{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FRXIF2VTK3BPBVITTDXOOURE47","short_pith_number":"pith:FRXIF2VT","canonical_record":{"source":{"id":"2507.05251","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-07-07T17:58:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"43973a98f5f54f693b9b00656a73bd587757f6c950eff1451dcda0ff9b471dde","abstract_canon_sha256":"6a2e3e2b333f5ee422ccca5868c6db59b0decc9f7a6f83d900d0d1075223df1d"},"schema_version":"1.0"},"canonical_sha256":"2c6e82eab356c2f0d51398eee75224e7edb4a7481b548b750273fdf13f911e11","source":{"kind":"arxiv","id":"2507.05251","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.05251","created_at":"2026-07-05T11:33:11Z"},{"alias_kind":"arxiv_version","alias_value":"2507.05251v1","created_at":"2026-07-05T11:33:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05251","created_at":"2026-07-05T11:33:11Z"},{"alias_kind":"pith_short_12","alias_value":"FRXIF2VTK3BP","created_at":"2026-07-05T11:33:11Z"},{"alias_kind":"pith_short_16","alias_value":"FRXIF2VTK3BPBVIT","created_at":"2026-07-05T11:33:11Z"},{"alias_kind":"pith_short_8","alias_value":"FRXIF2VT","created_at":"2026-07-05T11:33:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FRXIF2VTK3BPBVITTDXOOURE47","target":"record","payload":{"canonical_record":{"source":{"id":"2507.05251","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-07-07T17:58:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"43973a98f5f54f693b9b00656a73bd587757f6c950eff1451dcda0ff9b471dde","abstract_canon_sha256":"6a2e3e2b333f5ee422ccca5868c6db59b0decc9f7a6f83d900d0d1075223df1d"},"schema_version":"1.0"},"canonical_sha256":"2c6e82eab356c2f0d51398eee75224e7edb4a7481b548b750273fdf13f911e11","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:11.259676Z","signature_b64":"ITj7nFJ6YPz+8g196Exasc05gB+gcDYujzrTL6I4x2gEXXO0p/INCr5MB94fjwi38B3RLtPITyzGBbxE3T3WBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c6e82eab356c2f0d51398eee75224e7edb4a7481b548b750273fdf13f911e11","last_reissued_at":"2026-07-05T11:33:11.259242Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:11.259242Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.05251","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":"2026-07-05T11:33:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"71OTOPUqto45tBUFoFZX/Suh5TU3dv36/gIpfeU4JPF8FxCT9A2DuolnhdUTImpg9FXVmaRp9sVvvVZeFQeNAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T21:16:21.442650Z"},"content_sha256":"72384d702f94167b0cc7e29121f4a09474db9d9aa4f75df3ed5f36f4121689d5","schema_version":"1.0","event_id":"sha256:72384d702f94167b0cc7e29121f4a09474db9d9aa4f75df3ed5f36f4121689d5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FRXIF2VTK3BPBVITTDXOOURE47","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Action Space Reduction Strategies for Reinforcement Learning in Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Elahe Delavari, Feeza Khan Khanzada, Jaerock Kwon","submitted_at":"2025-07-07T17:58:08Z","abstract_excerpt":"Reinforcement Learning (RL) offers a promising framework for autonomous driving by enabling agents to learn control policies through interaction with environments. However, large and high-dimensional action spaces often used to support fine-grained control can impede training efficiency and increase exploration costs. In this study, we introduce and evaluate two novel structured action space modification strategies for RL in autonomous driving: dynamic masking and relative action space reduction. These approaches are systematically compared against fixed reduction schemes and full action space"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05251","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/2507.05251/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":"2026-07-05T11:33:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h+WStpA+0EM7Mk4b8t2PhZ6Ki9xqfn2LD/c8dk7CnXLLYgGExnnttR8DtFw7uC5stT5oE1aVJeiAhk7rmYY5Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T21:16:21.443314Z"},"content_sha256":"52b171ea7c30030fbfaaa077f44c6bba46c2c8523702e4ee417d665be7b582f6","schema_version":"1.0","event_id":"sha256:52b171ea7c30030fbfaaa077f44c6bba46c2c8523702e4ee417d665be7b582f6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FRXIF2VTK3BPBVITTDXOOURE47/bundle.json","state_url":"https://pith.science/pith/FRXIF2VTK3BPBVITTDXOOURE47/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FRXIF2VTK3BPBVITTDXOOURE47/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":"2026-08-10T21:16:21Z","links":{"resolver":"https://pith.science/pith/FRXIF2VTK3BPBVITTDXOOURE47","bundle":"https://pith.science/pith/FRXIF2VTK3BPBVITTDXOOURE47/bundle.json","state":"https://pith.science/pith/FRXIF2VTK3BPBVITTDXOOURE47/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FRXIF2VTK3BPBVITTDXOOURE47/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FRXIF2VTK3BPBVITTDXOOURE47","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":"6a2e3e2b333f5ee422ccca5868c6db59b0decc9f7a6f83d900d0d1075223df1d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-07-07T17:58:08Z","title_canon_sha256":"43973a98f5f54f693b9b00656a73bd587757f6c950eff1451dcda0ff9b471dde"},"schema_version":"1.0","source":{"id":"2507.05251","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.05251","created_at":"2026-07-05T11:33:11Z"},{"alias_kind":"arxiv_version","alias_value":"2507.05251v1","created_at":"2026-07-05T11:33:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05251","created_at":"2026-07-05T11:33:11Z"},{"alias_kind":"pith_short_12","alias_value":"FRXIF2VTK3BP","created_at":"2026-07-05T11:33:11Z"},{"alias_kind":"pith_short_16","alias_value":"FRXIF2VTK3BPBVIT","created_at":"2026-07-05T11:33:11Z"},{"alias_kind":"pith_short_8","alias_value":"FRXIF2VT","created_at":"2026-07-05T11:33:11Z"}],"graph_snapshots":[{"event_id":"sha256:52b171ea7c30030fbfaaa077f44c6bba46c2c8523702e4ee417d665be7b582f6","target":"graph","created_at":"2026-07-05T11:33:11Z","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/2507.05251/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) offers a promising framework for autonomous driving by enabling agents to learn control policies through interaction with environments. However, large and high-dimensional action spaces often used to support fine-grained control can impede training efficiency and increase exploration costs. In this study, we introduce and evaluate two novel structured action space modification strategies for RL in autonomous driving: dynamic masking and relative action space reduction. These approaches are systematically compared against fixed reduction schemes and full action space","authors_text":"Elahe Delavari, Feeza Khan Khanzada, Jaerock Kwon","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-07-07T17:58:08Z","title":"Action Space Reduction Strategies for Reinforcement Learning in Autonomous Driving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05251","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":"sha256:72384d702f94167b0cc7e29121f4a09474db9d9aa4f75df3ed5f36f4121689d5","target":"record","created_at":"2026-07-05T11:33:11Z","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":"6a2e3e2b333f5ee422ccca5868c6db59b0decc9f7a6f83d900d0d1075223df1d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-07-07T17:58:08Z","title_canon_sha256":"43973a98f5f54f693b9b00656a73bd587757f6c950eff1451dcda0ff9b471dde"},"schema_version":"1.0","source":{"id":"2507.05251","kind":"arxiv","version":1}},"canonical_sha256":"2c6e82eab356c2f0d51398eee75224e7edb4a7481b548b750273fdf13f911e11","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c6e82eab356c2f0d51398eee75224e7edb4a7481b548b750273fdf13f911e11","first_computed_at":"2026-07-05T11:33:11.259242Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:11.259242Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ITj7nFJ6YPz+8g196Exasc05gB+gcDYujzrTL6I4x2gEXXO0p/INCr5MB94fjwi38B3RLtPITyzGBbxE3T3WBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:11.259676Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.05251","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72384d702f94167b0cc7e29121f4a09474db9d9aa4f75df3ed5f36f4121689d5","sha256:52b171ea7c30030fbfaaa077f44c6bba46c2c8523702e4ee417d665be7b582f6"],"state_sha256":"95d5bdd87b50fd2042c436d8c169269159972926d01a83a698a55c1942e18298"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Sy+JvFIrkBlse2ihiO7Rue0Jz0P68kmAEhJhf+asPxESQ+Nn7t9xmWqJq/kB6UyUJ1rxuPGehKirs/kLEGnoCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T21:16:21.448318Z","bundle_sha256":"6ac71605a8d57a559ecc0911ea1c3ea6b3c4e6318d5fc2d5d7b1fbcb2d3506f9"}}