{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GFYTDUHPBDYRSMPDNHGDCMA4IR","short_pith_number":"pith:GFYTDUHP","canonical_record":{"source":{"id":"2606.26527","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-25T02:02:37Z","cross_cats_sorted":[],"title_canon_sha256":"0c48bc12fdbd6fd266bcd3056f0e77ed7ccb7a9863a85bae79b8ee763b064ba8","abstract_canon_sha256":"efc1ad88c00c47c8917e8ca4f551dfda8cba0c489c52de2aba4a9d09a8e7fe31"},"schema_version":"1.0"},"canonical_sha256":"317131d0ef08f11931e369cc31301c444569e7c7b12e4c0b464e6982a69233de","source":{"kind":"arxiv","id":"2606.26527","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.26527","created_at":"2026-06-26T01:15:33Z"},{"alias_kind":"arxiv_version","alias_value":"2606.26527v1","created_at":"2026-06-26T01:15:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26527","created_at":"2026-06-26T01:15:33Z"},{"alias_kind":"pith_short_12","alias_value":"GFYTDUHPBDYR","created_at":"2026-06-26T01:15:33Z"},{"alias_kind":"pith_short_16","alias_value":"GFYTDUHPBDYRSMPD","created_at":"2026-06-26T01:15:33Z"},{"alias_kind":"pith_short_8","alias_value":"GFYTDUHP","created_at":"2026-06-26T01:15:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GFYTDUHPBDYRSMPDNHGDCMA4IR","target":"record","payload":{"canonical_record":{"source":{"id":"2606.26527","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-25T02:02:37Z","cross_cats_sorted":[],"title_canon_sha256":"0c48bc12fdbd6fd266bcd3056f0e77ed7ccb7a9863a85bae79b8ee763b064ba8","abstract_canon_sha256":"efc1ad88c00c47c8917e8ca4f551dfda8cba0c489c52de2aba4a9d09a8e7fe31"},"schema_version":"1.0"},"canonical_sha256":"317131d0ef08f11931e369cc31301c444569e7c7b12e4c0b464e6982a69233de","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:15:33.639927Z","signature_b64":"7NtBXKLEYSwSD2EBrZrq4KoxEdf1eYIQPgyb6/YNVkbncyLyVNv2yrv0KPY3McVEgMUdfM41+epcw/PgDAI9CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"317131d0ef08f11931e369cc31301c444569e7c7b12e4c0b464e6982a69233de","last_reissued_at":"2026-06-26T01:15:33.639478Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:15:33.639478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.26527","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":"2026-06-26T01:15:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6pYM3It48/yLKn+Kf8YxOg7z7p6orJxPrDr+rZOsjBIEv92MGjBM5hoHvH5SoPcaF1oLDjMzBAjUcrWT2cskAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T09:38:44.991358Z"},"content_sha256":"1fe256dd6673ac31467740cef66c2e0235dede5accf4606ed29d31ad32a37a50","schema_version":"1.0","event_id":"sha256:1fe256dd6673ac31467740cef66c2e0235dede5accf4606ed29d31ad32a37a50"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GFYTDUHPBDYRSMPDNHGDCMA4IR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sample-efficient Transfer Reinforcement Learning via Adaptive Reward Shaping and Policy-Ratio Reweighting Strategy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Helai Huang, Jingjia Teng, Kai Song, Mingwei Jin, Qisong Yang, Wenjie Huang, Yang Li, Yongfu Li, Yougang Bian","submitted_at":"2026-06-25T02:02:37Z","abstract_excerpt":"Transfer learning improves policy learning efficiency by reusing knowledge from source tasks, providing a feasible paradigm for safe and efficient autonomous highway lane changing decision-making. Existing methods frequently encounter transfer mismatch induced by distribution shifts between source and target domains, leading to training oscillation and performance decline. Besides, target domain adaptation depends on exploratory interactions, which struggles to guarantee training safety in safety-critical lane changing cases. To tackle these limitations, this paper proposes a safe transfer rei"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26527","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/2606.26527/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":"2026-06-26T01:15:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gSCg6nXxN9I37jMiBZfcZjHa3o7o++wINE7I4hkr5kIo2qDBi2VqcpxccClV6qx3gEGdXG0W5CnkbHuWmo0dBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T09:38:44.992019Z"},"content_sha256":"c66ddddb36c1ac8d8d3a6a19e2a2ae2c3c6127358f5abed21b5d0d6f802ba47a","schema_version":"1.0","event_id":"sha256:c66ddddb36c1ac8d8d3a6a19e2a2ae2c3c6127358f5abed21b5d0d6f802ba47a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GFYTDUHPBDYRSMPDNHGDCMA4IR/bundle.json","state_url":"https://pith.science/pith/GFYTDUHPBDYRSMPDNHGDCMA4IR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GFYTDUHPBDYRSMPDNHGDCMA4IR/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":"2026-07-01T09:38:44Z","links":{"resolver":"https://pith.science/pith/GFYTDUHPBDYRSMPDNHGDCMA4IR","bundle":"https://pith.science/pith/GFYTDUHPBDYRSMPDNHGDCMA4IR/bundle.json","state":"https://pith.science/pith/GFYTDUHPBDYRSMPDNHGDCMA4IR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GFYTDUHPBDYRSMPDNHGDCMA4IR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GFYTDUHPBDYRSMPDNHGDCMA4IR","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":"efc1ad88c00c47c8917e8ca4f551dfda8cba0c489c52de2aba4a9d09a8e7fe31","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-25T02:02:37Z","title_canon_sha256":"0c48bc12fdbd6fd266bcd3056f0e77ed7ccb7a9863a85bae79b8ee763b064ba8"},"schema_version":"1.0","source":{"id":"2606.26527","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.26527","created_at":"2026-06-26T01:15:33Z"},{"alias_kind":"arxiv_version","alias_value":"2606.26527v1","created_at":"2026-06-26T01:15:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26527","created_at":"2026-06-26T01:15:33Z"},{"alias_kind":"pith_short_12","alias_value":"GFYTDUHPBDYR","created_at":"2026-06-26T01:15:33Z"},{"alias_kind":"pith_short_16","alias_value":"GFYTDUHPBDYRSMPD","created_at":"2026-06-26T01:15:33Z"},{"alias_kind":"pith_short_8","alias_value":"GFYTDUHP","created_at":"2026-06-26T01:15:33Z"}],"graph_snapshots":[{"event_id":"sha256:c66ddddb36c1ac8d8d3a6a19e2a2ae2c3c6127358f5abed21b5d0d6f802ba47a","target":"graph","created_at":"2026-06-26T01:15:33Z","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/2606.26527/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transfer learning improves policy learning efficiency by reusing knowledge from source tasks, providing a feasible paradigm for safe and efficient autonomous highway lane changing decision-making. Existing methods frequently encounter transfer mismatch induced by distribution shifts between source and target domains, leading to training oscillation and performance decline. Besides, target domain adaptation depends on exploratory interactions, which struggles to guarantee training safety in safety-critical lane changing cases. To tackle these limitations, this paper proposes a safe transfer rei","authors_text":"Helai Huang, Jingjia Teng, Kai Song, Mingwei Jin, Qisong Yang, Wenjie Huang, Yang Li, Yongfu Li, Yougang Bian","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-25T02:02:37Z","title":"Sample-efficient Transfer Reinforcement Learning via Adaptive Reward Shaping and Policy-Ratio Reweighting Strategy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26527","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":"sha256:1fe256dd6673ac31467740cef66c2e0235dede5accf4606ed29d31ad32a37a50","target":"record","created_at":"2026-06-26T01:15:33Z","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":"efc1ad88c00c47c8917e8ca4f551dfda8cba0c489c52de2aba4a9d09a8e7fe31","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-25T02:02:37Z","title_canon_sha256":"0c48bc12fdbd6fd266bcd3056f0e77ed7ccb7a9863a85bae79b8ee763b064ba8"},"schema_version":"1.0","source":{"id":"2606.26527","kind":"arxiv","version":1}},"canonical_sha256":"317131d0ef08f11931e369cc31301c444569e7c7b12e4c0b464e6982a69233de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"317131d0ef08f11931e369cc31301c444569e7c7b12e4c0b464e6982a69233de","first_computed_at":"2026-06-26T01:15:33.639478Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-26T01:15:33.639478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7NtBXKLEYSwSD2EBrZrq4KoxEdf1eYIQPgyb6/YNVkbncyLyVNv2yrv0KPY3McVEgMUdfM41+epcw/PgDAI9CA==","signature_status":"signed_v1","signed_at":"2026-06-26T01:15:33.639927Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.26527","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1fe256dd6673ac31467740cef66c2e0235dede5accf4606ed29d31ad32a37a50","sha256:c66ddddb36c1ac8d8d3a6a19e2a2ae2c3c6127358f5abed21b5d0d6f802ba47a"],"state_sha256":"2ed579460c24b3eee2bad45eb2100410de0890552681bbc8f8bb05953f58739a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QnBtVPKDPYzhx1zPSrsEvfbEmriDEswNHcxsg/Z5O+tAljvR3/aQxojFxTvfxyv7TGzZCg65xiiOdDWMDfQnCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-01T09:38:44.995366Z","bundle_sha256":"31fee5a80750cd07347df8b04d4189ea0d58eb9ae1d3e769ef68c86838ed3022"}}