{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4KTZG6FV4QM7RSRIFKPKQ5PDUR","short_pith_number":"pith:4KTZG6FV","canonical_record":{"source":{"id":"2408.03029","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-06T08:22:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"375948f751d877f579e054e66b17f7b07f16efcc8f3e9a641f9206d59d2a4a64","abstract_canon_sha256":"b86ff8fe64266e045d81fbb718a56ec06283265f22ca4e91ec97ea34540c55fb"},"schema_version":"1.0"},"canonical_sha256":"e2a79378b5e419f8ca282a9ea875e3a44db9044ad9b942b26b24149a7ad1eb62","source":{"kind":"arxiv","id":"2408.03029","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.03029","created_at":"2026-07-05T10:21:22Z"},{"alias_kind":"arxiv_version","alias_value":"2408.03029v4","created_at":"2026-07-05T10:21:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.03029","created_at":"2026-07-05T10:21:22Z"},{"alias_kind":"pith_short_12","alias_value":"4KTZG6FV4QM7","created_at":"2026-07-05T10:21:22Z"},{"alias_kind":"pith_short_16","alias_value":"4KTZG6FV4QM7RSRI","created_at":"2026-07-05T10:21:22Z"},{"alias_kind":"pith_short_8","alias_value":"4KTZG6FV","created_at":"2026-07-05T10:21:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4KTZG6FV4QM7RSRIFKPKQ5PDUR","target":"record","payload":{"canonical_record":{"source":{"id":"2408.03029","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-06T08:22:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"375948f751d877f579e054e66b17f7b07f16efcc8f3e9a641f9206d59d2a4a64","abstract_canon_sha256":"b86ff8fe64266e045d81fbb718a56ec06283265f22ca4e91ec97ea34540c55fb"},"schema_version":"1.0"},"canonical_sha256":"e2a79378b5e419f8ca282a9ea875e3a44db9044ad9b942b26b24149a7ad1eb62","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:22.302349Z","signature_b64":"B/ObTXYQn0qA88hF/ySvgazmQP7+xQTA3mOGWmrVsCoqytREY8VUb+xrbDqrieVLrH7LLsMhd9uc6liBMrk5BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2a79378b5e419f8ca282a9ea875e3a44db9044ad9b942b26b24149a7ad1eb62","last_reissued_at":"2026-07-05T10:21:22.301786Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:22.301786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.03029","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:21:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zBLaToxyG8iMnDBDeLSY0kHUsuDNPrMPVuH/dmLjIyEX/yr2vrConnrj5IebyqHiOFoZwOMKcBoZ4A1sro9UAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:23:25.986571Z"},"content_sha256":"5d3bf662c1a8bf16c0e7b0a5c0d95dbdb40eefad7f5cc348ac1805524d7332cf","schema_version":"1.0","event_id":"sha256:5d3bf662c1a8bf16c0e7b0a5c0d95dbdb40eefad7f5cc348ac1805524d7332cf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4KTZG6FV4QM7RSRIFKPKQ5PDUR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Highly Efficient Self-Adaptive Reward Shaping for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haozhe Ma, Kuankuan Sima, Thanh Vinh Vo, Tze-Yun Leong, Zhengding Luo","submitted_at":"2024-08-06T08:22:16Z","abstract_excerpt":"Reward shaping is a technique in reinforcement learning that addresses the sparse-reward problem by providing more frequent and informative rewards. We introduce a self-adaptive and highly efficient reward shaping mechanism that incorporates success rates derived from historical experiences as shaped rewards. The success rates are sampled from Beta distributions, which dynamically evolve from uncertain to reliable values as data accumulates. Initially, the shaped rewards exhibit more randomness to encourage exploration, while over time, the increasing certainty enhances exploitation, naturally"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.03029","kind":"arxiv","version":4},"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/2408.03029/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":"2026-07-05T10:21:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sAEmKOPjVUAIdaAI5UYKeCh9BJ6e8vZvLP5W2tpHoSbmVb8Gf94AfQcuyKSgTwAQN/PpC3J1mj58DKO8+b0QAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:23:25.987451Z"},"content_sha256":"d0f7c01b2739670de32ee90cd335efb33ddcfc23c0dd4a2b4b06145e43bcf8a0","schema_version":"1.0","event_id":"sha256:d0f7c01b2739670de32ee90cd335efb33ddcfc23c0dd4a2b4b06145e43bcf8a0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4KTZG6FV4QM7RSRIFKPKQ5PDUR/bundle.json","state_url":"https://pith.science/pith/4KTZG6FV4QM7RSRIFKPKQ5PDUR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4KTZG6FV4QM7RSRIFKPKQ5PDUR/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":"2026-08-09T20:23:25Z","links":{"resolver":"https://pith.science/pith/4KTZG6FV4QM7RSRIFKPKQ5PDUR","bundle":"https://pith.science/pith/4KTZG6FV4QM7RSRIFKPKQ5PDUR/bundle.json","state":"https://pith.science/pith/4KTZG6FV4QM7RSRIFKPKQ5PDUR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4KTZG6FV4QM7RSRIFKPKQ5PDUR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4KTZG6FV4QM7RSRIFKPKQ5PDUR","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":"b86ff8fe64266e045d81fbb718a56ec06283265f22ca4e91ec97ea34540c55fb","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-06T08:22:16Z","title_canon_sha256":"375948f751d877f579e054e66b17f7b07f16efcc8f3e9a641f9206d59d2a4a64"},"schema_version":"1.0","source":{"id":"2408.03029","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.03029","created_at":"2026-07-05T10:21:22Z"},{"alias_kind":"arxiv_version","alias_value":"2408.03029v4","created_at":"2026-07-05T10:21:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.03029","created_at":"2026-07-05T10:21:22Z"},{"alias_kind":"pith_short_12","alias_value":"4KTZG6FV4QM7","created_at":"2026-07-05T10:21:22Z"},{"alias_kind":"pith_short_16","alias_value":"4KTZG6FV4QM7RSRI","created_at":"2026-07-05T10:21:22Z"},{"alias_kind":"pith_short_8","alias_value":"4KTZG6FV","created_at":"2026-07-05T10:21:22Z"}],"graph_snapshots":[{"event_id":"sha256:d0f7c01b2739670de32ee90cd335efb33ddcfc23c0dd4a2b4b06145e43bcf8a0","target":"graph","created_at":"2026-07-05T10:21:22Z","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/2408.03029/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reward shaping is a technique in reinforcement learning that addresses the sparse-reward problem by providing more frequent and informative rewards. We introduce a self-adaptive and highly efficient reward shaping mechanism that incorporates success rates derived from historical experiences as shaped rewards. The success rates are sampled from Beta distributions, which dynamically evolve from uncertain to reliable values as data accumulates. Initially, the shaped rewards exhibit more randomness to encourage exploration, while over time, the increasing certainty enhances exploitation, naturally","authors_text":"Haozhe Ma, Kuankuan Sima, Thanh Vinh Vo, Tze-Yun Leong, Zhengding Luo","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-06T08:22:16Z","title":"Highly Efficient Self-Adaptive Reward Shaping for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.03029","kind":"arxiv","version":4},"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":"sha256:5d3bf662c1a8bf16c0e7b0a5c0d95dbdb40eefad7f5cc348ac1805524d7332cf","target":"record","created_at":"2026-07-05T10:21:22Z","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":"b86ff8fe64266e045d81fbb718a56ec06283265f22ca4e91ec97ea34540c55fb","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-06T08:22:16Z","title_canon_sha256":"375948f751d877f579e054e66b17f7b07f16efcc8f3e9a641f9206d59d2a4a64"},"schema_version":"1.0","source":{"id":"2408.03029","kind":"arxiv","version":4}},"canonical_sha256":"e2a79378b5e419f8ca282a9ea875e3a44db9044ad9b942b26b24149a7ad1eb62","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2a79378b5e419f8ca282a9ea875e3a44db9044ad9b942b26b24149a7ad1eb62","first_computed_at":"2026-07-05T10:21:22.301786Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:21:22.301786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B/ObTXYQn0qA88hF/ySvgazmQP7+xQTA3mOGWmrVsCoqytREY8VUb+xrbDqrieVLrH7LLsMhd9uc6liBMrk5BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:21:22.302349Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.03029","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d3bf662c1a8bf16c0e7b0a5c0d95dbdb40eefad7f5cc348ac1805524d7332cf","sha256:d0f7c01b2739670de32ee90cd335efb33ddcfc23c0dd4a2b4b06145e43bcf8a0"],"state_sha256":"fd7ad4f57e51287438273a17f07c4a25b40bd15011c0e025afac197f4ec7b60a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pN8bIaC3HJ8Huai5dnc5UtjPGBpppnPQ8tWHT1g6lyiWtdwPvwWtX5TWvXHCrucctNKhx0zs5Gq2VfETKZErAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T20:23:25.994214Z","bundle_sha256":"050ad19eafc5e2dd9d84828dd63179481a9a472b183a35c4ef3b6126bebe5aad"}}