{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BYV4XLD77CZ4LBWFRTBD2BEFB3","short_pith_number":"pith:BYV4XLD7","canonical_record":{"source":{"id":"2505.10802","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T02:43:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"26786e3a304e8fd96cbd96a24aa1ffe7946233e2063d998cac93655130f136af","abstract_canon_sha256":"7162c683ae2af5182fca0d00825e07ccea3f3ccfeeafe6b9c0c4ea442cda6945"},"schema_version":"1.0"},"canonical_sha256":"0e2bcbac7ff8b3c586c58cc23d04850ef02e59c62002ff9051b81576afb9ef56","source":{"kind":"arxiv","id":"2505.10802","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.10802","created_at":"2026-07-05T11:04:05Z"},{"alias_kind":"arxiv_version","alias_value":"2505.10802v1","created_at":"2026-07-05T11:04:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.10802","created_at":"2026-07-05T11:04:05Z"},{"alias_kind":"pith_short_12","alias_value":"BYV4XLD77CZ4","created_at":"2026-07-05T11:04:05Z"},{"alias_kind":"pith_short_16","alias_value":"BYV4XLD77CZ4LBWF","created_at":"2026-07-05T11:04:05Z"},{"alias_kind":"pith_short_8","alias_value":"BYV4XLD7","created_at":"2026-07-05T11:04:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BYV4XLD77CZ4LBWFRTBD2BEFB3","target":"record","payload":{"canonical_record":{"source":{"id":"2505.10802","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T02:43:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"26786e3a304e8fd96cbd96a24aa1ffe7946233e2063d998cac93655130f136af","abstract_canon_sha256":"7162c683ae2af5182fca0d00825e07ccea3f3ccfeeafe6b9c0c4ea442cda6945"},"schema_version":"1.0"},"canonical_sha256":"0e2bcbac7ff8b3c586c58cc23d04850ef02e59c62002ff9051b81576afb9ef56","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:05.994466Z","signature_b64":"pviVEjcGnQG1NUYibwcvfvJoRIGGSw9tnaEUa0j5UHPU4u7BeZw191RpCseqJVs8GmW75+BGAUS0WgcWuBvCBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e2bcbac7ff8b3c586c58cc23d04850ef02e59c62002ff9051b81576afb9ef56","last_reissued_at":"2026-07-05T11:04:05.993926Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:05.993926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.10802","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":"2026-07-05T11:04:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g/bnBvZb2K0oGeIxYaQoL5ZcvKD0avLEb3e8rO5C+YibUQjDnm0CQP2bH5hQBK4S3h2+iA4mV0J7HZoVXUfbDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:18:11.153956Z"},"content_sha256":"31f71c52ec633fdc3f03acc88cfd29e20942f9d6b9b24f57d67e3ca27b61b4c6","schema_version":"1.0","event_id":"sha256:31f71c52ec633fdc3f03acc88cfd29e20942f9d6b9b24f57d67e3ca27b61b4c6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BYV4XLD77CZ4LBWFRTBD2BEFB3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Attention-Based Reward Shaping for Sparse and Delayed Rewards","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ian Holmes, Min Chi","submitted_at":"2025-05-16T02:43:05Z","abstract_excerpt":"Sparse and delayed reward functions pose a significant obstacle for real-world Reinforcement Learning (RL) applications. In this work, we propose Attention-based REward Shaping (ARES), a general and robust algorithm which uses a transformer's attention mechanism to generate shaped rewards and create a dense reward function for any environment. ARES requires a set of episodes and their final returns as input. It can be trained entirely offline and is able to generate meaningful shaped rewards even when using small datasets or episodes produced by agents taking random actions. ARES is compatible"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.10802","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/2505.10802/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":"2026-07-05T11:04:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8rS377qvsz2zvC3+DSUvZuue7Id/n3H2TAEDwX7kiJGicULsUmn9F+bX8kh+zcSXFwCCjBo5AAsqMUo1kRDVBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:18:11.154469Z"},"content_sha256":"1a28935b7eb2d5629d4c6a59e5973d4c2f81294b2b0a17cf93eef57d5c6cfb31","schema_version":"1.0","event_id":"sha256:1a28935b7eb2d5629d4c6a59e5973d4c2f81294b2b0a17cf93eef57d5c6cfb31"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BYV4XLD77CZ4LBWFRTBD2BEFB3/bundle.json","state_url":"https://pith.science/pith/BYV4XLD77CZ4LBWFRTBD2BEFB3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BYV4XLD77CZ4LBWFRTBD2BEFB3/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":"2026-08-05T02:18:11Z","links":{"resolver":"https://pith.science/pith/BYV4XLD77CZ4LBWFRTBD2BEFB3","bundle":"https://pith.science/pith/BYV4XLD77CZ4LBWFRTBD2BEFB3/bundle.json","state":"https://pith.science/pith/BYV4XLD77CZ4LBWFRTBD2BEFB3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BYV4XLD77CZ4LBWFRTBD2BEFB3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BYV4XLD77CZ4LBWFRTBD2BEFB3","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":"7162c683ae2af5182fca0d00825e07ccea3f3ccfeeafe6b9c0c4ea442cda6945","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T02:43:05Z","title_canon_sha256":"26786e3a304e8fd96cbd96a24aa1ffe7946233e2063d998cac93655130f136af"},"schema_version":"1.0","source":{"id":"2505.10802","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.10802","created_at":"2026-07-05T11:04:05Z"},{"alias_kind":"arxiv_version","alias_value":"2505.10802v1","created_at":"2026-07-05T11:04:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.10802","created_at":"2026-07-05T11:04:05Z"},{"alias_kind":"pith_short_12","alias_value":"BYV4XLD77CZ4","created_at":"2026-07-05T11:04:05Z"},{"alias_kind":"pith_short_16","alias_value":"BYV4XLD77CZ4LBWF","created_at":"2026-07-05T11:04:05Z"},{"alias_kind":"pith_short_8","alias_value":"BYV4XLD7","created_at":"2026-07-05T11:04:05Z"}],"graph_snapshots":[{"event_id":"sha256:1a28935b7eb2d5629d4c6a59e5973d4c2f81294b2b0a17cf93eef57d5c6cfb31","target":"graph","created_at":"2026-07-05T11:04:05Z","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/2505.10802/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sparse and delayed reward functions pose a significant obstacle for real-world Reinforcement Learning (RL) applications. In this work, we propose Attention-based REward Shaping (ARES), a general and robust algorithm which uses a transformer's attention mechanism to generate shaped rewards and create a dense reward function for any environment. ARES requires a set of episodes and their final returns as input. It can be trained entirely offline and is able to generate meaningful shaped rewards even when using small datasets or episodes produced by agents taking random actions. ARES is compatible","authors_text":"Ian Holmes, Min Chi","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T02:43:05Z","title":"Attention-Based Reward Shaping for Sparse and Delayed Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.10802","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":"sha256:31f71c52ec633fdc3f03acc88cfd29e20942f9d6b9b24f57d67e3ca27b61b4c6","target":"record","created_at":"2026-07-05T11:04:05Z","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":"7162c683ae2af5182fca0d00825e07ccea3f3ccfeeafe6b9c0c4ea442cda6945","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T02:43:05Z","title_canon_sha256":"26786e3a304e8fd96cbd96a24aa1ffe7946233e2063d998cac93655130f136af"},"schema_version":"1.0","source":{"id":"2505.10802","kind":"arxiv","version":1}},"canonical_sha256":"0e2bcbac7ff8b3c586c58cc23d04850ef02e59c62002ff9051b81576afb9ef56","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e2bcbac7ff8b3c586c58cc23d04850ef02e59c62002ff9051b81576afb9ef56","first_computed_at":"2026-07-05T11:04:05.993926Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:05.993926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pviVEjcGnQG1NUYibwcvfvJoRIGGSw9tnaEUa0j5UHPU4u7BeZw191RpCseqJVs8GmW75+BGAUS0WgcWuBvCBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:05.994466Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.10802","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:31f71c52ec633fdc3f03acc88cfd29e20942f9d6b9b24f57d67e3ca27b61b4c6","sha256:1a28935b7eb2d5629d4c6a59e5973d4c2f81294b2b0a17cf93eef57d5c6cfb31"],"state_sha256":"c0a62ad8355b14fd76f20db7bdcd78de20a40a5e13012204c560c75a86b365d8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uAXXdY3MZHkMIz49No5k7bC5sY+Sgq8qXjAqWODplX8jt4UzbC5uKBKOawahzUeoQI9B4n/sutnJTZwB+L0/CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T02:18:11.158451Z","bundle_sha256":"175bc581ec1a43e617f9ef8c18149c1360decde7e3609d33d8990afafec24be6"}}