{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:D4P2DV6LIIIIRGCRDXKHAA5O37","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":"bc2e9e1224c1999b6cc3401d3812d2799b24d510a12aa392ce1dfc2ae4c82519","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-08-03T01:46:10Z","title_canon_sha256":"7096a60e5e4aa8d09a86b0557462dc86be89ab3f187edaddeb39c41bd9546a27"},"schema_version":"1.0","source":{"id":"2508.01539","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.01539","created_at":"2026-07-05T11:47:40Z"},{"alias_kind":"arxiv_version","alias_value":"2508.01539v1","created_at":"2026-07-05T11:47:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.01539","created_at":"2026-07-05T11:47:40Z"},{"alias_kind":"pith_short_12","alias_value":"D4P2DV6LIIII","created_at":"2026-07-05T11:47:40Z"},{"alias_kind":"pith_short_16","alias_value":"D4P2DV6LIIIIRGCR","created_at":"2026-07-05T11:47:40Z"},{"alias_kind":"pith_short_8","alias_value":"D4P2DV6L","created_at":"2026-07-05T11:47:40Z"}],"graph_snapshots":[{"event_id":"sha256:cf8db2f39f9fa2614f5abad5a3daf75354cc18d7d4657773d36ec2544d8fde9c","target":"graph","created_at":"2026-07-05T11:47:40Z","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/2508.01539/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we introduce HALO, a novel Offline Reward Learning algorithm that quantifies human intuition in navigation into a vision-based reward function for robot navigation. HALO learns a reward model from offline data, leveraging expert trajectories collected from mobile robots. During training, actions are uniformly sampled around a reference action and ranked using preference scores derived from a Boltzmann distribution centered on the preferred action, and shaped based on binary user feedback to intuitive navigation queries. The reward model is trained via the Plackett-Luce loss to a","authors_text":"Amogha Thalihalla Sunil, Dinesh Manocha, Gershom Seneviratne, Jianyu An, Jonathan Deepak Kannan, Kasun Weerakoon, Mohamed Bashir Elnoor, Sahire Ellahy","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-08-03T01:46:10Z","title":"HALO: Human Preference Aligned Offline Reward Learning for Robot Navigation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.01539","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:b9b7910355421e182074cf59e4ac0b21ded2fcde9f540b0aec4c32afa81e1d52","target":"record","created_at":"2026-07-05T11:47:40Z","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":"bc2e9e1224c1999b6cc3401d3812d2799b24d510a12aa392ce1dfc2ae4c82519","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-08-03T01:46:10Z","title_canon_sha256":"7096a60e5e4aa8d09a86b0557462dc86be89ab3f187edaddeb39c41bd9546a27"},"schema_version":"1.0","source":{"id":"2508.01539","kind":"arxiv","version":1}},"canonical_sha256":"1f1fa1d7cb42108898511dd47003aedfee63f763e5a2e5f753c1aedf64a975dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f1fa1d7cb42108898511dd47003aedfee63f763e5a2e5f753c1aedf64a975dc","first_computed_at":"2026-07-05T11:47:40.689079Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:47:40.689079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+9fJwy3g2rCNKtVNvHJPgTCaBfp1VW2U8w/jy3iMKrJ7v8W2VPyotKoHhEBxdZ9DchPAMatZAdXJMBp1ICfEAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:47:40.689594Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.01539","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b9b7910355421e182074cf59e4ac0b21ded2fcde9f540b0aec4c32afa81e1d52","sha256:cf8db2f39f9fa2614f5abad5a3daf75354cc18d7d4657773d36ec2544d8fde9c"],"state_sha256":"f91dd2d1a3a89bba41ebd68fa915d0077bebf1994c7fb8a14d2151d824e61776"}