionally robust and safe IL framework that explicitly addresses both policy-induced and uncertainty-induced distribution shifts. Our approach develops a unified framework leveraging Taylor Series Imitation Learning (TaSIL) to mitigate policy-induced shifts and distributionally robust adaptive control to handle uncertainty-induced shifts. This architecture enables the formulati"},"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":"2607.13436","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-15T04:40:09Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"80dc6d5187314eba37aa709c6371fc903ce1e0bacd408715e27f79b26020bc4e","abstract_canon_sha256":"15861e51073976a922ff74a6ea9c0fa2cd7bb5872a700bfa6ccbd649a8d3d1f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-16T01:22:12.659657Z","signature_b64":"KdVHXTj8iYq7PQS/8NWeljtBfk6wvkzWElCbjCTPqnzPKZrlTjzKjFUAT02JmNAxfcKzWuG2/fPXhQqHGxSZCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db90425dfe789ec4ffd7857aeadb9bda9b9fb52f462fc718c1065fb48c80f4b9","last_reissued_at":"2026-07-16T01:22:12.658685Z","signature_status":"signed_v1","first_computed_at":"2026-07-16T01:22:12.658685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distributionally Robust and Safe Imitation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Ahmed Aboudonia, Naira Hovakimyan","submitted_at":"2026-07-15T04:40:09Z","abstract_excerpt":"Imitation learning (IL) has achieved remarkable success in complex decision-making tasks. However, its performance is highly sensitive to distribution shifts, which can pose significant safety risks. We propose a distributionally robust and safe IL framework that explicitly addresses both policy-induced and uncertainty-induced distribution shifts. Our approach develops a unified framework leveraging Taylor Series Imitation Learning (TaSIL) to mitigate policy-induced shifts and distributionally robust adaptive control to handle uncertainty-induced shifts. This architecture enables the formulati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.13436","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/2607.13436/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":"2607.13436","created_at":"2026-07-16T01:22:12.659144+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.13436v1","created_at":"2026-07-16T01:22:12.659144+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.13436","created_at":"2026-07-16T01:22:12.659144+00:00"},{"alias_kind":"pith_short_12","alias_value":"3OIEEXP6PCPM","created_at":"2026-07-16T01:22:12.659144+00:00"},{"alias_kind":"pith_short_16","alias_value":"3OIEEXP6PCPMJ76X","created_at":"2026-07-16T01:22:12.659144+00:00"},{"alias_kind":"pith_short_8","alias_value":"3OIEEXP6","created_at":"2026-07-16T01:22:12.659144+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/3OIEEXP6PCPMJ76XQV5OVW433K","json":"https://pith.science/pith/3OIEEXP6PCPMJ76XQV5OVW433K.json","graph_json":"https://pith.science/api/pith-number/3OIEEXP6PCPMJ76XQV5OVW433K/graph.json","events_json":"https://pith.science/api/pith-number/3OIEEXP6PCPMJ76XQV5OVW433K/events.json","paper":"https://pith.science/paper/3OIEEXP6"},"agent_actions":{"view_html":"https://pith.science/pith/3OIEEXP6PCPMJ76XQV5OVW433K","download_json":"https://pith.science/pith/3OIEEXP6PCPMJ76XQV5OVW433K.json","view_paper":"https://pith.science/paper/3OIEEXP6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.13436&json=true","fetch_graph":"https://pith.science/api/pith-number/3OIEEXP6PCPMJ76XQV5OVW433K/graph.json","fetch_events":"https://pith.science/api/pith-number/3OIEEXP6PCPMJ76XQV5OVW433K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3OIEEXP6PCPMJ76XQV5OVW433K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3OIEEXP6PCPMJ76XQV5OVW433K/action/storage_attestation","attest_author":"https://pith.science/pith/3OIEEXP6PCPMJ76XQV5OVW433K/action/author_attestation","sign_citation":"https://pith.science/pith/3OIEEXP6PCPMJ76XQV5OVW433K/action/citation_signature","submit_replication":"https://pith.science/pith/3OIEEXP6PCPMJ76XQV5OVW433K/action/replication_record"}},"created_at":"2026-07-16T01:22:12.659144+00:00","updated_at":"2026-07-16T01:22:12.659144+00:00"}