{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:U7E4KL6DL3LGRZIDU6DFOTYEGH","short_pith_number":"pith:U7E4KL6D","canonical_record":{"source":{"id":"2409.15755","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-09-24T05:25:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e18ca2b878fbee32a22ff5334c100e23deab1bc1470d2906e3b82598937fa68b","abstract_canon_sha256":"364ce1ce88aea5f4ed67a0ad1a4c55bad09eda2a1bc21e0289093821fd59ef3d"},"schema_version":"1.0"},"canonical_sha256":"a7c9c52fc35ed668e503a786574f0431df2fd83a41971760aeb6bee53a6e484a","source":{"kind":"arxiv","id":"2409.15755","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.15755","created_at":"2026-07-05T09:10:59Z"},{"alias_kind":"arxiv_version","alias_value":"2409.15755v1","created_at":"2026-07-05T09:10:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.15755","created_at":"2026-07-05T09:10:59Z"},{"alias_kind":"pith_short_12","alias_value":"U7E4KL6DL3LG","created_at":"2026-07-05T09:10:59Z"},{"alias_kind":"pith_short_16","alias_value":"U7E4KL6DL3LGRZID","created_at":"2026-07-05T09:10:59Z"},{"alias_kind":"pith_short_8","alias_value":"U7E4KL6D","created_at":"2026-07-05T09:10:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:U7E4KL6DL3LGRZIDU6DFOTYEGH","target":"record","payload":{"canonical_record":{"source":{"id":"2409.15755","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-09-24T05:25:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e18ca2b878fbee32a22ff5334c100e23deab1bc1470d2906e3b82598937fa68b","abstract_canon_sha256":"364ce1ce88aea5f4ed67a0ad1a4c55bad09eda2a1bc21e0289093821fd59ef3d"},"schema_version":"1.0"},"canonical_sha256":"a7c9c52fc35ed668e503a786574f0431df2fd83a41971760aeb6bee53a6e484a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:59.598780Z","signature_b64":"sOjTzrD7RIMwx03UF0wFi88W2/+7vvnp6inViPlgg43l5M6+H8IT4TbTU1r2Xtz6R63nLxu/KVTWAC0frrCkAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7c9c52fc35ed668e503a786574f0431df2fd83a41971760aeb6bee53a6e484a","last_reissued_at":"2026-07-05T09:10:59.598294Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:59.598294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.15755","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":"2026-07-05T09:10:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ucjinYLmIoeUktQqtCGV+Au+3OINVu34rP5yLYDU+V7moGhONtI7cwtMmw7QsW+i0chctGgjpsFm+KAV2TYTBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:34:57.136575Z"},"content_sha256":"fd802ac0c456ca5e7c4ecc7f7cb8841fbff4f0f68b0ea4c3a7afbd54b2f0a616","schema_version":"1.0","event_id":"sha256:fd802ac0c456ca5e7c4ecc7f7cb8841fbff4f0f68b0ea4c3a7afbd54b2f0a616"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:U7E4KL6DL3LGRZIDU6DFOTYEGH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stage-Wise Reward Shaping for Acrobatic Robots: A Constrained Multi-Objective Reinforcement Learning Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Dohyeong Kim, Gunmin Lee, Hyeokjin Kwon, Junseok Kim, Songhwai Oh","submitted_at":"2024-09-24T05:25:24Z","abstract_excerpt":"As the complexity of tasks addressed through reinforcement learning (RL) increases, the definition of reward functions also has become highly complicated. We introduce an RL method aimed at simplifying the reward-shaping process through intuitive strategies. Initially, instead of a single reward function composed of various terms, we define multiple reward and cost functions within a constrained multi-objective RL (CMORL) framework. For tasks involving sequential complex movements, we segment the task into distinct stages and define multiple rewards and costs for each stage. Finally, we introd"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.15755","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/2409.15755/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":"2026-07-05T09:10:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KhveMhmLpS3i4uFpx0Zs3nSbpeuNB2PLvnvhoC6wlJcHTMvramyX3q319RCr/pVjVy/jFzFXovHGEYc6dlQMBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:34:57.138030Z"},"content_sha256":"09642611853827001ff263ea0e66bdb030c0e205a3543c5c4e1befdbea96a0fa","schema_version":"1.0","event_id":"sha256:09642611853827001ff263ea0e66bdb030c0e205a3543c5c4e1befdbea96a0fa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U7E4KL6DL3LGRZIDU6DFOTYEGH/bundle.json","state_url":"https://pith.science/pith/U7E4KL6DL3LGRZIDU6DFOTYEGH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U7E4KL6DL3LGRZIDU6DFOTYEGH/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":"2026-08-07T18:34:57Z","links":{"resolver":"https://pith.science/pith/U7E4KL6DL3LGRZIDU6DFOTYEGH","bundle":"https://pith.science/pith/U7E4KL6DL3LGRZIDU6DFOTYEGH/bundle.json","state":"https://pith.science/pith/U7E4KL6DL3LGRZIDU6DFOTYEGH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U7E4KL6DL3LGRZIDU6DFOTYEGH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:U7E4KL6DL3LGRZIDU6DFOTYEGH","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":"364ce1ce88aea5f4ed67a0ad1a4c55bad09eda2a1bc21e0289093821fd59ef3d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-09-24T05:25:24Z","title_canon_sha256":"e18ca2b878fbee32a22ff5334c100e23deab1bc1470d2906e3b82598937fa68b"},"schema_version":"1.0","source":{"id":"2409.15755","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.15755","created_at":"2026-07-05T09:10:59Z"},{"alias_kind":"arxiv_version","alias_value":"2409.15755v1","created_at":"2026-07-05T09:10:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.15755","created_at":"2026-07-05T09:10:59Z"},{"alias_kind":"pith_short_12","alias_value":"U7E4KL6DL3LG","created_at":"2026-07-05T09:10:59Z"},{"alias_kind":"pith_short_16","alias_value":"U7E4KL6DL3LGRZID","created_at":"2026-07-05T09:10:59Z"},{"alias_kind":"pith_short_8","alias_value":"U7E4KL6D","created_at":"2026-07-05T09:10:59Z"}],"graph_snapshots":[{"event_id":"sha256:09642611853827001ff263ea0e66bdb030c0e205a3543c5c4e1befdbea96a0fa","target":"graph","created_at":"2026-07-05T09:10:59Z","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/2409.15755/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As the complexity of tasks addressed through reinforcement learning (RL) increases, the definition of reward functions also has become highly complicated. We introduce an RL method aimed at simplifying the reward-shaping process through intuitive strategies. Initially, instead of a single reward function composed of various terms, we define multiple reward and cost functions within a constrained multi-objective RL (CMORL) framework. For tasks involving sequential complex movements, we segment the task into distinct stages and define multiple rewards and costs for each stage. Finally, we introd","authors_text":"Dohyeong Kim, Gunmin Lee, Hyeokjin Kwon, Junseok Kim, Songhwai Oh","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-09-24T05:25:24Z","title":"Stage-Wise Reward Shaping for Acrobatic Robots: A Constrained Multi-Objective Reinforcement Learning Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.15755","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:fd802ac0c456ca5e7c4ecc7f7cb8841fbff4f0f68b0ea4c3a7afbd54b2f0a616","target":"record","created_at":"2026-07-05T09:10:59Z","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":"364ce1ce88aea5f4ed67a0ad1a4c55bad09eda2a1bc21e0289093821fd59ef3d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-09-24T05:25:24Z","title_canon_sha256":"e18ca2b878fbee32a22ff5334c100e23deab1bc1470d2906e3b82598937fa68b"},"schema_version":"1.0","source":{"id":"2409.15755","kind":"arxiv","version":1}},"canonical_sha256":"a7c9c52fc35ed668e503a786574f0431df2fd83a41971760aeb6bee53a6e484a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a7c9c52fc35ed668e503a786574f0431df2fd83a41971760aeb6bee53a6e484a","first_computed_at":"2026-07-05T09:10:59.598294Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:10:59.598294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sOjTzrD7RIMwx03UF0wFi88W2/+7vvnp6inViPlgg43l5M6+H8IT4TbTU1r2Xtz6R63nLxu/KVTWAC0frrCkAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:10:59.598780Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.15755","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd802ac0c456ca5e7c4ecc7f7cb8841fbff4f0f68b0ea4c3a7afbd54b2f0a616","sha256:09642611853827001ff263ea0e66bdb030c0e205a3543c5c4e1befdbea96a0fa"],"state_sha256":"31dbdf0c4f03720af9a59292c9854212843748b90c2b74b83699dcb595317088"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"te082c2p47oK35MSa/hieBE2REUQttp85eYePzlWW22adlR5Jbsd6v/XFAtAYX3Kwo1KKXvCkgnqdjdX47UrAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T18:34:57.147296Z","bundle_sha256":"6ac0c2e0b0a22203c5e4db465c89138a1a870917fc45b08326eda6bed196a881"}}