{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:NC2XHRIXM7MJH5NK7ITB2KDHSV","short_pith_number":"pith:NC2XHRIX","canonical_record":{"source":{"id":"2606.01123","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-31T09:46:53Z","cross_cats_sorted":[],"title_canon_sha256":"fc754fa0c3d0146a27b807a4650d32930e64440083759b88c6694268665573d8","abstract_canon_sha256":"2278d13ecbe4bdcf4dcea20127d9612f3f6c614f10a417280cc97d7328c0acff"},"schema_version":"1.0"},"canonical_sha256":"68b573c51767d893f5aafa261d2867954cc908cf04bf15198279135bffa9845d","source":{"kind":"arxiv","id":"2606.01123","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01123","created_at":"2026-06-02T02:04:24Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01123v1","created_at":"2026-06-02T02:04:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01123","created_at":"2026-06-02T02:04:24Z"},{"alias_kind":"pith_short_12","alias_value":"NC2XHRIXM7MJ","created_at":"2026-06-02T02:04:24Z"},{"alias_kind":"pith_short_16","alias_value":"NC2XHRIXM7MJH5NK","created_at":"2026-06-02T02:04:24Z"},{"alias_kind":"pith_short_8","alias_value":"NC2XHRIX","created_at":"2026-06-02T02:04:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:NC2XHRIXM7MJH5NK7ITB2KDHSV","target":"record","payload":{"canonical_record":{"source":{"id":"2606.01123","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-31T09:46:53Z","cross_cats_sorted":[],"title_canon_sha256":"fc754fa0c3d0146a27b807a4650d32930e64440083759b88c6694268665573d8","abstract_canon_sha256":"2278d13ecbe4bdcf4dcea20127d9612f3f6c614f10a417280cc97d7328c0acff"},"schema_version":"1.0"},"canonical_sha256":"68b573c51767d893f5aafa261d2867954cc908cf04bf15198279135bffa9845d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:24.165522Z","signature_b64":"r6F1mD2YuPLv9vrVr8qv1DGeEEilnArECGDB0En7X98KmZJMif1SXzJJ1TtY6rGYm5sqjxql8JnpklQAbPGTDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68b573c51767d893f5aafa261d2867954cc908cf04bf15198279135bffa9845d","last_reissued_at":"2026-06-02T02:04:24.165009Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:24.165009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.01123","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T02:04:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H4LuOxbPmrDhF9p/BBFhCEao/wbLHEunudfROKhkb7GRRqCpoXg/YeuOzSgM72iEe49qQBfNJPGOmRXMQXiWAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T19:09:05.676912Z"},"content_sha256":"ea7b8291b69e05b80bda91096a335221a4241c8ae4a6fed0ef224015e32d6588","schema_version":"1.0","event_id":"sha256:ea7b8291b69e05b80bda91096a335221a4241c8ae4a6fed0ef224015e32d6588"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:NC2XHRIXM7MJH5NK7ITB2KDHSV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Reward-Free Representations to Preferences: Rethinking Offline Preference-Based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chia-Heng Hsu, Jun-Jie Yang, Kui-Yuan Chen, Ping-Chun Hsieh","submitted_at":"2026-05-31T09:46:53Z","abstract_excerpt":"Preference-based reinforcement learning (PbRL) avoids explicit reward engineering by learning from pairwise human preference feedback. Existing offline PbRL methods typically follow a two-stage pipeline, first learning a reward or preference model from labeled preferences and then performing offline RL on unlabeled data. We revisit offline PbRL through the lens of reward-free representation learning (RFRL) from the zero-shot RL literature, and propose a new training framework that first learns latent successor-measure representations from reward-free offline data, followed by contrastive searc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01123","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.01123/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T02:04:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QTjpmvX3LcI3p4BAZutzCQIflnZkqK4ibE3AhTHTmUdTapi0NTEx6Lpg0AMitg3nOHfrtJUxUE2jCzTyjLw4DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T19:09:05.677370Z"},"content_sha256":"6a4e1c89a7a91cbd0bc992d239d12c13108dc4e663de70b562f90037d1084136","schema_version":"1.0","event_id":"sha256:6a4e1c89a7a91cbd0bc992d239d12c13108dc4e663de70b562f90037d1084136"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NC2XHRIXM7MJH5NK7ITB2KDHSV/bundle.json","state_url":"https://pith.science/pith/NC2XHRIXM7MJH5NK7ITB2KDHSV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NC2XHRIXM7MJH5NK7ITB2KDHSV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-08T19:09:05Z","links":{"resolver":"https://pith.science/pith/NC2XHRIXM7MJH5NK7ITB2KDHSV","bundle":"https://pith.science/pith/NC2XHRIXM7MJH5NK7ITB2KDHSV/bundle.json","state":"https://pith.science/pith/NC2XHRIXM7MJH5NK7ITB2KDHSV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NC2XHRIXM7MJH5NK7ITB2KDHSV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NC2XHRIXM7MJH5NK7ITB2KDHSV","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":"2278d13ecbe4bdcf4dcea20127d9612f3f6c614f10a417280cc97d7328c0acff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-31T09:46:53Z","title_canon_sha256":"fc754fa0c3d0146a27b807a4650d32930e64440083759b88c6694268665573d8"},"schema_version":"1.0","source":{"id":"2606.01123","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01123","created_at":"2026-06-02T02:04:24Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01123v1","created_at":"2026-06-02T02:04:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01123","created_at":"2026-06-02T02:04:24Z"},{"alias_kind":"pith_short_12","alias_value":"NC2XHRIXM7MJ","created_at":"2026-06-02T02:04:24Z"},{"alias_kind":"pith_short_16","alias_value":"NC2XHRIXM7MJH5NK","created_at":"2026-06-02T02:04:24Z"},{"alias_kind":"pith_short_8","alias_value":"NC2XHRIX","created_at":"2026-06-02T02:04:24Z"}],"graph_snapshots":[{"event_id":"sha256:6a4e1c89a7a91cbd0bc992d239d12c13108dc4e663de70b562f90037d1084136","target":"graph","created_at":"2026-06-02T02:04:24Z","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/2606.01123/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Preference-based reinforcement learning (PbRL) avoids explicit reward engineering by learning from pairwise human preference feedback. Existing offline PbRL methods typically follow a two-stage pipeline, first learning a reward or preference model from labeled preferences and then performing offline RL on unlabeled data. We revisit offline PbRL through the lens of reward-free representation learning (RFRL) from the zero-shot RL literature, and propose a new training framework that first learns latent successor-measure representations from reward-free offline data, followed by contrastive searc","authors_text":"Chia-Heng Hsu, Jun-Jie Yang, Kui-Yuan Chen, Ping-Chun Hsieh","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-31T09:46:53Z","title":"From Reward-Free Representations to Preferences: Rethinking Offline Preference-Based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01123","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:ea7b8291b69e05b80bda91096a335221a4241c8ae4a6fed0ef224015e32d6588","target":"record","created_at":"2026-06-02T02:04:24Z","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":"2278d13ecbe4bdcf4dcea20127d9612f3f6c614f10a417280cc97d7328c0acff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-31T09:46:53Z","title_canon_sha256":"fc754fa0c3d0146a27b807a4650d32930e64440083759b88c6694268665573d8"},"schema_version":"1.0","source":{"id":"2606.01123","kind":"arxiv","version":1}},"canonical_sha256":"68b573c51767d893f5aafa261d2867954cc908cf04bf15198279135bffa9845d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68b573c51767d893f5aafa261d2867954cc908cf04bf15198279135bffa9845d","first_computed_at":"2026-06-02T02:04:24.165009Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:24.165009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r6F1mD2YuPLv9vrVr8qv1DGeEEilnArECGDB0En7X98KmZJMif1SXzJJ1TtY6rGYm5sqjxql8JnpklQAbPGTDA==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:24.165522Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.01123","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea7b8291b69e05b80bda91096a335221a4241c8ae4a6fed0ef224015e32d6588","sha256:6a4e1c89a7a91cbd0bc992d239d12c13108dc4e663de70b562f90037d1084136"],"state_sha256":"5ea6a31cf301dea313a27d263aac8fbfe0090a636ee8255d7bdc3bfff3517176"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0CgV7ILSQVWGGHnncX7NCQ2/LvoD5mptfFKpdXoYc2epnEkGCjm4EMVhm67htktUcSQ21DTV87l6wzyG2QaHCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T19:09:05.680538Z","bundle_sha256":"7d23e15460642f4edec488748d8f7a49a33f762c57c74a551d9eea4bb1884784"}}