{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4ONGHOOZTCHQQA5QJX7ZGEDRFP","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":"0eb98af81b84313eff191f88c6fb7837312ff920d64172023f1f04d696926b39","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-11T16:05:18Z","title_canon_sha256":"f2e8ba086e29467cb72c31171a2b7e524718364a912cc9a4599b57119853f878"},"schema_version":"1.0","source":{"id":"2507.08707","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.08707","created_at":"2026-07-05T11:35:45Z"},{"alias_kind":"arxiv_version","alias_value":"2507.08707v1","created_at":"2026-07-05T11:35:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.08707","created_at":"2026-07-05T11:35:45Z"},{"alias_kind":"pith_short_12","alias_value":"4ONGHOOZTCHQ","created_at":"2026-07-05T11:35:45Z"},{"alias_kind":"pith_short_16","alias_value":"4ONGHOOZTCHQQA5Q","created_at":"2026-07-05T11:35:45Z"},{"alias_kind":"pith_short_8","alias_value":"4ONGHOOZ","created_at":"2026-07-05T11:35:45Z"}],"graph_snapshots":[{"event_id":"sha256:c686587b6e76faf59207ebd314e01a791f292130810e370e7291a4e5976ce276","target":"graph","created_at":"2026-07-05T11:35:45Z","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/2507.08707/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Inverse Reinforcement Learning (IRL) presents a powerful paradigm for learning complex robotic tasks from human demonstrations. However, most approaches make the assumption that expert demonstrations are available, which is often not the case. Those that allow for suboptimality in the demonstrations are not designed for long-horizon goals or adversarial tasks. Many desirable robot capabilities fall into one or both of these categories, thus highlighting a critical shortcoming in the ability of IRL to produce field-ready robotic agents. We introduce Sample-efficient Preference-based inverse rei","authors_text":"Calin Belta, Makai Mann, Michael Benjamin, Peter Crowley, Tyler Paine, Zachary Serlin","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-11T16:05:18Z","title":"SPLASH! Sample-efficient Preference-based inverse reinforcement learning for Long-horizon Adversarial tasks from Suboptimal Hierarchical demonstrations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.08707","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":"sha256:19c08101e94e74dfbbcb26c99f54e46cb0862966cbf049e6b220d79618599314","target":"record","created_at":"2026-07-05T11:35:45Z","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":"0eb98af81b84313eff191f88c6fb7837312ff920d64172023f1f04d696926b39","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-11T16:05:18Z","title_canon_sha256":"f2e8ba086e29467cb72c31171a2b7e524718364a912cc9a4599b57119853f878"},"schema_version":"1.0","source":{"id":"2507.08707","kind":"arxiv","version":1}},"canonical_sha256":"e39a63b9d9988f0803b04dff9310712be56f39c95fc326a0f23005da2c326839","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e39a63b9d9988f0803b04dff9310712be56f39c95fc326a0f23005da2c326839","first_computed_at":"2026-07-05T11:35:45.238956Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:35:45.238956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DqgjSPvtu0yJiucAYXm8/L5Ypo22MeyLALtzsLdlPaZNjbgELO1SJKqm3Unat9TDSNmJgXbtDu8RxBjvfagHDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:35:45.239405Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.08707","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:19c08101e94e74dfbbcb26c99f54e46cb0862966cbf049e6b220d79618599314","sha256:c686587b6e76faf59207ebd314e01a791f292130810e370e7291a4e5976ce276"],"state_sha256":"17b18dea094200430c7f39541745131c994f2670ebc7c2823ef1ad3b5892bcff"}