{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:P5CZ7ZIEKZJTF32JUMNR5A26JH","short_pith_number":"pith:P5CZ7ZIE","canonical_record":{"source":{"id":"2605.22376","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T12:09:11Z","cross_cats_sorted":[],"title_canon_sha256":"9eab486557f1b15fdcfc0e023da7993d2a3e6ce51499d27b41a34e3ae96c3381","abstract_canon_sha256":"ece670b2e855b9927a8e6ad732468655426cb4ed6ad2162ae09b2b66caf33a28"},"schema_version":"1.0"},"canonical_sha256":"7f459fe504565332ef49a31b1e835e49d432e64bec81a66094050b00eea68a9e","source":{"kind":"arxiv","id":"2605.22376","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22376","created_at":"2026-05-22T01:04:40Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22376v1","created_at":"2026-05-22T01:04:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22376","created_at":"2026-05-22T01:04:40Z"},{"alias_kind":"pith_short_12","alias_value":"P5CZ7ZIEKZJT","created_at":"2026-05-22T01:04:40Z"},{"alias_kind":"pith_short_16","alias_value":"P5CZ7ZIEKZJTF32J","created_at":"2026-05-22T01:04:40Z"},{"alias_kind":"pith_short_8","alias_value":"P5CZ7ZIE","created_at":"2026-05-22T01:04:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:P5CZ7ZIEKZJTF32JUMNR5A26JH","target":"record","payload":{"canonical_record":{"source":{"id":"2605.22376","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T12:09:11Z","cross_cats_sorted":[],"title_canon_sha256":"9eab486557f1b15fdcfc0e023da7993d2a3e6ce51499d27b41a34e3ae96c3381","abstract_canon_sha256":"ece670b2e855b9927a8e6ad732468655426cb4ed6ad2162ae09b2b66caf33a28"},"schema_version":"1.0"},"canonical_sha256":"7f459fe504565332ef49a31b1e835e49d432e64bec81a66094050b00eea68a9e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:04:40.606625Z","signature_b64":"ha0/QdPye11PWnkdaYa+S99yIZnScPFSjiLjkvn0/l0lwXDymiILXe6eBKfeZoAHz1iaZbRbueWdGV1wkA5dDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f459fe504565332ef49a31b1e835e49d432e64bec81a66094050b00eea68a9e","last_reissued_at":"2026-05-22T01:04:40.605652Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:04:40.605652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.22376","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":"2026-05-22T01:04:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1buTWuA3NWK7rdGrpMho43lGe7wB9ctYk4ekkR3yxI5Xp2RPCZHd8AFdr6QwOuV0GyNE5Cj5C18YMEU48dGvAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T00:06:31.984210Z"},"content_sha256":"f62af7235bd5d8ceab0933877b37a61090b7de569c563a153c8f42697ab7b934","schema_version":"1.0","event_id":"sha256:f62af7235bd5d8ceab0933877b37a61090b7de569c563a153c8f42697ab7b934"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:P5CZ7ZIEKZJTF32JUMNR5A26JH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Target-Aligned Bellman Backup for Cross-domain Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ting Long, Wei Liu","submitted_at":"2026-05-21T12:09:11Z","abstract_excerpt":"Cross-domain offline reinforcement learning (CDRL) aims to improve policy learning in a target domain by leveraging data collected from a source domain. Existing works typically assess the transferability of source-domain data by measuring its similarity to target-domain transitions, and implicitly perform transition-level selection. Transitions that are considered similar are assigned higher weights or rewards, while dissimilar ones are down-weighted. However, transition-level similarity does not necessarily imply consistency in long-term returns. Even visually or dynamically similar transiti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22376","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/2605.22376/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":"2026-05-22T01:04:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"InA0INro8Cu+cClsBsdy32OM4Q3npOqMYVi4G2HKWmok/In9qZNsXGOf1rnYI2Dtz6EeEGF6NR4eiPGuKrhsBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T00:06:31.984607Z"},"content_sha256":"6e3ee3df6543ce1edf0445c95a9e4581bce6e19719b2b3c62513dc963967c071","schema_version":"1.0","event_id":"sha256:6e3ee3df6543ce1edf0445c95a9e4581bce6e19719b2b3c62513dc963967c071"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P5CZ7ZIEKZJTF32JUMNR5A26JH/bundle.json","state_url":"https://pith.science/pith/P5CZ7ZIEKZJTF32JUMNR5A26JH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P5CZ7ZIEKZJTF32JUMNR5A26JH/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":"2026-06-09T00:06:31Z","links":{"resolver":"https://pith.science/pith/P5CZ7ZIEKZJTF32JUMNR5A26JH","bundle":"https://pith.science/pith/P5CZ7ZIEKZJTF32JUMNR5A26JH/bundle.json","state":"https://pith.science/pith/P5CZ7ZIEKZJTF32JUMNR5A26JH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P5CZ7ZIEKZJTF32JUMNR5A26JH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:P5CZ7ZIEKZJTF32JUMNR5A26JH","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":"ece670b2e855b9927a8e6ad732468655426cb4ed6ad2162ae09b2b66caf33a28","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T12:09:11Z","title_canon_sha256":"9eab486557f1b15fdcfc0e023da7993d2a3e6ce51499d27b41a34e3ae96c3381"},"schema_version":"1.0","source":{"id":"2605.22376","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22376","created_at":"2026-05-22T01:04:40Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22376v1","created_at":"2026-05-22T01:04:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22376","created_at":"2026-05-22T01:04:40Z"},{"alias_kind":"pith_short_12","alias_value":"P5CZ7ZIEKZJT","created_at":"2026-05-22T01:04:40Z"},{"alias_kind":"pith_short_16","alias_value":"P5CZ7ZIEKZJTF32J","created_at":"2026-05-22T01:04:40Z"},{"alias_kind":"pith_short_8","alias_value":"P5CZ7ZIE","created_at":"2026-05-22T01:04:40Z"}],"graph_snapshots":[{"event_id":"sha256:6e3ee3df6543ce1edf0445c95a9e4581bce6e19719b2b3c62513dc963967c071","target":"graph","created_at":"2026-05-22T01:04:40Z","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/2605.22376/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cross-domain offline reinforcement learning (CDRL) aims to improve policy learning in a target domain by leveraging data collected from a source domain. Existing works typically assess the transferability of source-domain data by measuring its similarity to target-domain transitions, and implicitly perform transition-level selection. Transitions that are considered similar are assigned higher weights or rewards, while dissimilar ones are down-weighted. However, transition-level similarity does not necessarily imply consistency in long-term returns. Even visually or dynamically similar transiti","authors_text":"Ting Long, Wei Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T12:09:11Z","title":"Target-Aligned Bellman Backup for Cross-domain Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22376","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:f62af7235bd5d8ceab0933877b37a61090b7de569c563a153c8f42697ab7b934","target":"record","created_at":"2026-05-22T01:04:40Z","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":"ece670b2e855b9927a8e6ad732468655426cb4ed6ad2162ae09b2b66caf33a28","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T12:09:11Z","title_canon_sha256":"9eab486557f1b15fdcfc0e023da7993d2a3e6ce51499d27b41a34e3ae96c3381"},"schema_version":"1.0","source":{"id":"2605.22376","kind":"arxiv","version":1}},"canonical_sha256":"7f459fe504565332ef49a31b1e835e49d432e64bec81a66094050b00eea68a9e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f459fe504565332ef49a31b1e835e49d432e64bec81a66094050b00eea68a9e","first_computed_at":"2026-05-22T01:04:40.605652Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:04:40.605652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ha0/QdPye11PWnkdaYa+S99yIZnScPFSjiLjkvn0/l0lwXDymiILXe6eBKfeZoAHz1iaZbRbueWdGV1wkA5dDg==","signature_status":"signed_v1","signed_at":"2026-05-22T01:04:40.606625Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.22376","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f62af7235bd5d8ceab0933877b37a61090b7de569c563a153c8f42697ab7b934","sha256:6e3ee3df6543ce1edf0445c95a9e4581bce6e19719b2b3c62513dc963967c071"],"state_sha256":"13054a8d07f3095cc93c7c0d3d04fddd9bb445f4eed242db8e50b6c828be6645"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2Qgq2DiF5YoL3uNxJeHxnefvTdwIsnp3WsRMQhCBE5g1PHo8ORhx9Q8jHFQo0Q8IF81rIG6+quQ7QacDzdABAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T00:06:31.987069Z","bundle_sha256":"0b9273ee28617927e41a4bfebb591f46a9ba43e4837777390ec813b716832319"}}