{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NL2PHCU4IFOKH6OT4AQGQLACWY","short_pith_number":"pith:NL2PHCU4","canonical_record":{"source":{"id":"2407.10967","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-15T17:59:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3e3454e202238541d3a3c847f394027b2db5c10efb31dbb1c7921c350235f544","abstract_canon_sha256":"c69503c872f3a1340833fae2b8da3329a9775765980ebe6eb188d6d6caad01c2"},"schema_version":"1.0"},"canonical_sha256":"6af4f38a9c415ca3f9d3e020682c02b62e650adc4f6a5894aa62bfdf8bfc215b","source":{"kind":"arxiv","id":"2407.10967","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.10967","created_at":"2026-07-05T10:22:02Z"},{"alias_kind":"arxiv_version","alias_value":"2407.10967v2","created_at":"2026-07-05T10:22:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10967","created_at":"2026-07-05T10:22:02Z"},{"alias_kind":"pith_short_12","alias_value":"NL2PHCU4IFOK","created_at":"2026-07-05T10:22:02Z"},{"alias_kind":"pith_short_16","alias_value":"NL2PHCU4IFOKH6OT","created_at":"2026-07-05T10:22:02Z"},{"alias_kind":"pith_short_8","alias_value":"NL2PHCU4","created_at":"2026-07-05T10:22:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NL2PHCU4IFOKH6OT4AQGQLACWY","target":"record","payload":{"canonical_record":{"source":{"id":"2407.10967","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-15T17:59:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3e3454e202238541d3a3c847f394027b2db5c10efb31dbb1c7921c350235f544","abstract_canon_sha256":"c69503c872f3a1340833fae2b8da3329a9775765980ebe6eb188d6d6caad01c2"},"schema_version":"1.0"},"canonical_sha256":"6af4f38a9c415ca3f9d3e020682c02b62e650adc4f6a5894aa62bfdf8bfc215b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:02.167087Z","signature_b64":"BZqOdNy6gdMzq9OzeOqj+PY4LdUnKSnVywyIfs+gtaqok7GNkAfbAFNaDH81n3Y/vRdmMBSa57u9CJBaEd39DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6af4f38a9c415ca3f9d3e020682c02b62e650adc4f6a5894aa62bfdf8bfc215b","last_reissued_at":"2026-07-05T10:22:02.166564Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:02.166564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.10967","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:22:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gFofRjDILre/Mb/ZwI6hCeIQyOeXQcjxD6lH5F9YqzyKcwny1qaf9wJ/HfcRXvH4hLR0ivWzt7EhFLfMoiZDDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:44:40.827279Z"},"content_sha256":"12c0e8bf3fa51d95ac439e3e95da2d054f31beb81e533d80dfff6ff735c8074b","schema_version":"1.0","event_id":"sha256:12c0e8bf3fa51d95ac439e3e95da2d054f31beb81e533d80dfff6ff735c8074b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NL2PHCU4IFOKH6OT4AQGQLACWY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BECAUSE: Bilinear Causal Representation for Generalizable Offline Model-based Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bo Li, Ding Zhao, Haohong Lin, Jiacheng Zhu, Jian Chen, Laixi Shi, Wenhao Ding","submitted_at":"2024-07-15T17:59:23Z","abstract_excerpt":"Offline model-based reinforcement learning (MBRL) enhances data efficiency by utilizing pre-collected datasets to learn models and policies, especially in scenarios where exploration is costly or infeasible. Nevertheless, its performance often suffers from the objective mismatch between model and policy learning, resulting in inferior performance despite accurate model predictions. This paper first identifies the primary source of this mismatch comes from the underlying confounders present in offline data for MBRL. Subsequently, we introduce \\textbf{B}ilin\\textbf{E}ar \\textbf{CAUS}al r\\textbf{"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10967","kind":"arxiv","version":2},"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/2407.10967/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":"2026-07-05T10:22:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FVb5loMUR/zNk3PXfBa1hhciNOnleL9Ig9mfAlLbe5gsDmyPVrxXF8jjzUcESxJJ6v8TP1mKw84IsPhIPCdXBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:44:40.828357Z"},"content_sha256":"c239a467a25911c7ce98f41b3c1bd35b4088f45e10860a595c849c340429fa21","schema_version":"1.0","event_id":"sha256:c239a467a25911c7ce98f41b3c1bd35b4088f45e10860a595c849c340429fa21"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NL2PHCU4IFOKH6OT4AQGQLACWY/bundle.json","state_url":"https://pith.science/pith/NL2PHCU4IFOKH6OT4AQGQLACWY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NL2PHCU4IFOKH6OT4AQGQLACWY/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":"2026-08-05T20:44:40Z","links":{"resolver":"https://pith.science/pith/NL2PHCU4IFOKH6OT4AQGQLACWY","bundle":"https://pith.science/pith/NL2PHCU4IFOKH6OT4AQGQLACWY/bundle.json","state":"https://pith.science/pith/NL2PHCU4IFOKH6OT4AQGQLACWY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NL2PHCU4IFOKH6OT4AQGQLACWY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NL2PHCU4IFOKH6OT4AQGQLACWY","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":"c69503c872f3a1340833fae2b8da3329a9775765980ebe6eb188d6d6caad01c2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-15T17:59:23Z","title_canon_sha256":"3e3454e202238541d3a3c847f394027b2db5c10efb31dbb1c7921c350235f544"},"schema_version":"1.0","source":{"id":"2407.10967","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.10967","created_at":"2026-07-05T10:22:02Z"},{"alias_kind":"arxiv_version","alias_value":"2407.10967v2","created_at":"2026-07-05T10:22:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10967","created_at":"2026-07-05T10:22:02Z"},{"alias_kind":"pith_short_12","alias_value":"NL2PHCU4IFOK","created_at":"2026-07-05T10:22:02Z"},{"alias_kind":"pith_short_16","alias_value":"NL2PHCU4IFOKH6OT","created_at":"2026-07-05T10:22:02Z"},{"alias_kind":"pith_short_8","alias_value":"NL2PHCU4","created_at":"2026-07-05T10:22:02Z"}],"graph_snapshots":[{"event_id":"sha256:c239a467a25911c7ce98f41b3c1bd35b4088f45e10860a595c849c340429fa21","target":"graph","created_at":"2026-07-05T10:22:02Z","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/2407.10967/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline model-based reinforcement learning (MBRL) enhances data efficiency by utilizing pre-collected datasets to learn models and policies, especially in scenarios where exploration is costly or infeasible. Nevertheless, its performance often suffers from the objective mismatch between model and policy learning, resulting in inferior performance despite accurate model predictions. This paper first identifies the primary source of this mismatch comes from the underlying confounders present in offline data for MBRL. Subsequently, we introduce \\textbf{B}ilin\\textbf{E}ar \\textbf{CAUS}al r\\textbf{","authors_text":"Bo Li, Ding Zhao, Haohong Lin, Jiacheng Zhu, Jian Chen, Laixi Shi, Wenhao Ding","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-15T17:59:23Z","title":"BECAUSE: Bilinear Causal Representation for Generalizable Offline Model-based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10967","kind":"arxiv","version":2},"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":"sha256:12c0e8bf3fa51d95ac439e3e95da2d054f31beb81e533d80dfff6ff735c8074b","target":"record","created_at":"2026-07-05T10:22:02Z","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":"c69503c872f3a1340833fae2b8da3329a9775765980ebe6eb188d6d6caad01c2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-15T17:59:23Z","title_canon_sha256":"3e3454e202238541d3a3c847f394027b2db5c10efb31dbb1c7921c350235f544"},"schema_version":"1.0","source":{"id":"2407.10967","kind":"arxiv","version":2}},"canonical_sha256":"6af4f38a9c415ca3f9d3e020682c02b62e650adc4f6a5894aa62bfdf8bfc215b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6af4f38a9c415ca3f9d3e020682c02b62e650adc4f6a5894aa62bfdf8bfc215b","first_computed_at":"2026-07-05T10:22:02.166564Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:22:02.166564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BZqOdNy6gdMzq9OzeOqj+PY4LdUnKSnVywyIfs+gtaqok7GNkAfbAFNaDH81n3Y/vRdmMBSa57u9CJBaEd39DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:22:02.167087Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.10967","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:12c0e8bf3fa51d95ac439e3e95da2d054f31beb81e533d80dfff6ff735c8074b","sha256:c239a467a25911c7ce98f41b3c1bd35b4088f45e10860a595c849c340429fa21"],"state_sha256":"593eb5d63129efe35b784d8490dafa9880fa045e05dfe1286df7a6653697b49f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dzmVNxlhLl2fIHetSqMT1w//4PHClISl46hCsUxqO/JD+mEoPOjkkrYLQ1u/3RXWjUT6J87DOdckRmvplAZVBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T20:44:40.835480Z","bundle_sha256":"751640b8d04fcf77d3647b1d547fcd44a9cc80a21818eeb7f2030007ef4fb71a"}}