{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:N4S5GRUPL2SFF5T3TX2Y2SPQTB","short_pith_number":"pith:N4S5GRUP","canonical_record":{"source":{"id":"2010.02474","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-06T04:38:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ae8edf8c1ec9f2d10116bbbc0b9add96d1a6a4c0f9f8d7f48a7ab277b3ec8a88","abstract_canon_sha256":"add46f60d1580c46e4d71f99b85f87417cf17887a6305913803900ca51c3d2b3"},"schema_version":"1.0"},"canonical_sha256":"6f25d3468f5ea452f67b9df58d49f09862c3d395af676086ca4a3c0783b76b68","source":{"kind":"arxiv","id":"2010.02474","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.02474","created_at":"2026-07-05T02:16:27Z"},{"alias_kind":"arxiv_version","alias_value":"2010.02474v2","created_at":"2026-07-05T02:16:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.02474","created_at":"2026-07-05T02:16:27Z"},{"alias_kind":"pith_short_12","alias_value":"N4S5GRUPL2SF","created_at":"2026-07-05T02:16:27Z"},{"alias_kind":"pith_short_16","alias_value":"N4S5GRUPL2SFF5T3","created_at":"2026-07-05T02:16:27Z"},{"alias_kind":"pith_short_8","alias_value":"N4S5GRUP","created_at":"2026-07-05T02:16:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:N4S5GRUPL2SFF5T3TX2Y2SPQTB","target":"record","payload":{"canonical_record":{"source":{"id":"2010.02474","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-06T04:38:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ae8edf8c1ec9f2d10116bbbc0b9add96d1a6a4c0f9f8d7f48a7ab277b3ec8a88","abstract_canon_sha256":"add46f60d1580c46e4d71f99b85f87417cf17887a6305913803900ca51c3d2b3"},"schema_version":"1.0"},"canonical_sha256":"6f25d3468f5ea452f67b9df58d49f09862c3d395af676086ca4a3c0783b76b68","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:16:27.583380Z","signature_b64":"wH00w64lU5jUsHZPeW/jTdoMNXrOsUrlXZ291Gw7fFpd99Dk78Lf4UOF26rAg96yibiuvSTFm+S0DS0PVL5QCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f25d3468f5ea452f67b9df58d49f09862c3d395af676086ca4a3c0783b76b68","last_reissued_at":"2026-07-05T02:16:27.582822Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:16:27.582822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.02474","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":"2026-07-05T02:16:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lGZU20lZFJICJGyKRlffj7CQ5m9aLCXTzyAVBvvIjND5kB+qwktbXNAVZHYUViznW0w/nS1PHuvX0eGG9JM1BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:48:18.920495Z"},"content_sha256":"2c6f48aeaec553ad7ede66383b454d6537c564d6d437bf9cf992067c338dd4de","schema_version":"1.0","event_id":"sha256:2c6f48aeaec553ad7ede66383b454d6537c564d6d437bf9cf992067c338dd4de"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:N4S5GRUPL2SFF5T3TX2Y2SPQTB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reward Propagation Using Graph Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Doina Precup, Martin Klissarov","submitted_at":"2020-10-06T04:38:16Z","abstract_excerpt":"Potential-based reward shaping provides an approach for designing good reward functions, with the purpose of speeding up learning. However, automatically finding potential functions for complex environments is a difficult problem (in fact, of the same difficulty as learning a value function from scratch). We propose a new framework for learning potential functions by leveraging ideas from graph representation learning. Our approach relies on Graph Convolutional Networks which we use as a key ingredient in combination with the probabilistic inference view of reinforcement learning. More precise"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.02474","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/2010.02474/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":"2026-07-05T02:16:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+mB3T0rQRWSlqsXRy9XYyB5qmHgFQIlO7S4DNyDQBbAJi5G7iWYHxsbLmCAnHpYZhWsdITAJVqE9lNsyR5i4AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:48:18.921424Z"},"content_sha256":"25533c51d1950d5c7d9b7084287aa1b1f4e07d893c523b1c61a4b00fcf6636d8","schema_version":"1.0","event_id":"sha256:25533c51d1950d5c7d9b7084287aa1b1f4e07d893c523b1c61a4b00fcf6636d8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N4S5GRUPL2SFF5T3TX2Y2SPQTB/bundle.json","state_url":"https://pith.science/pith/N4S5GRUPL2SFF5T3TX2Y2SPQTB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N4S5GRUPL2SFF5T3TX2Y2SPQTB/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":"2026-08-06T06:48:18Z","links":{"resolver":"https://pith.science/pith/N4S5GRUPL2SFF5T3TX2Y2SPQTB","bundle":"https://pith.science/pith/N4S5GRUPL2SFF5T3TX2Y2SPQTB/bundle.json","state":"https://pith.science/pith/N4S5GRUPL2SFF5T3TX2Y2SPQTB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N4S5GRUPL2SFF5T3TX2Y2SPQTB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:N4S5GRUPL2SFF5T3TX2Y2SPQTB","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":"add46f60d1580c46e4d71f99b85f87417cf17887a6305913803900ca51c3d2b3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-06T04:38:16Z","title_canon_sha256":"ae8edf8c1ec9f2d10116bbbc0b9add96d1a6a4c0f9f8d7f48a7ab277b3ec8a88"},"schema_version":"1.0","source":{"id":"2010.02474","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.02474","created_at":"2026-07-05T02:16:27Z"},{"alias_kind":"arxiv_version","alias_value":"2010.02474v2","created_at":"2026-07-05T02:16:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.02474","created_at":"2026-07-05T02:16:27Z"},{"alias_kind":"pith_short_12","alias_value":"N4S5GRUPL2SF","created_at":"2026-07-05T02:16:27Z"},{"alias_kind":"pith_short_16","alias_value":"N4S5GRUPL2SFF5T3","created_at":"2026-07-05T02:16:27Z"},{"alias_kind":"pith_short_8","alias_value":"N4S5GRUP","created_at":"2026-07-05T02:16:27Z"}],"graph_snapshots":[{"event_id":"sha256:25533c51d1950d5c7d9b7084287aa1b1f4e07d893c523b1c61a4b00fcf6636d8","target":"graph","created_at":"2026-07-05T02:16:27Z","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/2010.02474/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Potential-based reward shaping provides an approach for designing good reward functions, with the purpose of speeding up learning. However, automatically finding potential functions for complex environments is a difficult problem (in fact, of the same difficulty as learning a value function from scratch). We propose a new framework for learning potential functions by leveraging ideas from graph representation learning. Our approach relies on Graph Convolutional Networks which we use as a key ingredient in combination with the probabilistic inference view of reinforcement learning. More precise","authors_text":"Doina Precup, Martin Klissarov","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-06T04:38:16Z","title":"Reward Propagation Using Graph Convolutional Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.02474","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":"sha256:2c6f48aeaec553ad7ede66383b454d6537c564d6d437bf9cf992067c338dd4de","target":"record","created_at":"2026-07-05T02:16:27Z","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":"add46f60d1580c46e4d71f99b85f87417cf17887a6305913803900ca51c3d2b3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-06T04:38:16Z","title_canon_sha256":"ae8edf8c1ec9f2d10116bbbc0b9add96d1a6a4c0f9f8d7f48a7ab277b3ec8a88"},"schema_version":"1.0","source":{"id":"2010.02474","kind":"arxiv","version":2}},"canonical_sha256":"6f25d3468f5ea452f67b9df58d49f09862c3d395af676086ca4a3c0783b76b68","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f25d3468f5ea452f67b9df58d49f09862c3d395af676086ca4a3c0783b76b68","first_computed_at":"2026-07-05T02:16:27.582822Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:16:27.582822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wH00w64lU5jUsHZPeW/jTdoMNXrOsUrlXZ291Gw7fFpd99Dk78Lf4UOF26rAg96yibiuvSTFm+S0DS0PVL5QCA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:16:27.583380Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.02474","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c6f48aeaec553ad7ede66383b454d6537c564d6d437bf9cf992067c338dd4de","sha256:25533c51d1950d5c7d9b7084287aa1b1f4e07d893c523b1c61a4b00fcf6636d8"],"state_sha256":"660eb6306e2b15f9f9c25e31d30183d76cba0c61c17bd562553229d3c196cd8f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Em+idhOxLsnw4tYE8Xm9E3s0YxMnEWwQmapC0Log9rW1oUQwu/vvGdO8liQevInLC3p6+pVqVLKq+wmrME4zCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T06:48:18.926874Z","bundle_sha256":"a652ad0c46fb5d8403227e59b0965f045e24df7dbc3c15e77e579e16d4665dab"}}