{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XVTQJF3DPSH4ZL3DWKNN2WV3EM","short_pith_number":"pith:XVTQJF3D","canonical_record":{"source":{"id":"2501.19128","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-31T13:35:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e960e65fa750226502b5f00ad454f5561fcfc682da4629db2c87bcf995b426c8","abstract_canon_sha256":"4993b5860be35b7e4fa792e808ec8a17b494af55cc02e833e8fbf4ac97e0e531"},"schema_version":"1.0"},"canonical_sha256":"bd670497637c8fccaf63b29add5abb2309ff4e0093405a07dd51f831c0e6a743","source":{"kind":"arxiv","id":"2501.19128","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.19128","created_at":"2026-05-20T00:00:17Z"},{"alias_kind":"arxiv_version","alias_value":"2501.19128v5","created_at":"2026-05-20T00:00:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.19128","created_at":"2026-05-20T00:00:17Z"},{"alias_kind":"pith_short_12","alias_value":"XVTQJF3DPSH4","created_at":"2026-05-20T00:00:17Z"},{"alias_kind":"pith_short_16","alias_value":"XVTQJF3DPSH4ZL3D","created_at":"2026-05-20T00:00:17Z"},{"alias_kind":"pith_short_8","alias_value":"XVTQJF3D","created_at":"2026-05-20T00:00:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XVTQJF3DPSH4ZL3DWKNN2WV3EM","target":"record","payload":{"canonical_record":{"source":{"id":"2501.19128","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-31T13:35:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e960e65fa750226502b5f00ad454f5561fcfc682da4629db2c87bcf995b426c8","abstract_canon_sha256":"4993b5860be35b7e4fa792e808ec8a17b494af55cc02e833e8fbf4ac97e0e531"},"schema_version":"1.0"},"canonical_sha256":"bd670497637c8fccaf63b29add5abb2309ff4e0093405a07dd51f831c0e6a743","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:17.590124Z","signature_b64":"CCHABbGvzvyQGFNh4LxrEcsMLoNbzZm92e2gnGWIZ2DVUkP71f2pw3OoMmxEVIWCTO6d+/KTwcusGp1O/DDuAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd670497637c8fccaf63b29add5abb2309ff4e0093405a07dd51f831c0e6a743","last_reissued_at":"2026-05-20T00:00:17.589342Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:17.589342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.19128","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":"2026-05-20T00:00:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P1Ripl36czabxGR383dAgwyV08hwUyOEfEs3cE0xW5mp2rWQglyZq2RxUoUr6au9iyQaMBl9FKfKaEBpSzhVAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T13:07:07.661818Z"},"content_sha256":"57af76924e44adf9db2004e10fc550d4edd892a0787a8ce97834303bd473f0f5","schema_version":"1.0","event_id":"sha256:57af76924e44adf9db2004e10fc550d4edd892a0787a8ce97834303bd473f0f5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XVTQJF3DPSH4ZL3DWKNN2WV3EM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Shaping Sparse Rewards in Reinforcement Learning: A Semi-supervised Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chen Sun, Wenjie Huang, Wenyun Li","submitted_at":"2025-01-31T13:35:19Z","abstract_excerpt":"In many real-world scenarios, reward signal for agents are exceedingly sparse, making it challenging to learn an effective reward function for reward shaping. To address this issue, the proposed approach in this paper performs reward shaping not only by utilizing non-zero-reward transitions but also by employing the \\emph{Semi-Supervised Learning} (SSL) technique combined with a novel data augmentation to learn trajectory space representations from the majority of transitions, {i.e}., zero-reward transitions, thereby improving the efficacy of reward shaping. Experimental results in Atari and r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.19128","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/2501.19128/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":"2026-05-20T00:00:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IJqpk8nCxicu/mII3iCTQrNIZgTOmq7dP6YsxvSETGum/f52AIXpEDweUjoFDv57p9BFzG3BfWLwn6kBA7d6Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T13:07:07.662631Z"},"content_sha256":"43d8b4829a1054f4a5290e63e0b44cf8de33826fe7eae134f11ef52d8c8287f6","schema_version":"1.0","event_id":"sha256:43d8b4829a1054f4a5290e63e0b44cf8de33826fe7eae134f11ef52d8c8287f6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XVTQJF3DPSH4ZL3DWKNN2WV3EM/bundle.json","state_url":"https://pith.science/pith/XVTQJF3DPSH4ZL3DWKNN2WV3EM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XVTQJF3DPSH4ZL3DWKNN2WV3EM/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":"2026-05-23T13:07:07Z","links":{"resolver":"https://pith.science/pith/XVTQJF3DPSH4ZL3DWKNN2WV3EM","bundle":"https://pith.science/pith/XVTQJF3DPSH4ZL3DWKNN2WV3EM/bundle.json","state":"https://pith.science/pith/XVTQJF3DPSH4ZL3DWKNN2WV3EM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XVTQJF3DPSH4ZL3DWKNN2WV3EM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XVTQJF3DPSH4ZL3DWKNN2WV3EM","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":"4993b5860be35b7e4fa792e808ec8a17b494af55cc02e833e8fbf4ac97e0e531","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-31T13:35:19Z","title_canon_sha256":"e960e65fa750226502b5f00ad454f5561fcfc682da4629db2c87bcf995b426c8"},"schema_version":"1.0","source":{"id":"2501.19128","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.19128","created_at":"2026-05-20T00:00:17Z"},{"alias_kind":"arxiv_version","alias_value":"2501.19128v5","created_at":"2026-05-20T00:00:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.19128","created_at":"2026-05-20T00:00:17Z"},{"alias_kind":"pith_short_12","alias_value":"XVTQJF3DPSH4","created_at":"2026-05-20T00:00:17Z"},{"alias_kind":"pith_short_16","alias_value":"XVTQJF3DPSH4ZL3D","created_at":"2026-05-20T00:00:17Z"},{"alias_kind":"pith_short_8","alias_value":"XVTQJF3D","created_at":"2026-05-20T00:00:17Z"}],"graph_snapshots":[{"event_id":"sha256:43d8b4829a1054f4a5290e63e0b44cf8de33826fe7eae134f11ef52d8c8287f6","target":"graph","created_at":"2026-05-20T00:00:17Z","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/2501.19128/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In many real-world scenarios, reward signal for agents are exceedingly sparse, making it challenging to learn an effective reward function for reward shaping. To address this issue, the proposed approach in this paper performs reward shaping not only by utilizing non-zero-reward transitions but also by employing the \\emph{Semi-Supervised Learning} (SSL) technique combined with a novel data augmentation to learn trajectory space representations from the majority of transitions, {i.e}., zero-reward transitions, thereby improving the efficacy of reward shaping. Experimental results in Atari and r","authors_text":"Chen Sun, Wenjie Huang, Wenyun Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-31T13:35:19Z","title":"Shaping Sparse Rewards in Reinforcement Learning: A Semi-supervised Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.19128","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":"sha256:57af76924e44adf9db2004e10fc550d4edd892a0787a8ce97834303bd473f0f5","target":"record","created_at":"2026-05-20T00:00:17Z","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":"4993b5860be35b7e4fa792e808ec8a17b494af55cc02e833e8fbf4ac97e0e531","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-31T13:35:19Z","title_canon_sha256":"e960e65fa750226502b5f00ad454f5561fcfc682da4629db2c87bcf995b426c8"},"schema_version":"1.0","source":{"id":"2501.19128","kind":"arxiv","version":5}},"canonical_sha256":"bd670497637c8fccaf63b29add5abb2309ff4e0093405a07dd51f831c0e6a743","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd670497637c8fccaf63b29add5abb2309ff4e0093405a07dd51f831c0e6a743","first_computed_at":"2026-05-20T00:00:17.589342Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:00:17.589342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CCHABbGvzvyQGFNh4LxrEcsMLoNbzZm92e2gnGWIZ2DVUkP71f2pw3OoMmxEVIWCTO6d+/KTwcusGp1O/DDuAw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:00:17.590124Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.19128","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:57af76924e44adf9db2004e10fc550d4edd892a0787a8ce97834303bd473f0f5","sha256:43d8b4829a1054f4a5290e63e0b44cf8de33826fe7eae134f11ef52d8c8287f6"],"state_sha256":"e4936b184cbe4a514d8e71955d18bf49a233bcc9265547474415fdd4295e0f33"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5EVdPp+iRaS2FzeykS1IKpti27776zaP4t7RVSXOT2NmVHbX/BpzrOSsbjrVa8KHJS00+tZ1zMf4JQBCa5fqAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T13:07:07.667761Z","bundle_sha256":"c9c776bf511e08c85fc0a66f1c572bdff70a9aa88e29a9b1e34f7565da536c17"}}