{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:2SOAVUHC7ZKPRBHQ4IQGTU4WMC","short_pith_number":"pith:2SOAVUHC","canonical_record":{"source":{"id":"2305.04073","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2023-05-06T15:26:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"998aacc361f3502309e76e0e0e6c785db8a48e767c2b6102c3e20f9f41efefdc","abstract_canon_sha256":"3f3cc2c03b6a60914080d8b1109781c0814e64c143c96d32ca07427148e31cd4"},"schema_version":"1.0"},"canonical_sha256":"d49c0ad0e2fe54f884f0e22069d396609ee7d3b98cb8474e18b8b984bcb2b7fb","source":{"kind":"arxiv","id":"2305.04073","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.04073","created_at":"2026-07-05T07:36:00Z"},{"alias_kind":"arxiv_version","alias_value":"2305.04073v2","created_at":"2026-07-05T07:36:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.04073","created_at":"2026-07-05T07:36:00Z"},{"alias_kind":"pith_short_12","alias_value":"2SOAVUHC7ZKP","created_at":"2026-07-05T07:36:00Z"},{"alias_kind":"pith_short_16","alias_value":"2SOAVUHC7ZKPRBHQ","created_at":"2026-07-05T07:36:00Z"},{"alias_kind":"pith_short_8","alias_value":"2SOAVUHC","created_at":"2026-07-05T07:36:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:2SOAVUHC7ZKPRBHQ4IQGTU4WMC","target":"record","payload":{"canonical_record":{"source":{"id":"2305.04073","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2023-05-06T15:26:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"998aacc361f3502309e76e0e0e6c785db8a48e767c2b6102c3e20f9f41efefdc","abstract_canon_sha256":"3f3cc2c03b6a60914080d8b1109781c0814e64c143c96d32ca07427148e31cd4"},"schema_version":"1.0"},"canonical_sha256":"d49c0ad0e2fe54f884f0e22069d396609ee7d3b98cb8474e18b8b984bcb2b7fb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:00.609641Z","signature_b64":"ASshaF10/Xkpve8xaehvLssjAzMxRdSzTYojIpnDLoxsy987+htZ6amDfC+2aVtwpVvGwmGXPcy+z0L68BaPCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d49c0ad0e2fe54f884f0e22069d396609ee7d3b98cb8474e18b8b984bcb2b7fb","last_reissued_at":"2026-07-05T07:36:00.609203Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:00.609203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.04073","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":"2026-07-05T07:36:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tctfBprX8yrmGKGQrgVSzCq/1kkMpbgGRRC3bPi3MCKZLDtTNUbYDIKKkNb4U5j12BPQ8VawdKAczpRjGJn9Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:51:42.188557Z"},"content_sha256":"011d4c1cb64bdc386984e4ce701535ac400550cb7f3e8ce4eb777a4c1cf6f08b","schema_version":"1.0","event_id":"sha256:011d4c1cb64bdc386984e4ce701535ac400550cb7f3e8ce4eb777a4c1cf6f08b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:2SOAVUHC7ZKPRBHQ4IQGTU4WMC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Explaining RL Decisions with Trajectories","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Arpan Dasgupta, Balaji Krishnamurthy, Chirag Agarwal, Georgios Theocharous, Jayakumar Subramanian, Nan Jiang, Shripad Vilasrao Deshmukh","submitted_at":"2023-05-06T15:26:22Z","abstract_excerpt":"Explanation is a key component for the adoption of reinforcement learning (RL) in many real-world decision-making problems. In the literature, the explanation is often provided by saliency attribution to the features of the RL agent's state. In this work, we propose a complementary approach to these explanations, particularly for offline RL, where we attribute the policy decisions of a trained RL agent to the trajectories encountered by it during training. To do so, we encode trajectories in offline training data individually as well as collectively (encoding a set of trajectories). We then at"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.04073","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/2305.04073/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":"2026-07-05T07:36:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t3DwrFgJAAklkUhn6AqOVFqOifbPcM6Dkw6cYvQuQecKXAHfHwStQ+hVnOVMVnF7Aw0DMibZxXplmugWejFWCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:51:42.189203Z"},"content_sha256":"7011d6d98b8bc2a336f6c0cacede0caf1eb12c1f8e4e475015e7179a8ec46d19","schema_version":"1.0","event_id":"sha256:7011d6d98b8bc2a336f6c0cacede0caf1eb12c1f8e4e475015e7179a8ec46d19"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2SOAVUHC7ZKPRBHQ4IQGTU4WMC/bundle.json","state_url":"https://pith.science/pith/2SOAVUHC7ZKPRBHQ4IQGTU4WMC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2SOAVUHC7ZKPRBHQ4IQGTU4WMC/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":"2026-07-09T06:51:42Z","links":{"resolver":"https://pith.science/pith/2SOAVUHC7ZKPRBHQ4IQGTU4WMC","bundle":"https://pith.science/pith/2SOAVUHC7ZKPRBHQ4IQGTU4WMC/bundle.json","state":"https://pith.science/pith/2SOAVUHC7ZKPRBHQ4IQGTU4WMC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2SOAVUHC7ZKPRBHQ4IQGTU4WMC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2SOAVUHC7ZKPRBHQ4IQGTU4WMC","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":"3f3cc2c03b6a60914080d8b1109781c0814e64c143c96d32ca07427148e31cd4","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2023-05-06T15:26:22Z","title_canon_sha256":"998aacc361f3502309e76e0e0e6c785db8a48e767c2b6102c3e20f9f41efefdc"},"schema_version":"1.0","source":{"id":"2305.04073","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.04073","created_at":"2026-07-05T07:36:00Z"},{"alias_kind":"arxiv_version","alias_value":"2305.04073v2","created_at":"2026-07-05T07:36:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.04073","created_at":"2026-07-05T07:36:00Z"},{"alias_kind":"pith_short_12","alias_value":"2SOAVUHC7ZKP","created_at":"2026-07-05T07:36:00Z"},{"alias_kind":"pith_short_16","alias_value":"2SOAVUHC7ZKPRBHQ","created_at":"2026-07-05T07:36:00Z"},{"alias_kind":"pith_short_8","alias_value":"2SOAVUHC","created_at":"2026-07-05T07:36:00Z"}],"graph_snapshots":[{"event_id":"sha256:7011d6d98b8bc2a336f6c0cacede0caf1eb12c1f8e4e475015e7179a8ec46d19","target":"graph","created_at":"2026-07-05T07:36:00Z","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/2305.04073/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Explanation is a key component for the adoption of reinforcement learning (RL) in many real-world decision-making problems. In the literature, the explanation is often provided by saliency attribution to the features of the RL agent's state. In this work, we propose a complementary approach to these explanations, particularly for offline RL, where we attribute the policy decisions of a trained RL agent to the trajectories encountered by it during training. To do so, we encode trajectories in offline training data individually as well as collectively (encoding a set of trajectories). We then at","authors_text":"Arpan Dasgupta, Balaji Krishnamurthy, Chirag Agarwal, Georgios Theocharous, Jayakumar Subramanian, Nan Jiang, Shripad Vilasrao Deshmukh","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2023-05-06T15:26:22Z","title":"Explaining RL Decisions with Trajectories"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.04073","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":"sha256:011d4c1cb64bdc386984e4ce701535ac400550cb7f3e8ce4eb777a4c1cf6f08b","target":"record","created_at":"2026-07-05T07:36:00Z","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":"3f3cc2c03b6a60914080d8b1109781c0814e64c143c96d32ca07427148e31cd4","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2023-05-06T15:26:22Z","title_canon_sha256":"998aacc361f3502309e76e0e0e6c785db8a48e767c2b6102c3e20f9f41efefdc"},"schema_version":"1.0","source":{"id":"2305.04073","kind":"arxiv","version":2}},"canonical_sha256":"d49c0ad0e2fe54f884f0e22069d396609ee7d3b98cb8474e18b8b984bcb2b7fb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d49c0ad0e2fe54f884f0e22069d396609ee7d3b98cb8474e18b8b984bcb2b7fb","first_computed_at":"2026-07-05T07:36:00.609203Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:36:00.609203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ASshaF10/Xkpve8xaehvLssjAzMxRdSzTYojIpnDLoxsy987+htZ6amDfC+2aVtwpVvGwmGXPcy+z0L68BaPCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:36:00.609641Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.04073","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:011d4c1cb64bdc386984e4ce701535ac400550cb7f3e8ce4eb777a4c1cf6f08b","sha256:7011d6d98b8bc2a336f6c0cacede0caf1eb12c1f8e4e475015e7179a8ec46d19"],"state_sha256":"029e60d5df0a6e47c08fab37cbdb310e5602c1e278ea0425a81eeb7dc1019379"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uxhIjPkcsb6Rh0aaH9GxT3Mjvfw6vIB4ZmdYUonLzX3fW5WbDnfbFXcluFQtXhZcPnyULieapuzjDFO5/QaQAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T06:51:42.192523Z","bundle_sha256":"a391f807c7d5830d311576704c334bbf463a64f110ea904eca780b7ff0ebdc4e"}}