{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:QE77I4WDEHB2C5CVW2XDGP2BME","short_pith_number":"pith:QE77I4WD","canonical_record":{"source":{"id":"2006.14804","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-06-26T05:40:05Z","cross_cats_sorted":[],"title_canon_sha256":"a98cf88c8a2e0917bd6feb8094c1af8b3d7377b3b3fb5d67ba88dbeef173ff3b","abstract_canon_sha256":"e66164a475ee55c3b3033dc2516b45598ccaab1dc19ff4bc1637254db60ccc83"},"schema_version":"1.0"},"canonical_sha256":"813ff472c321c3a17455b6ae333f41610100c917c28d35192a1f5e9b4d7c9848","source":{"kind":"arxiv","id":"2006.14804","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.14804","created_at":"2026-07-05T03:26:13Z"},{"alias_kind":"arxiv_version","alias_value":"2006.14804v5","created_at":"2026-07-05T03:26:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.14804","created_at":"2026-07-05T03:26:13Z"},{"alias_kind":"pith_short_12","alias_value":"QE77I4WDEHB2","created_at":"2026-07-05T03:26:13Z"},{"alias_kind":"pith_short_16","alias_value":"QE77I4WDEHB2C5CV","created_at":"2026-07-05T03:26:13Z"},{"alias_kind":"pith_short_8","alias_value":"QE77I4WD","created_at":"2026-07-05T03:26:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:QE77I4WDEHB2C5CVW2XDGP2BME","target":"record","payload":{"canonical_record":{"source":{"id":"2006.14804","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-06-26T05:40:05Z","cross_cats_sorted":[],"title_canon_sha256":"a98cf88c8a2e0917bd6feb8094c1af8b3d7377b3b3fb5d67ba88dbeef173ff3b","abstract_canon_sha256":"e66164a475ee55c3b3033dc2516b45598ccaab1dc19ff4bc1637254db60ccc83"},"schema_version":"1.0"},"canonical_sha256":"813ff472c321c3a17455b6ae333f41610100c917c28d35192a1f5e9b4d7c9848","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:26:13.172506Z","signature_b64":"On3p7/yVIFB1BnplmBs/thY/ZpM3RnUyq/TnTp6disWW7crSoqwGfDWu1TnprFFCQFBZ5HfhjZqWXtDfgj+oAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"813ff472c321c3a17455b6ae333f41610100c917c28d35192a1f5e9b4d7c9848","last_reissued_at":"2026-07-05T03:26:13.172004Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:26:13.172004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.14804","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:26:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e6c/buWR/7AxQTybISTZs+1EGJ2HmOKd3JU1RjG98rw2QeUgaW5XeWavc+jpUdRcVbRd3+9SpD5IjQWqYsJcDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T01:58:51.519824Z"},"content_sha256":"6c5f4de01a529ff40faef6fa1858103c8ec4bd4c93a5e70d0d92997d3cede0b4","schema_version":"1.0","event_id":"sha256:6c5f4de01a529ff40faef6fa1858103c8ec4bd4c93a5e70d0d92997d3cede0b4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:QE77I4WDEHB2C5CVW2XDGP2BME","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Widening the Pipeline in Human-Guided Reinforcement Learning with Explanation and Context-Aware Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Lin Guan, Mudit Verma, Ruohan Zhang, Sihang Guo, Subbarao Kambhampati","submitted_at":"2020-06-26T05:40:05Z","abstract_excerpt":"Human explanation (e.g., in terms of feature importance) has been recently used to extend the communication channel between human and agent in interactive machine learning. Under this setting, human trainers provide not only the ground truth but also some form of explanation. However, this kind of human guidance was only investigated in supervised learning tasks, and it remains unclear how to best incorporate this type of human knowledge into deep reinforcement learning. In this paper, we present the first study of using human visual explanations in human-in-the-loop reinforcement learning (HR"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.14804","kind":"arxiv","version":5},"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/2006.14804/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":"2026-07-05T03:26:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6ZlLs6+GkRk7KJvLrEfFAjRrApNAsQ5KWi+1Na0RyVSzAoU3c+MowfIU+3/ya8tWWTl1qIZEqNdF6ntZWmtuBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T01:58:51.520324Z"},"content_sha256":"9dd9bc554b6cba003679bb6260e3bd80a0d8639b260217a2fe6cd07f4e3895d4","schema_version":"1.0","event_id":"sha256:9dd9bc554b6cba003679bb6260e3bd80a0d8639b260217a2fe6cd07f4e3895d4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QE77I4WDEHB2C5CVW2XDGP2BME/bundle.json","state_url":"https://pith.science/pith/QE77I4WDEHB2C5CVW2XDGP2BME/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QE77I4WDEHB2C5CVW2XDGP2BME/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":"2026-08-14T01:58:51Z","links":{"resolver":"https://pith.science/pith/QE77I4WDEHB2C5CVW2XDGP2BME","bundle":"https://pith.science/pith/QE77I4WDEHB2C5CVW2XDGP2BME/bundle.json","state":"https://pith.science/pith/QE77I4WDEHB2C5CVW2XDGP2BME/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QE77I4WDEHB2C5CVW2XDGP2BME/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:QE77I4WDEHB2C5CVW2XDGP2BME","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":"e66164a475ee55c3b3033dc2516b45598ccaab1dc19ff4bc1637254db60ccc83","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-06-26T05:40:05Z","title_canon_sha256":"a98cf88c8a2e0917bd6feb8094c1af8b3d7377b3b3fb5d67ba88dbeef173ff3b"},"schema_version":"1.0","source":{"id":"2006.14804","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.14804","created_at":"2026-07-05T03:26:13Z"},{"alias_kind":"arxiv_version","alias_value":"2006.14804v5","created_at":"2026-07-05T03:26:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.14804","created_at":"2026-07-05T03:26:13Z"},{"alias_kind":"pith_short_12","alias_value":"QE77I4WDEHB2","created_at":"2026-07-05T03:26:13Z"},{"alias_kind":"pith_short_16","alias_value":"QE77I4WDEHB2C5CV","created_at":"2026-07-05T03:26:13Z"},{"alias_kind":"pith_short_8","alias_value":"QE77I4WD","created_at":"2026-07-05T03:26:13Z"}],"graph_snapshots":[{"event_id":"sha256:9dd9bc554b6cba003679bb6260e3bd80a0d8639b260217a2fe6cd07f4e3895d4","target":"graph","created_at":"2026-07-05T03:26:13Z","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/2006.14804/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Human explanation (e.g., in terms of feature importance) has been recently used to extend the communication channel between human and agent in interactive machine learning. Under this setting, human trainers provide not only the ground truth but also some form of explanation. However, this kind of human guidance was only investigated in supervised learning tasks, and it remains unclear how to best incorporate this type of human knowledge into deep reinforcement learning. In this paper, we present the first study of using human visual explanations in human-in-the-loop reinforcement learning (HR","authors_text":"Lin Guan, Mudit Verma, Ruohan Zhang, Sihang Guo, Subbarao Kambhampati","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-06-26T05:40:05Z","title":"Widening the Pipeline in Human-Guided Reinforcement Learning with Explanation and Context-Aware Data Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.14804","kind":"arxiv","version":5},"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":"sha256:6c5f4de01a529ff40faef6fa1858103c8ec4bd4c93a5e70d0d92997d3cede0b4","target":"record","created_at":"2026-07-05T03:26:13Z","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":"e66164a475ee55c3b3033dc2516b45598ccaab1dc19ff4bc1637254db60ccc83","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-06-26T05:40:05Z","title_canon_sha256":"a98cf88c8a2e0917bd6feb8094c1af8b3d7377b3b3fb5d67ba88dbeef173ff3b"},"schema_version":"1.0","source":{"id":"2006.14804","kind":"arxiv","version":5}},"canonical_sha256":"813ff472c321c3a17455b6ae333f41610100c917c28d35192a1f5e9b4d7c9848","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"813ff472c321c3a17455b6ae333f41610100c917c28d35192a1f5e9b4d7c9848","first_computed_at":"2026-07-05T03:26:13.172004Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:26:13.172004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"On3p7/yVIFB1BnplmBs/thY/ZpM3RnUyq/TnTp6disWW7crSoqwGfDWu1TnprFFCQFBZ5HfhjZqWXtDfgj+oAA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:26:13.172506Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.14804","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c5f4de01a529ff40faef6fa1858103c8ec4bd4c93a5e70d0d92997d3cede0b4","sha256:9dd9bc554b6cba003679bb6260e3bd80a0d8639b260217a2fe6cd07f4e3895d4"],"state_sha256":"9551e3d99a2c854f5e71715327903d374db80d849db42f3745e9673f901dd2df"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VCpmJjpyThVCb4vWJxEXXVsrloairDmAK/ebJ5/Du7DSJRJDSg19oK3py0cpnCUrO5b45VhF0N4IJegMOSz1CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T01:58:51.524831Z","bundle_sha256":"a084594e86abe69c3f8ee165b5e326865183413d2cfb241b0d24683bce0928f9"}}