{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2APNLYBI7GE6OZINSWLBONKLEQ","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":"2c34feaf7a2a1ebfa0c1eb7a5732d57e5ae103e71f95aeaf32e6408a263db2e8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-27T08:22:41Z","title_canon_sha256":"7b40aa3d081eac14e161521f74daaf1570e56a4ebade69253ecf163600a054f7"},"schema_version":"1.0","source":{"id":"2506.22008","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.22008","created_at":"2026-07-05T11:28:20Z"},{"alias_kind":"arxiv_version","alias_value":"2506.22008v1","created_at":"2026-07-05T11:28:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22008","created_at":"2026-07-05T11:28:20Z"},{"alias_kind":"pith_short_12","alias_value":"2APNLYBI7GE6","created_at":"2026-07-05T11:28:20Z"},{"alias_kind":"pith_short_16","alias_value":"2APNLYBI7GE6OZIN","created_at":"2026-07-05T11:28:20Z"},{"alias_kind":"pith_short_8","alias_value":"2APNLYBI","created_at":"2026-07-05T11:28:20Z"}],"graph_snapshots":[{"event_id":"sha256:d153243d4c60ccb25e8c623107dc610b2c18eb382c83837893cb28ce1c8c44e2","target":"graph","created_at":"2026-07-05T11:28:20Z","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/2506.22008/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In offline reinforcement learning, agents are trained using only a fixed set of stored transitions derived from a source policy. However, this requires that the dataset be labeled by a reward function. In applied settings such as video game development, the availability of the reward function is not always guaranteed. This paper proposes Trajectory-Ranked OFfline Inverse reinforcement learning (TROFI), a novel approach to effectively learn a policy offline without a pre-defined reward function. TROFI first learns a reward function from human preferences, which it then uses to label the origina","authors_text":"Alessandro Sestini, Andrew D. Bagdanov, Joakim Bergdahl, Konrad Tollmar, Linus Gissl\\'en","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-27T08:22:41Z","title":"TROFI: Trajectory-Ranked Offline Inverse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22008","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":"sha256:98e07c9cdbe5dccb16bbe6d15e20f6a592600196f00a8c48b0717af6c732d435","target":"record","created_at":"2026-07-05T11:28:20Z","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":"2c34feaf7a2a1ebfa0c1eb7a5732d57e5ae103e71f95aeaf32e6408a263db2e8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-27T08:22:41Z","title_canon_sha256":"7b40aa3d081eac14e161521f74daaf1570e56a4ebade69253ecf163600a054f7"},"schema_version":"1.0","source":{"id":"2506.22008","kind":"arxiv","version":1}},"canonical_sha256":"d01ed5e028f989e7650d959617354b2422dea84709dbfde01f445edf788f31fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d01ed5e028f989e7650d959617354b2422dea84709dbfde01f445edf788f31fa","first_computed_at":"2026-07-05T11:28:20.302372Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:28:20.302372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3ZjzzRFIDE0OJ+0FMKtO7Xmo4aOMiukoh3z63x8qbgUbBuHJMcHvbS3hGB76+KhvhEYb2xq+so/dMjxvcComCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:28:20.303020Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.22008","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:98e07c9cdbe5dccb16bbe6d15e20f6a592600196f00a8c48b0717af6c732d435","sha256:d153243d4c60ccb25e8c623107dc610b2c18eb382c83837893cb28ce1c8c44e2"],"state_sha256":"c890f6400ab2a8c3697ff9e0d5db2a9f5405d9fbed5c3457b8f3ebcfb72eb07d"}