{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:ADTQMV67YZTQTBTIQD5ZJH2663","short_pith_number":"pith:ADTQMV67","canonical_record":{"source":{"id":"1912.13414","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-21T03:32:00Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"812db0d98abb5bcec510d5d5eab20e41d67336a33c9e63fcaec619c5fe0cbeba","abstract_canon_sha256":"e0bc168a90cd0200a8d7ef6d9ed1eab6789c9c3a51fba1f63134a5acb73b9019"},"schema_version":"1.0"},"canonical_sha256":"00e70657dfc66709866880fb949f5ef6e41981d109068dcba04f0728f87a8868","source":{"kind":"arxiv","id":"1912.13414","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.13414","created_at":"2026-07-05T01:23:56Z"},{"alias_kind":"arxiv_version","alias_value":"1912.13414v2","created_at":"2026-07-05T01:23:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.13414","created_at":"2026-07-05T01:23:56Z"},{"alias_kind":"pith_short_12","alias_value":"ADTQMV67YZTQ","created_at":"2026-07-05T01:23:56Z"},{"alias_kind":"pith_short_16","alias_value":"ADTQMV67YZTQTBTI","created_at":"2026-07-05T01:23:56Z"},{"alias_kind":"pith_short_8","alias_value":"ADTQMV67","created_at":"2026-07-05T01:23:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:ADTQMV67YZTQTBTIQD5ZJH2663","target":"record","payload":{"canonical_record":{"source":{"id":"1912.13414","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-21T03:32:00Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"812db0d98abb5bcec510d5d5eab20e41d67336a33c9e63fcaec619c5fe0cbeba","abstract_canon_sha256":"e0bc168a90cd0200a8d7ef6d9ed1eab6789c9c3a51fba1f63134a5acb73b9019"},"schema_version":"1.0"},"canonical_sha256":"00e70657dfc66709866880fb949f5ef6e41981d109068dcba04f0728f87a8868","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:23:56.119046Z","signature_b64":"XoT6w++v+x41sXtM41WInuPGWQUqIjzbDdiml19gCMLSS9Id5tXa8uL2tmQdaFwTSBzPbrWK/StwayHo8YLhAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00e70657dfc66709866880fb949f5ef6e41981d109068dcba04f0728f87a8868","last_reissued_at":"2026-07-05T01:23:56.118611Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:23:56.118611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1912.13414","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":"2026-07-05T01:23:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aPoAhLydxB3h4DgvwBtzVh+N7mHW1wnB3Y2/63MXRQSaMvPdhi+YcK34sSxi3xBHEoeAfn2IJRK+dn23XSN4BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T20:54:02.489511Z"},"content_sha256":"2ee48bdd18edeb09573fb0d6e0992f2bb0ee392780765c2bb6cb2573b3db2d23","schema_version":"1.0","event_id":"sha256:2ee48bdd18edeb09573fb0d6e0992f2bb0ee392780765c2bb6cb2573b3db2d23"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:ADTQMV67YZTQTBTIQD5ZJH2663","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Predictive Coding for Boosting Deep Reinforcement Learning with Sparse Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Pieter Abbeel, Stas Tiomkin, Xingyu Lu","submitted_at":"2019-12-21T03:32:00Z","abstract_excerpt":"While recent progress in deep reinforcement learning has enabled robots to learn complex behaviors, tasks with long horizons and sparse rewards remain an ongoing challenge. In this work, we propose an effective reward shaping method through predictive coding to tackle sparse reward problems. By learning predictive representations offline and using these representations for reward shaping, we gain access to reward signals that understand the structure and dynamics of the environment. In particular, our method achieves better learning by providing reward signals that 1) understand environment dy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.13414","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/1912.13414/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":"2026-07-05T01:23:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UmLFA0A+P/IdzsImo3uXjDSbGTNwriM3itDUPMX/d7fRoZ18PuF6IAmEhw5/L9zdvkMAsEvRjFvt6o0F+DiVBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T20:54:02.490047Z"},"content_sha256":"50812aa05fdb79fe073df86439ad686bf41931d68fd9815fd64dba8ddda387a1","schema_version":"1.0","event_id":"sha256:50812aa05fdb79fe073df86439ad686bf41931d68fd9815fd64dba8ddda387a1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ADTQMV67YZTQTBTIQD5ZJH2663/bundle.json","state_url":"https://pith.science/pith/ADTQMV67YZTQTBTIQD5ZJH2663/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ADTQMV67YZTQTBTIQD5ZJH2663/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":"2026-08-18T20:54:02Z","links":{"resolver":"https://pith.science/pith/ADTQMV67YZTQTBTIQD5ZJH2663","bundle":"https://pith.science/pith/ADTQMV67YZTQTBTIQD5ZJH2663/bundle.json","state":"https://pith.science/pith/ADTQMV67YZTQTBTIQD5ZJH2663/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ADTQMV67YZTQTBTIQD5ZJH2663/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ADTQMV67YZTQTBTIQD5ZJH2663","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":"e0bc168a90cd0200a8d7ef6d9ed1eab6789c9c3a51fba1f63134a5acb73b9019","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-21T03:32:00Z","title_canon_sha256":"812db0d98abb5bcec510d5d5eab20e41d67336a33c9e63fcaec619c5fe0cbeba"},"schema_version":"1.0","source":{"id":"1912.13414","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.13414","created_at":"2026-07-05T01:23:56Z"},{"alias_kind":"arxiv_version","alias_value":"1912.13414v2","created_at":"2026-07-05T01:23:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.13414","created_at":"2026-07-05T01:23:56Z"},{"alias_kind":"pith_short_12","alias_value":"ADTQMV67YZTQ","created_at":"2026-07-05T01:23:56Z"},{"alias_kind":"pith_short_16","alias_value":"ADTQMV67YZTQTBTI","created_at":"2026-07-05T01:23:56Z"},{"alias_kind":"pith_short_8","alias_value":"ADTQMV67","created_at":"2026-07-05T01:23:56Z"}],"graph_snapshots":[{"event_id":"sha256:50812aa05fdb79fe073df86439ad686bf41931d68fd9815fd64dba8ddda387a1","target":"graph","created_at":"2026-07-05T01:23:56Z","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/1912.13414/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While recent progress in deep reinforcement learning has enabled robots to learn complex behaviors, tasks with long horizons and sparse rewards remain an ongoing challenge. In this work, we propose an effective reward shaping method through predictive coding to tackle sparse reward problems. By learning predictive representations offline and using these representations for reward shaping, we gain access to reward signals that understand the structure and dynamics of the environment. In particular, our method achieves better learning by providing reward signals that 1) understand environment dy","authors_text":"Pieter Abbeel, Stas Tiomkin, Xingyu Lu","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-21T03:32:00Z","title":"Predictive Coding for Boosting Deep Reinforcement Learning with Sparse Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.13414","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":"sha256:2ee48bdd18edeb09573fb0d6e0992f2bb0ee392780765c2bb6cb2573b3db2d23","target":"record","created_at":"2026-07-05T01:23:56Z","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":"e0bc168a90cd0200a8d7ef6d9ed1eab6789c9c3a51fba1f63134a5acb73b9019","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-21T03:32:00Z","title_canon_sha256":"812db0d98abb5bcec510d5d5eab20e41d67336a33c9e63fcaec619c5fe0cbeba"},"schema_version":"1.0","source":{"id":"1912.13414","kind":"arxiv","version":2}},"canonical_sha256":"00e70657dfc66709866880fb949f5ef6e41981d109068dcba04f0728f87a8868","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00e70657dfc66709866880fb949f5ef6e41981d109068dcba04f0728f87a8868","first_computed_at":"2026-07-05T01:23:56.118611Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:23:56.118611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XoT6w++v+x41sXtM41WInuPGWQUqIjzbDdiml19gCMLSS9Id5tXa8uL2tmQdaFwTSBzPbrWK/StwayHo8YLhAg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:23:56.119046Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.13414","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2ee48bdd18edeb09573fb0d6e0992f2bb0ee392780765c2bb6cb2573b3db2d23","sha256:50812aa05fdb79fe073df86439ad686bf41931d68fd9815fd64dba8ddda387a1"],"state_sha256":"79c87794e2c40ec78d76f703e2636c92fcb7fd2e012f56b1e7649be71a7730ba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"21Mxi/Nn9+1+IEDx2QRGqB6Fno+RrifFc2QIEjL4bA8DmkU4bLBZ6BzRuvmzBxF5NkAUW5yf2fLDW44ailrJCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T20:54:02.495232Z","bundle_sha256":"c2a5a0a1a1e0faf8c7ee7fddfa8fdc48c80fd0f9d5fe8f3e398f43f34263d23d"}}