{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:RKEBLHLQN3XI4WIFIQZQHTY43X","short_pith_number":"pith:RKEBLHLQ","canonical_record":{"source":{"id":"2201.12462","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-29T00:52:37Z","cross_cats_sorted":["cs.AI","cs.HC","cs.RO"],"title_canon_sha256":"8b63c873c9c9d6036a41172e85ce700a118f5031e7f7bd0461d2aa2eee636189","abstract_canon_sha256":"30e971a780f6b386f82b7921c73a446d9c5d2b2b2ff4e0318345d9b8169d7dac"},"schema_version":"1.0"},"canonical_sha256":"8a88159d706eee8e5905443303cf1cddeb1a8b613a155cf6b0c90e7bab954d8a","source":{"kind":"arxiv","id":"2201.12462","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.12462","created_at":"2026-07-05T04:06:30Z"},{"alias_kind":"arxiv_version","alias_value":"2201.12462v2","created_at":"2026-07-05T04:06:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.12462","created_at":"2026-07-05T04:06:30Z"},{"alias_kind":"pith_short_12","alias_value":"RKEBLHLQN3XI","created_at":"2026-07-05T04:06:30Z"},{"alias_kind":"pith_short_16","alias_value":"RKEBLHLQN3XI4WIF","created_at":"2026-07-05T04:06:30Z"},{"alias_kind":"pith_short_8","alias_value":"RKEBLHLQ","created_at":"2026-07-05T04:06:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:RKEBLHLQN3XI4WIFIQZQHTY43X","target":"record","payload":{"canonical_record":{"source":{"id":"2201.12462","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-29T00:52:37Z","cross_cats_sorted":["cs.AI","cs.HC","cs.RO"],"title_canon_sha256":"8b63c873c9c9d6036a41172e85ce700a118f5031e7f7bd0461d2aa2eee636189","abstract_canon_sha256":"30e971a780f6b386f82b7921c73a446d9c5d2b2b2ff4e0318345d9b8169d7dac"},"schema_version":"1.0"},"canonical_sha256":"8a88159d706eee8e5905443303cf1cddeb1a8b613a155cf6b0c90e7bab954d8a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:30.697132Z","signature_b64":"VI7XO3D7CEmy2aRpkWCl4/ODOOuTaCNqa5egu8p6KksGVbV2hcJMtmFD9WhvyYOFts4FkFe/29p1p6akpb3eAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a88159d706eee8e5905443303cf1cddeb1a8b613a155cf6b0c90e7bab954d8a","last_reissued_at":"2026-07-05T04:06:30.696707Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:30.696707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.12462","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":"2026-07-05T04:06:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VP4u7htPE/owxg3iAxrDefuIJeDRJzBZ5P49uAB0HXwqmxe3oOVRQXyduRNFsE0GMOewj7IXtIQdFzQxHv7RAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:51:48.634594Z"},"content_sha256":"d7d844186558e4c5ff6e98c19db27cc3ac370c662a09822b78c642dd249fa025","schema_version":"1.0","event_id":"sha256:d7d844186558e4c5ff6e98c19db27cc3ac370c662a09822b78c642dd249fa025"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:RKEBLHLQN3XI4WIFIQZQHTY43X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Explaining Reinforcement Learning Policies through Counterfactual Trajectories","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.RO"],"primary_cat":"cs.LG","authors_text":"Bryan Plummer, Eric Weiner, Julius Frost, Kate Saenko, Olivia Watkins, Pieter Abbeel, Trevor Darrell","submitted_at":"2022-01-29T00:52:37Z","abstract_excerpt":"In order for humans to confidently decide where to employ RL agents for real-world tasks, a human developer must validate that the agent will perform well at test-time. Some policy interpretability methods facilitate this by capturing the policy's decision making in a set of agent rollouts. However, even the most informative trajectories of training time behavior may give little insight into the agent's behavior out of distribution. In contrast, our method conveys how the agent performs under distribution shifts by showing the agent's behavior across a wider trajectory distribution. We generat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.12462","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/2201.12462/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":"2026-07-05T04:06:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vyM3BEuET+3Jgdr2XJzo7hXY1XQWr8FCnf7OKqKwjK4mxBMbyz/R0DQu+T0IONq5ieyaBOF4l7Q9CnlItAWOAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:51:48.634926Z"},"content_sha256":"264937efe6edc6cb0ed3584305315aa092894564f121042c04b52f6007c023fb","schema_version":"1.0","event_id":"sha256:264937efe6edc6cb0ed3584305315aa092894564f121042c04b52f6007c023fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RKEBLHLQN3XI4WIFIQZQHTY43X/bundle.json","state_url":"https://pith.science/pith/RKEBLHLQN3XI4WIFIQZQHTY43X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RKEBLHLQN3XI4WIFIQZQHTY43X/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":"2026-08-05T11:51:48Z","links":{"resolver":"https://pith.science/pith/RKEBLHLQN3XI4WIFIQZQHTY43X","bundle":"https://pith.science/pith/RKEBLHLQN3XI4WIFIQZQHTY43X/bundle.json","state":"https://pith.science/pith/RKEBLHLQN3XI4WIFIQZQHTY43X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RKEBLHLQN3XI4WIFIQZQHTY43X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:RKEBLHLQN3XI4WIFIQZQHTY43X","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":"30e971a780f6b386f82b7921c73a446d9c5d2b2b2ff4e0318345d9b8169d7dac","cross_cats_sorted":["cs.AI","cs.HC","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-29T00:52:37Z","title_canon_sha256":"8b63c873c9c9d6036a41172e85ce700a118f5031e7f7bd0461d2aa2eee636189"},"schema_version":"1.0","source":{"id":"2201.12462","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.12462","created_at":"2026-07-05T04:06:30Z"},{"alias_kind":"arxiv_version","alias_value":"2201.12462v2","created_at":"2026-07-05T04:06:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.12462","created_at":"2026-07-05T04:06:30Z"},{"alias_kind":"pith_short_12","alias_value":"RKEBLHLQN3XI","created_at":"2026-07-05T04:06:30Z"},{"alias_kind":"pith_short_16","alias_value":"RKEBLHLQN3XI4WIF","created_at":"2026-07-05T04:06:30Z"},{"alias_kind":"pith_short_8","alias_value":"RKEBLHLQ","created_at":"2026-07-05T04:06:30Z"}],"graph_snapshots":[{"event_id":"sha256:264937efe6edc6cb0ed3584305315aa092894564f121042c04b52f6007c023fb","target":"graph","created_at":"2026-07-05T04:06:30Z","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/2201.12462/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In order for humans to confidently decide where to employ RL agents for real-world tasks, a human developer must validate that the agent will perform well at test-time. Some policy interpretability methods facilitate this by capturing the policy's decision making in a set of agent rollouts. However, even the most informative trajectories of training time behavior may give little insight into the agent's behavior out of distribution. In contrast, our method conveys how the agent performs under distribution shifts by showing the agent's behavior across a wider trajectory distribution. We generat","authors_text":"Bryan Plummer, Eric Weiner, Julius Frost, Kate Saenko, Olivia Watkins, Pieter Abbeel, Trevor Darrell","cross_cats":["cs.AI","cs.HC","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-29T00:52:37Z","title":"Explaining Reinforcement Learning Policies through Counterfactual Trajectories"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.12462","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:d7d844186558e4c5ff6e98c19db27cc3ac370c662a09822b78c642dd249fa025","target":"record","created_at":"2026-07-05T04:06:30Z","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":"30e971a780f6b386f82b7921c73a446d9c5d2b2b2ff4e0318345d9b8169d7dac","cross_cats_sorted":["cs.AI","cs.HC","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-29T00:52:37Z","title_canon_sha256":"8b63c873c9c9d6036a41172e85ce700a118f5031e7f7bd0461d2aa2eee636189"},"schema_version":"1.0","source":{"id":"2201.12462","kind":"arxiv","version":2}},"canonical_sha256":"8a88159d706eee8e5905443303cf1cddeb1a8b613a155cf6b0c90e7bab954d8a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a88159d706eee8e5905443303cf1cddeb1a8b613a155cf6b0c90e7bab954d8a","first_computed_at":"2026-07-05T04:06:30.696707Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:06:30.696707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VI7XO3D7CEmy2aRpkWCl4/ODOOuTaCNqa5egu8p6KksGVbV2hcJMtmFD9WhvyYOFts4FkFe/29p1p6akpb3eAg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:06:30.697132Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.12462","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d7d844186558e4c5ff6e98c19db27cc3ac370c662a09822b78c642dd249fa025","sha256:264937efe6edc6cb0ed3584305315aa092894564f121042c04b52f6007c023fb"],"state_sha256":"08dd0a758bd70c92d6d28d5ee687b84300fdea958f50fd9308bd240b6259f417"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BMKHjpa4h+YOWWh+LMTqFKLXCcjoNNFVwuQ6k/82wymmP6GY04l5llOEnpqJDLo9rygqQOGfUraUxZ39jkY0Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T11:51:48.638078Z","bundle_sha256":"2efa054a96232aa754a494831413d82ae35d5371ae1c92686bc121caef3b5763"}}