{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:ZBN6YRKCITZGS2QHSGMX652MBY","short_pith_number":"pith:ZBN6YRKC","canonical_record":{"source":{"id":"2007.15543","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-30T15:50:38Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"1f270a7d55865623adb1b7a9a1d87e207e1582b7ad824da903d43011bbd1d336","abstract_canon_sha256":"7d2ed6f46105391f8c95217e49cc81532e4354729bdaa05f53b1a37928477c6e"},"schema_version":"1.0"},"canonical_sha256":"c85bec454244f2696a0791997f774c0e1c15c995db653793b8329db7591791e1","source":{"kind":"arxiv","id":"2007.15543","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.15543","created_at":"2026-07-05T01:52:59Z"},{"alias_kind":"arxiv_version","alias_value":"2007.15543v2","created_at":"2026-07-05T01:52:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.15543","created_at":"2026-07-05T01:52:59Z"},{"alias_kind":"pith_short_12","alias_value":"ZBN6YRKCITZG","created_at":"2026-07-05T01:52:59Z"},{"alias_kind":"pith_short_16","alias_value":"ZBN6YRKCITZGS2QH","created_at":"2026-07-05T01:52:59Z"},{"alias_kind":"pith_short_8","alias_value":"ZBN6YRKC","created_at":"2026-07-05T01:52:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:ZBN6YRKCITZGS2QHSGMX652MBY","target":"record","payload":{"canonical_record":{"source":{"id":"2007.15543","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-30T15:50:38Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"1f270a7d55865623adb1b7a9a1d87e207e1582b7ad824da903d43011bbd1d336","abstract_canon_sha256":"7d2ed6f46105391f8c95217e49cc81532e4354729bdaa05f53b1a37928477c6e"},"schema_version":"1.0"},"canonical_sha256":"c85bec454244f2696a0791997f774c0e1c15c995db653793b8329db7591791e1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:52:59.592541Z","signature_b64":"t6wpQKavGxTrHB5f/Iztv3zjRCmHIL98LLQGpfh19Bu0M8dKDTZsdxrbRVzZ4OMx1/7BEdfa7JiiVhBxgFzACw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c85bec454244f2696a0791997f774c0e1c15c995db653793b8329db7591791e1","last_reissued_at":"2026-07-05T01:52:59.592099Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:52:59.592099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.15543","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":"2026-07-05T01:52:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jMTCZODEFNpW4rgz9Jma4Rjtia6Jj2rADHQ6ApgZYWa7xIqUxtLxAyHaNpHTP4lGmAdlMSZ4WmVmq2sY8zKxCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T21:17:19.898784Z"},"content_sha256":"7b350d57181084a51297fa820ba7d7962dbf9a43dee1eaced018d973f80f6228","schema_version":"1.0","event_id":"sha256:7b350d57181084a51297fa820ba7d7962dbf9a43dee1eaced018d973f80f6228"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:ZBN6YRKCITZGS2QHSGMX652MBY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PixL2R: Guiding Reinforcement Learning Using Natural Language by Mapping Pixels to Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Prasoon Goyal, Raymond J. Mooney, Scott Niekum","submitted_at":"2020-07-30T15:50:38Z","abstract_excerpt":"Reinforcement learning (RL), particularly in sparse reward settings, often requires prohibitively large numbers of interactions with the environment, thereby limiting its applicability to complex problems. To address this, several prior approaches have used natural language to guide the agent's exploration. However, these approaches typically operate on structured representations of the environment, and/or assume some structure in the natural language commands. In this work, we propose a model that directly maps pixels to rewards, given a free-form natural language description of the task, whi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.15543","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/2007.15543/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":"2026-07-05T01:52:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cYVab3zla42AUlipPJGNTtOmngj4x/DnLeOOwR1eJj3ivvp4LTU3tvXWGKzlQdxRhZCpFq9zIfNZDJ6QD3f1AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T21:17:19.899293Z"},"content_sha256":"ab9c91678b2cbba01c0c0ef0de63b0967a6170d05be75727cf3e7109dcb43b38","schema_version":"1.0","event_id":"sha256:ab9c91678b2cbba01c0c0ef0de63b0967a6170d05be75727cf3e7109dcb43b38"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZBN6YRKCITZGS2QHSGMX652MBY/bundle.json","state_url":"https://pith.science/pith/ZBN6YRKCITZGS2QHSGMX652MBY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZBN6YRKCITZGS2QHSGMX652MBY/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":"2026-08-11T21:17:19Z","links":{"resolver":"https://pith.science/pith/ZBN6YRKCITZGS2QHSGMX652MBY","bundle":"https://pith.science/pith/ZBN6YRKCITZGS2QHSGMX652MBY/bundle.json","state":"https://pith.science/pith/ZBN6YRKCITZGS2QHSGMX652MBY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZBN6YRKCITZGS2QHSGMX652MBY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ZBN6YRKCITZGS2QHSGMX652MBY","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":"7d2ed6f46105391f8c95217e49cc81532e4354729bdaa05f53b1a37928477c6e","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-30T15:50:38Z","title_canon_sha256":"1f270a7d55865623adb1b7a9a1d87e207e1582b7ad824da903d43011bbd1d336"},"schema_version":"1.0","source":{"id":"2007.15543","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.15543","created_at":"2026-07-05T01:52:59Z"},{"alias_kind":"arxiv_version","alias_value":"2007.15543v2","created_at":"2026-07-05T01:52:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.15543","created_at":"2026-07-05T01:52:59Z"},{"alias_kind":"pith_short_12","alias_value":"ZBN6YRKCITZG","created_at":"2026-07-05T01:52:59Z"},{"alias_kind":"pith_short_16","alias_value":"ZBN6YRKCITZGS2QH","created_at":"2026-07-05T01:52:59Z"},{"alias_kind":"pith_short_8","alias_value":"ZBN6YRKC","created_at":"2026-07-05T01:52:59Z"}],"graph_snapshots":[{"event_id":"sha256:ab9c91678b2cbba01c0c0ef0de63b0967a6170d05be75727cf3e7109dcb43b38","target":"graph","created_at":"2026-07-05T01:52:59Z","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/2007.15543/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL), particularly in sparse reward settings, often requires prohibitively large numbers of interactions with the environment, thereby limiting its applicability to complex problems. To address this, several prior approaches have used natural language to guide the agent's exploration. However, these approaches typically operate on structured representations of the environment, and/or assume some structure in the natural language commands. In this work, we propose a model that directly maps pixels to rewards, given a free-form natural language description of the task, whi","authors_text":"Prasoon Goyal, Raymond J. Mooney, Scott Niekum","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-30T15:50:38Z","title":"PixL2R: Guiding Reinforcement Learning Using Natural Language by Mapping Pixels to Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.15543","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":"sha256:7b350d57181084a51297fa820ba7d7962dbf9a43dee1eaced018d973f80f6228","target":"record","created_at":"2026-07-05T01:52:59Z","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":"7d2ed6f46105391f8c95217e49cc81532e4354729bdaa05f53b1a37928477c6e","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-30T15:50:38Z","title_canon_sha256":"1f270a7d55865623adb1b7a9a1d87e207e1582b7ad824da903d43011bbd1d336"},"schema_version":"1.0","source":{"id":"2007.15543","kind":"arxiv","version":2}},"canonical_sha256":"c85bec454244f2696a0791997f774c0e1c15c995db653793b8329db7591791e1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c85bec454244f2696a0791997f774c0e1c15c995db653793b8329db7591791e1","first_computed_at":"2026-07-05T01:52:59.592099Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:52:59.592099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t6wpQKavGxTrHB5f/Iztv3zjRCmHIL98LLQGpfh19Bu0M8dKDTZsdxrbRVzZ4OMx1/7BEdfa7JiiVhBxgFzACw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:52:59.592541Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.15543","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7b350d57181084a51297fa820ba7d7962dbf9a43dee1eaced018d973f80f6228","sha256:ab9c91678b2cbba01c0c0ef0de63b0967a6170d05be75727cf3e7109dcb43b38"],"state_sha256":"da138be25fc07f0ecbf9549f5758a9df860256e6f7fe9919f4650c55aaeaa72b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9yDsTyZ/Tgho7FRjE0vcdTBGar0FY1AE+39iQipVk5mqxbJr+RZrhfxzFHRkbtVnB1NlZ5vqZ7gVqHhm7O90Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T21:17:19.905882Z","bundle_sha256":"32b709fe50c1a471fe5a202b37b284f7a2da5b0e7ab89e3fa00b33eb01d430d9"}}