{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:LYJ6LMLGXEV3DHYDPOTUACCFLL","short_pith_number":"pith:LYJ6LMLG","canonical_record":{"source":{"id":"2606.11982","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T12:00:17Z","cross_cats_sorted":[],"title_canon_sha256":"6bdfea58ce104d373e03269c1e4dd20929ef31b396e1afb85ea30515f6571b54","abstract_canon_sha256":"4ef747065eecb34b0ba5fc52e496a7cb2b208274ba195639dc2389e2baaca723"},"schema_version":"1.0"},"canonical_sha256":"5e13e5b166b92bb19f037ba74008455aef8194af9ef07dee64d24020ce7140a3","source":{"kind":"arxiv","id":"2606.11982","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.11982","created_at":"2026-06-11T01:10:40Z"},{"alias_kind":"arxiv_version","alias_value":"2606.11982v1","created_at":"2026-06-11T01:10:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11982","created_at":"2026-06-11T01:10:40Z"},{"alias_kind":"pith_short_12","alias_value":"LYJ6LMLGXEV3","created_at":"2026-06-11T01:10:40Z"},{"alias_kind":"pith_short_16","alias_value":"LYJ6LMLGXEV3DHYD","created_at":"2026-06-11T01:10:40Z"},{"alias_kind":"pith_short_8","alias_value":"LYJ6LMLG","created_at":"2026-06-11T01:10:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:LYJ6LMLGXEV3DHYDPOTUACCFLL","target":"record","payload":{"canonical_record":{"source":{"id":"2606.11982","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T12:00:17Z","cross_cats_sorted":[],"title_canon_sha256":"6bdfea58ce104d373e03269c1e4dd20929ef31b396e1afb85ea30515f6571b54","abstract_canon_sha256":"4ef747065eecb34b0ba5fc52e496a7cb2b208274ba195639dc2389e2baaca723"},"schema_version":"1.0"},"canonical_sha256":"5e13e5b166b92bb19f037ba74008455aef8194af9ef07dee64d24020ce7140a3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:10:40.946438Z","signature_b64":"kc7RdasR94bSxuxhVC6EePKnApVr401szUC3+2pCcw3giZipnvG0So87fjkj/zANPZnzwQU+qgjfE+s1wcS6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e13e5b166b92bb19f037ba74008455aef8194af9ef07dee64d24020ce7140a3","last_reissued_at":"2026-06-11T01:10:40.945106Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:10:40.945106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.11982","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":"2026-06-11T01:10:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BI1RL0Ciow9689Znb6BgrlsFIDmXvu2OHgUcI7vYvatyeFL2Dy0LJEddplC/0pRWHXBelTZ2fZshjvr5NNXLDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-22T10:33:57.315338Z"},"content_sha256":"20d6ab1c4eedb83f4f8ed4473c156c8c7cbf2b58bdc3736dcfd128ef9bffa0c4","schema_version":"1.0","event_id":"sha256:20d6ab1c4eedb83f4f8ed4473c156c8c7cbf2b58bdc3736dcfd128ef9bffa0c4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:LYJ6LMLGXEV3DHYDPOTUACCFLL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PAWS: Preference Learning with Advantage-Weighted Segments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aleksandar Taranovic, Ge Li, Gerhard Neumann, Huy Le, Niklas Freymuth, Onur Celik, Rania Rayyes, Serge Thilges, Tai Hoang","submitted_at":"2026-06-10T12:00:17Z","abstract_excerpt":"Preference-based reinforcement learning (PbRL) learns policies from human trajectory-level comparisons, avoiding explicit reward design and expert demonstrations. Existing methods typically train utility functions on trajectory or segment-level preferences while relying on per-step utility estimates during policy optimization. This training and inference mismatch induces a distribution shift that severely degrades temporal credit assignment and limits policy learning. We analyze this issue and propose PAWS, a segment-based preference learning method that performs policy updates directly using "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11982","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/2606.11982/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":"2026-06-11T01:10:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lFr3pDD/bhOPncJiD7ezHXtZpfhPjCMxVrFRp9NeZ7LxJwXN/EVef3rDtm/MSShLuFLf16z/cu+bBVa2V+GQCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-22T10:33:57.315726Z"},"content_sha256":"a36cb937dc26fab18316b75f3cfb3c6a684485ae58484642000121eff6cb96ba","schema_version":"1.0","event_id":"sha256:a36cb937dc26fab18316b75f3cfb3c6a684485ae58484642000121eff6cb96ba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LYJ6LMLGXEV3DHYDPOTUACCFLL/bundle.json","state_url":"https://pith.science/pith/LYJ6LMLGXEV3DHYDPOTUACCFLL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LYJ6LMLGXEV3DHYDPOTUACCFLL/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":"2026-06-22T10:33:57Z","links":{"resolver":"https://pith.science/pith/LYJ6LMLGXEV3DHYDPOTUACCFLL","bundle":"https://pith.science/pith/LYJ6LMLGXEV3DHYDPOTUACCFLL/bundle.json","state":"https://pith.science/pith/LYJ6LMLGXEV3DHYDPOTUACCFLL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LYJ6LMLGXEV3DHYDPOTUACCFLL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LYJ6LMLGXEV3DHYDPOTUACCFLL","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":"4ef747065eecb34b0ba5fc52e496a7cb2b208274ba195639dc2389e2baaca723","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T12:00:17Z","title_canon_sha256":"6bdfea58ce104d373e03269c1e4dd20929ef31b396e1afb85ea30515f6571b54"},"schema_version":"1.0","source":{"id":"2606.11982","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.11982","created_at":"2026-06-11T01:10:40Z"},{"alias_kind":"arxiv_version","alias_value":"2606.11982v1","created_at":"2026-06-11T01:10:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11982","created_at":"2026-06-11T01:10:40Z"},{"alias_kind":"pith_short_12","alias_value":"LYJ6LMLGXEV3","created_at":"2026-06-11T01:10:40Z"},{"alias_kind":"pith_short_16","alias_value":"LYJ6LMLGXEV3DHYD","created_at":"2026-06-11T01:10:40Z"},{"alias_kind":"pith_short_8","alias_value":"LYJ6LMLG","created_at":"2026-06-11T01:10:40Z"}],"graph_snapshots":[{"event_id":"sha256:a36cb937dc26fab18316b75f3cfb3c6a684485ae58484642000121eff6cb96ba","target":"graph","created_at":"2026-06-11T01:10:40Z","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/2606.11982/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Preference-based reinforcement learning (PbRL) learns policies from human trajectory-level comparisons, avoiding explicit reward design and expert demonstrations. Existing methods typically train utility functions on trajectory or segment-level preferences while relying on per-step utility estimates during policy optimization. This training and inference mismatch induces a distribution shift that severely degrades temporal credit assignment and limits policy learning. We analyze this issue and propose PAWS, a segment-based preference learning method that performs policy updates directly using ","authors_text":"Aleksandar Taranovic, Ge Li, Gerhard Neumann, Huy Le, Niklas Freymuth, Onur Celik, Rania Rayyes, Serge Thilges, Tai Hoang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T12:00:17Z","title":"PAWS: Preference Learning with Advantage-Weighted Segments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11982","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":"sha256:20d6ab1c4eedb83f4f8ed4473c156c8c7cbf2b58bdc3736dcfd128ef9bffa0c4","target":"record","created_at":"2026-06-11T01:10:40Z","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":"4ef747065eecb34b0ba5fc52e496a7cb2b208274ba195639dc2389e2baaca723","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T12:00:17Z","title_canon_sha256":"6bdfea58ce104d373e03269c1e4dd20929ef31b396e1afb85ea30515f6571b54"},"schema_version":"1.0","source":{"id":"2606.11982","kind":"arxiv","version":1}},"canonical_sha256":"5e13e5b166b92bb19f037ba74008455aef8194af9ef07dee64d24020ce7140a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e13e5b166b92bb19f037ba74008455aef8194af9ef07dee64d24020ce7140a3","first_computed_at":"2026-06-11T01:10:40.945106Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T01:10:40.945106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kc7RdasR94bSxuxhVC6EePKnApVr401szUC3+2pCcw3giZipnvG0So87fjkj/zANPZnzwQU+qgjfE+s1wcS6AQ==","signature_status":"signed_v1","signed_at":"2026-06-11T01:10:40.946438Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.11982","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20d6ab1c4eedb83f4f8ed4473c156c8c7cbf2b58bdc3736dcfd128ef9bffa0c4","sha256:a36cb937dc26fab18316b75f3cfb3c6a684485ae58484642000121eff6cb96ba"],"state_sha256":"5e5f887fb690974df1eedec19dd7ba686fccc67e128045a73896abf778cefa43"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wlA28terD3K7IWwin0JTLlzriUnup19GydGkkRYkJBuNx6wIzJKT945l2MFzAbOXCHeNrbhRHqaxGlI7bjbNAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-22T10:33:57.317733Z","bundle_sha256":"fc8ee89f9978b111a1a0fbabd964331390db4f10a23c113b109089978d8a2785"}}