{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BSZXDBJHPXRV45BNHZ5WVZVEZD","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":"740ae3daf08b6c8e89ba183c090cf4839d763607d0bb99899886d6993c11a861","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-30T17:54:02Z","title_canon_sha256":"b086994ab512a196c6e2ee66ef2da0926dc1923c80586a20dd6130849cfb1e54"},"schema_version":"1.0","source":{"id":"2606.32027","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.32027","created_at":"2026-07-01T02:17:47Z"},{"alias_kind":"arxiv_version","alias_value":"2606.32027v1","created_at":"2026-07-01T02:17:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.32027","created_at":"2026-07-01T02:17:47Z"},{"alias_kind":"pith_short_12","alias_value":"BSZXDBJHPXRV","created_at":"2026-07-01T02:17:47Z"},{"alias_kind":"pith_short_16","alias_value":"BSZXDBJHPXRV45BN","created_at":"2026-07-01T02:17:47Z"},{"alias_kind":"pith_short_8","alias_value":"BSZXDBJH","created_at":"2026-07-01T02:17:47Z"}],"graph_snapshots":[{"event_id":"sha256:63a2e72399d12e9a3ef23e006fd120e2d8dbe5accdda47058cf2083d4c7d1123","target":"graph","created_at":"2026-07-01T02:17:47Z","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/2606.32027/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reward design remains a central bottleneck for autonomous robot policy improvement, especially in long-horizon manipulation tasks where sparse success labels provide too little signal and binary preferences collapse many competing notions of quality into one ambiguous signal. We introduce Freeform Preference Learning (FPL), a method for learning robot policies from freeform human preferences. Rather than asking annotators which of two trajectories is better overall, FPL lets them define natural-language preference axes, such as speed, safety, quality of placement, or carefulness, and provide p","authors_text":"Abhijnya Bhat, Anubha Mahajan, Chelsea Finn, Marcel Torne","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-30T17:54:02Z","title":"Freeform Preference Learning for Robotic Manipulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.32027","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":"sha256:723d801b49f874c9f36b573a2cc0e5a5377625cd7935eef0cf8d50f6853417e0","target":"record","created_at":"2026-07-01T02:17:47Z","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":"740ae3daf08b6c8e89ba183c090cf4839d763607d0bb99899886d6993c11a861","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-30T17:54:02Z","title_canon_sha256":"b086994ab512a196c6e2ee66ef2da0926dc1923c80586a20dd6130849cfb1e54"},"schema_version":"1.0","source":{"id":"2606.32027","kind":"arxiv","version":1}},"canonical_sha256":"0cb37185277de35e742d3e7b6ae6a4c8dd716b05db7449e93fd0e734c7fcecfc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0cb37185277de35e742d3e7b6ae6a4c8dd716b05db7449e93fd0e734c7fcecfc","first_computed_at":"2026-07-01T02:17:47.667193Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T02:17:47.667193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v3SwBfmvbaDL4Vuq26ZHukvBh2JwR4D1Yh/ADawbC4pxaucA5xOhcO+4EZ8m3LnlCFjQSgwAg8Sw73JeD2trCQ==","signature_status":"signed_v1","signed_at":"2026-07-01T02:17:47.667702Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.32027","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:723d801b49f874c9f36b573a2cc0e5a5377625cd7935eef0cf8d50f6853417e0","sha256:63a2e72399d12e9a3ef23e006fd120e2d8dbe5accdda47058cf2083d4c7d1123"],"state_sha256":"3c8808c6d3a0553b1964f0e6fed8e37e16acd0216a105da24562f498d06a95ef"}