{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZQUQXRKQEO45EU5NDN4JYHOM5X","short_pith_number":"pith:ZQUQXRKQ","canonical_record":{"source":{"id":"2412.10917","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-14T18:04:18Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"84792c14b5bbb98baf18b8061a084c470ad8700fe098a158528a04c13671a0d9","abstract_canon_sha256":"4b7556fd44033c716ccfc47fc18b5d61a13926447aa51000a062e7ed96fcd9df"},"schema_version":"1.0"},"canonical_sha256":"cc290bc55023b9d253ad1b789c1dccedcb4e9d2a2c1c8ce234ae7ff35d9a1fdb","source":{"kind":"arxiv","id":"2412.10917","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10917","created_at":"2026-07-05T11:04:42Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10917v2","created_at":"2026-07-05T11:04:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10917","created_at":"2026-07-05T11:04:42Z"},{"alias_kind":"pith_short_12","alias_value":"ZQUQXRKQEO45","created_at":"2026-07-05T11:04:42Z"},{"alias_kind":"pith_short_16","alias_value":"ZQUQXRKQEO45EU5N","created_at":"2026-07-05T11:04:42Z"},{"alias_kind":"pith_short_8","alias_value":"ZQUQXRKQ","created_at":"2026-07-05T11:04:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZQUQXRKQEO45EU5NDN4JYHOM5X","target":"record","payload":{"canonical_record":{"source":{"id":"2412.10917","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-14T18:04:18Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"84792c14b5bbb98baf18b8061a084c470ad8700fe098a158528a04c13671a0d9","abstract_canon_sha256":"4b7556fd44033c716ccfc47fc18b5d61a13926447aa51000a062e7ed96fcd9df"},"schema_version":"1.0"},"canonical_sha256":"cc290bc55023b9d253ad1b789c1dccedcb4e9d2a2c1c8ce234ae7ff35d9a1fdb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:42.848956Z","signature_b64":"2w+E42f6NGn2Z+4zShDgQ88jZeUK54MX0kx6C7ODFH1MFR8Vz6QW+GjQsXbsBHQHvHdcCrsuyVghfMJZ9F4mBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc290bc55023b9d253ad1b789c1dccedcb4e9d2a2c1c8ce234ae7ff35d9a1fdb","last_reissued_at":"2026-07-05T11:04:42.848537Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:42.848537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.10917","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":"2026-07-05T11:04:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Okw92bJujSzdlR4/OXkv5TlyE9OClaZWPRzD6S8c4Ak6rDJiV816AVXNgKmCb0eXbL/XbY6WooO6mxhOf2wIBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T15:19:55.704153Z"},"content_sha256":"96d8202d1f9b47819584ce2f7032e1cf1823c18a2699dfa693be380d4fe16e0a","schema_version":"1.0","event_id":"sha256:96d8202d1f9b47819584ce2f7032e1cf1823c18a2699dfa693be380d4fe16e0a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZQUQXRKQEO45EU5NDN4JYHOM5X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adaptive Reward Design for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Ingy Elsayed-Aly, Lu Feng, Minjae Kwon","submitted_at":"2024-12-14T18:04:18Z","abstract_excerpt":"There is a surge of interest in using formal languages such as Linear Temporal Logic (LTL) to precisely and succinctly specify complex tasks and derive reward functions for Reinforcement Learning (RL). However, existing methods often assign sparse rewards (e.g., giving a reward of 1 only if a task is completed and 0 otherwise). By providing feedback solely upon task completion, these methods fail to encourage successful subtask completion. This is particularly problematic in environments with inherent uncertainty, where task completion may be unreliable despite progress on intermediate goals. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10917","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/2412.10917/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":"2026-07-05T11:04:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9uWltLIr97YcgQLvNReGGwb+//FdrhkYqGc4qefF2rkY4Fpda0qd9f80V+Ju9cry0P1uw4EER/1DxZ283XueBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T15:19:55.706567Z"},"content_sha256":"34bd08dea05c45fe56913cc98f9d0f0619ad459a9f55c4302120359f17336993","schema_version":"1.0","event_id":"sha256:34bd08dea05c45fe56913cc98f9d0f0619ad459a9f55c4302120359f17336993"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZQUQXRKQEO45EU5NDN4JYHOM5X/bundle.json","state_url":"https://pith.science/pith/ZQUQXRKQEO45EU5NDN4JYHOM5X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZQUQXRKQEO45EU5NDN4JYHOM5X/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":"2026-08-13T15:19:55Z","links":{"resolver":"https://pith.science/pith/ZQUQXRKQEO45EU5NDN4JYHOM5X","bundle":"https://pith.science/pith/ZQUQXRKQEO45EU5NDN4JYHOM5X/bundle.json","state":"https://pith.science/pith/ZQUQXRKQEO45EU5NDN4JYHOM5X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZQUQXRKQEO45EU5NDN4JYHOM5X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZQUQXRKQEO45EU5NDN4JYHOM5X","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":"4b7556fd44033c716ccfc47fc18b5d61a13926447aa51000a062e7ed96fcd9df","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-14T18:04:18Z","title_canon_sha256":"84792c14b5bbb98baf18b8061a084c470ad8700fe098a158528a04c13671a0d9"},"schema_version":"1.0","source":{"id":"2412.10917","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10917","created_at":"2026-07-05T11:04:42Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10917v2","created_at":"2026-07-05T11:04:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10917","created_at":"2026-07-05T11:04:42Z"},{"alias_kind":"pith_short_12","alias_value":"ZQUQXRKQEO45","created_at":"2026-07-05T11:04:42Z"},{"alias_kind":"pith_short_16","alias_value":"ZQUQXRKQEO45EU5N","created_at":"2026-07-05T11:04:42Z"},{"alias_kind":"pith_short_8","alias_value":"ZQUQXRKQ","created_at":"2026-07-05T11:04:42Z"}],"graph_snapshots":[{"event_id":"sha256:34bd08dea05c45fe56913cc98f9d0f0619ad459a9f55c4302120359f17336993","target":"graph","created_at":"2026-07-05T11:04:42Z","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/2412.10917/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There is a surge of interest in using formal languages such as Linear Temporal Logic (LTL) to precisely and succinctly specify complex tasks and derive reward functions for Reinforcement Learning (RL). However, existing methods often assign sparse rewards (e.g., giving a reward of 1 only if a task is completed and 0 otherwise). By providing feedback solely upon task completion, these methods fail to encourage successful subtask completion. This is particularly problematic in environments with inherent uncertainty, where task completion may be unreliable despite progress on intermediate goals. ","authors_text":"Ingy Elsayed-Aly, Lu Feng, Minjae Kwon","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-14T18:04:18Z","title":"Adaptive Reward Design for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10917","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":"sha256:96d8202d1f9b47819584ce2f7032e1cf1823c18a2699dfa693be380d4fe16e0a","target":"record","created_at":"2026-07-05T11:04:42Z","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":"4b7556fd44033c716ccfc47fc18b5d61a13926447aa51000a062e7ed96fcd9df","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-14T18:04:18Z","title_canon_sha256":"84792c14b5bbb98baf18b8061a084c470ad8700fe098a158528a04c13671a0d9"},"schema_version":"1.0","source":{"id":"2412.10917","kind":"arxiv","version":2}},"canonical_sha256":"cc290bc55023b9d253ad1b789c1dccedcb4e9d2a2c1c8ce234ae7ff35d9a1fdb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc290bc55023b9d253ad1b789c1dccedcb4e9d2a2c1c8ce234ae7ff35d9a1fdb","first_computed_at":"2026-07-05T11:04:42.848537Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:42.848537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2w+E42f6NGn2Z+4zShDgQ88jZeUK54MX0kx6C7ODFH1MFR8Vz6QW+GjQsXbsBHQHvHdcCrsuyVghfMJZ9F4mBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:42.848956Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.10917","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:96d8202d1f9b47819584ce2f7032e1cf1823c18a2699dfa693be380d4fe16e0a","sha256:34bd08dea05c45fe56913cc98f9d0f0619ad459a9f55c4302120359f17336993"],"state_sha256":"a9408d115bfeca46990ca336b870dbd1eef3c74e02e23fcb24bcc318f500bf3a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7fQUU8PTYSh7f/2H89lwwgB1XcBEEIt9vwl4zDvKZsUIWnzF0lIfqEFwHFji+1B6fgI/wICbD5Tvof6EymeWCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T15:19:55.711613Z","bundle_sha256":"553fa357f40e9ec2a6a1c03fe46c49476bbc643518be6b7a81295b2d0965ca3d"}}