{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SD4A5Z3M5WTT3WGRRU6IZBETGD","short_pith_number":"pith:SD4A5Z3M","canonical_record":{"source":{"id":"2402.04581","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-02-07T04:44:41Z","cross_cats_sorted":[],"title_canon_sha256":"4595ba0dfd4b59a974db95e380e3661423f4807837313570d89b1bed91b4bd18","abstract_canon_sha256":"759ba4bd737cdcf9945bb5be5c2e7e32f623e7e526a214d152b7e00ccfe935da"},"schema_version":"1.0"},"canonical_sha256":"90f80ee76ceda73dd8d18d3c8c849330c178ed50e12d6cef34a1b8224538dabf","source":{"kind":"arxiv","id":"2402.04581","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.04581","created_at":"2026-07-05T07:42:29Z"},{"alias_kind":"arxiv_version","alias_value":"2402.04581v1","created_at":"2026-07-05T07:42:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04581","created_at":"2026-07-05T07:42:29Z"},{"alias_kind":"pith_short_12","alias_value":"SD4A5Z3M5WTT","created_at":"2026-07-05T07:42:29Z"},{"alias_kind":"pith_short_16","alias_value":"SD4A5Z3M5WTT3WGR","created_at":"2026-07-05T07:42:29Z"},{"alias_kind":"pith_short_8","alias_value":"SD4A5Z3M","created_at":"2026-07-05T07:42:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SD4A5Z3M5WTT3WGRRU6IZBETGD","target":"record","payload":{"canonical_record":{"source":{"id":"2402.04581","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-02-07T04:44:41Z","cross_cats_sorted":[],"title_canon_sha256":"4595ba0dfd4b59a974db95e380e3661423f4807837313570d89b1bed91b4bd18","abstract_canon_sha256":"759ba4bd737cdcf9945bb5be5c2e7e32f623e7e526a214d152b7e00ccfe935da"},"schema_version":"1.0"},"canonical_sha256":"90f80ee76ceda73dd8d18d3c8c849330c178ed50e12d6cef34a1b8224538dabf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:42:29.175609Z","signature_b64":"Gy4TFneMdPmt38wRKkL6psYINeQ/JU31fmo/gdk1uf0MuqBxtr9Jz3kdNQEJLAAt61ZISTkcHFAzvh/+hVljBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90f80ee76ceda73dd8d18d3c8c849330c178ed50e12d6cef34a1b8224538dabf","last_reissued_at":"2026-07-05T07:42:29.175124Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:42:29.175124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.04581","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:42:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T+uvOck4waN2ubKp82rx5xML5Lr0jvTpR+AOBxwbaP6nsFDup7CgYp1YCpjPG7eN7hlYnIZE3NWOv6KDr6uKCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:36:50.977372Z"},"content_sha256":"948ef158a006af19180d1507673800c417a3c27b898d5c395f051b5cd9ea3a51","schema_version":"1.0","event_id":"sha256:948ef158a006af19180d1507673800c417a3c27b898d5c395f051b5cd9ea3a51"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SD4A5Z3M5WTT3WGRRU6IZBETGD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Boosting Reinforcement Learning Algorithms in Continuous Robotic Reaching Tasks using Adaptive Potential Functions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Francisco Cruz, Lambert Schomaker, Yifei Chen","submitted_at":"2024-02-07T04:44:41Z","abstract_excerpt":"In reinforcement learning, reward shaping is an efficient way to guide the learning process of an agent, as the reward can indicate the optimal policy of the task. The potential-based reward shaping framework was proposed to guarantee policy invariance after reward shaping, where a potential function is used to calculate the shaping reward. In former work, we proposed a novel adaptive potential function (APF) method to learn the potential function concurrently with training the agent based on information collected by the agent during the training process, and examined the APF method in discret"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04581","kind":"arxiv","version":1},"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/2402.04581/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":"2026-07-05T07:42:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pyrjcsgQo9IhCCteUYV4CQd++FV6L2dRPsrD7/AAQVrC9BF7xk9kL2SeAKZAWBwSyaTNb6t5/8bKxYZK+5t0AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:36:50.978035Z"},"content_sha256":"75a13122aede3b7ab760f16295024b4e381b93f8a867cbfa210af61731768621","schema_version":"1.0","event_id":"sha256:75a13122aede3b7ab760f16295024b4e381b93f8a867cbfa210af61731768621"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SD4A5Z3M5WTT3WGRRU6IZBETGD/bundle.json","state_url":"https://pith.science/pith/SD4A5Z3M5WTT3WGRRU6IZBETGD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SD4A5Z3M5WTT3WGRRU6IZBETGD/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":"2026-07-07T04:36:50Z","links":{"resolver":"https://pith.science/pith/SD4A5Z3M5WTT3WGRRU6IZBETGD","bundle":"https://pith.science/pith/SD4A5Z3M5WTT3WGRRU6IZBETGD/bundle.json","state":"https://pith.science/pith/SD4A5Z3M5WTT3WGRRU6IZBETGD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SD4A5Z3M5WTT3WGRRU6IZBETGD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SD4A5Z3M5WTT3WGRRU6IZBETGD","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":"759ba4bd737cdcf9945bb5be5c2e7e32f623e7e526a214d152b7e00ccfe935da","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-02-07T04:44:41Z","title_canon_sha256":"4595ba0dfd4b59a974db95e380e3661423f4807837313570d89b1bed91b4bd18"},"schema_version":"1.0","source":{"id":"2402.04581","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.04581","created_at":"2026-07-05T07:42:29Z"},{"alias_kind":"arxiv_version","alias_value":"2402.04581v1","created_at":"2026-07-05T07:42:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04581","created_at":"2026-07-05T07:42:29Z"},{"alias_kind":"pith_short_12","alias_value":"SD4A5Z3M5WTT","created_at":"2026-07-05T07:42:29Z"},{"alias_kind":"pith_short_16","alias_value":"SD4A5Z3M5WTT3WGR","created_at":"2026-07-05T07:42:29Z"},{"alias_kind":"pith_short_8","alias_value":"SD4A5Z3M","created_at":"2026-07-05T07:42:29Z"}],"graph_snapshots":[{"event_id":"sha256:75a13122aede3b7ab760f16295024b4e381b93f8a867cbfa210af61731768621","target":"graph","created_at":"2026-07-05T07:42:29Z","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/2402.04581/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In reinforcement learning, reward shaping is an efficient way to guide the learning process of an agent, as the reward can indicate the optimal policy of the task. The potential-based reward shaping framework was proposed to guarantee policy invariance after reward shaping, where a potential function is used to calculate the shaping reward. In former work, we proposed a novel adaptive potential function (APF) method to learn the potential function concurrently with training the agent based on information collected by the agent during the training process, and examined the APF method in discret","authors_text":"Francisco Cruz, Lambert Schomaker, Yifei Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-02-07T04:44:41Z","title":"Boosting Reinforcement Learning Algorithms in Continuous Robotic Reaching Tasks using Adaptive Potential Functions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04581","kind":"arxiv","version":1},"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":"sha256:948ef158a006af19180d1507673800c417a3c27b898d5c395f051b5cd9ea3a51","target":"record","created_at":"2026-07-05T07:42:29Z","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":"759ba4bd737cdcf9945bb5be5c2e7e32f623e7e526a214d152b7e00ccfe935da","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-02-07T04:44:41Z","title_canon_sha256":"4595ba0dfd4b59a974db95e380e3661423f4807837313570d89b1bed91b4bd18"},"schema_version":"1.0","source":{"id":"2402.04581","kind":"arxiv","version":1}},"canonical_sha256":"90f80ee76ceda73dd8d18d3c8c849330c178ed50e12d6cef34a1b8224538dabf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"90f80ee76ceda73dd8d18d3c8c849330c178ed50e12d6cef34a1b8224538dabf","first_computed_at":"2026-07-05T07:42:29.175124Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:42:29.175124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Gy4TFneMdPmt38wRKkL6psYINeQ/JU31fmo/gdk1uf0MuqBxtr9Jz3kdNQEJLAAt61ZISTkcHFAzvh/+hVljBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:42:29.175609Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.04581","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:948ef158a006af19180d1507673800c417a3c27b898d5c395f051b5cd9ea3a51","sha256:75a13122aede3b7ab760f16295024b4e381b93f8a867cbfa210af61731768621"],"state_sha256":"4a23ab4ea6b3f464b39299392fefbb38b80526bb368381579e2ca6daf77e8df4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kATY3H1rs+DYSC764GrhBrTWBlewmLLbhPk6XEdfdWI8iBegLDQy9huWBWmnhxFd9Rq0QETbrJuQL11pzfKZCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T04:36:50.981942Z","bundle_sha256":"8e91d348dd6e9e22c163d896d31440f96b3c88b9afe168d849cbebdbac2eeb5b"}}