{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BH7PRE7MRSPBOTPNVSA3R6DNXP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f7f905d5e259175ff5557e1d9b8f5312589407d1da1190f714affbe4bc7cf334","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-10T18:52:58Z","title_canon_sha256":"a50b774604b5f509f3704600828de93f539266bad447a7e485d1137cee13d166"},"schema_version":"1.0","source":{"id":"2410.08307","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.08307","created_at":"2026-07-05T09:18:55Z"},{"alias_kind":"arxiv_version","alias_value":"2410.08307v1","created_at":"2026-07-05T09:18:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08307","created_at":"2026-07-05T09:18:55Z"},{"alias_kind":"pith_short_12","alias_value":"BH7PRE7MRSPB","created_at":"2026-07-05T09:18:55Z"},{"alias_kind":"pith_short_16","alias_value":"BH7PRE7MRSPBOTPN","created_at":"2026-07-05T09:18:55Z"},{"alias_kind":"pith_short_8","alias_value":"BH7PRE7M","created_at":"2026-07-05T09:18:55Z"}],"graph_snapshots":[{"event_id":"sha256:1afb509951e453df9321c802c13adb153d63070bfe9fa0a663c3a98734b9fca0","target":"graph","created_at":"2026-07-05T09:18:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.08307/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We address the problem of offline learning a policy that avoids undesirable demonstrations. Unlike conventional offline imitation learning approaches that aim to imitate expert or near-optimal demonstrations, our setting involves avoiding undesirable behavior (specified using undesirable demonstrations). To tackle this problem, unlike standard imitation learning where the aim is to minimize the distance between learning policy and expert demonstrations, we formulate the learning task as maximizing a statistical distance, in the space of state-action stationary distributions, between the learni","authors_text":"Huy Hoang, Pradeep Varakantham, Tien Mai","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-10T18:52:58Z","title":"UNIQ: Offline Inverse Q-learning for Avoiding Undesirable Demonstrations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08307","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9035d90f9f62e5a8513e391f5405177f4bc2feecee82854b3cb4c6ce073fda4a","target":"record","created_at":"2026-07-05T09:18:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f7f905d5e259175ff5557e1d9b8f5312589407d1da1190f714affbe4bc7cf334","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-10T18:52:58Z","title_canon_sha256":"a50b774604b5f509f3704600828de93f539266bad447a7e485d1137cee13d166"},"schema_version":"1.0","source":{"id":"2410.08307","kind":"arxiv","version":1}},"canonical_sha256":"09fef893ec8c9e174dedac81b8f86dbbcf0d2f0ffe910c91647c215c5266960f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"09fef893ec8c9e174dedac81b8f86dbbcf0d2f0ffe910c91647c215c5266960f","first_computed_at":"2026-07-05T09:18:55.954369Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:18:55.954369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3gYzMueZ7Rt4Rg21d1skmjArsHiXtqhiUlmB6v2Dr5jOmSmSIjDdvmA5UnEwdG6TrnqopuWKCgAwJbBnwU/pCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:18:55.954805Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.08307","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9035d90f9f62e5a8513e391f5405177f4bc2feecee82854b3cb4c6ce073fda4a","sha256:1afb509951e453df9321c802c13adb153d63070bfe9fa0a663c3a98734b9fca0"],"state_sha256":"af6940c587ff9beeeb8a854c609a5cfe9e28285fecfd684557feb60e954e12d9"}