{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XONAHMGMSCXVZM3EDDAPDNZCRR","short_pith_number":"pith:XONAHMGM","canonical_record":{"source":{"id":"2507.00030","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T20:04:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"41f8d2748ea15f7d1214c37fbe4618dd49e4ecf7e83019dd631373083bac3806","abstract_canon_sha256":"cf38bfa0586ea482e4cadce19a15f4d42075964dc55e31d95d126f8f79bd53c9"},"schema_version":"1.0"},"canonical_sha256":"bb9a03b0cc90af5cb36418c0f1b7228c5a9880bca7afbf652e0e3bcb6a716fea","source":{"kind":"arxiv","id":"2507.00030","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.00030","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"arxiv_version","alias_value":"2507.00030v1","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00030","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"pith_short_12","alias_value":"XONAHMGMSCXV","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"pith_short_16","alias_value":"XONAHMGMSCXVZM3E","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"pith_short_8","alias_value":"XONAHMGM","created_at":"2026-07-05T11:29:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XONAHMGMSCXVZM3EDDAPDNZCRR","target":"record","payload":{"canonical_record":{"source":{"id":"2507.00030","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T20:04:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"41f8d2748ea15f7d1214c37fbe4618dd49e4ecf7e83019dd631373083bac3806","abstract_canon_sha256":"cf38bfa0586ea482e4cadce19a15f4d42075964dc55e31d95d126f8f79bd53c9"},"schema_version":"1.0"},"canonical_sha256":"bb9a03b0cc90af5cb36418c0f1b7228c5a9880bca7afbf652e0e3bcb6a716fea","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:35.378327Z","signature_b64":"4h+OWp4ZrrYlfZWdVxQyF53o2NGzDRLfyLTPhAhSuR2G3KWHygK+6l1opxxBJMZl2Cp+0c8dO/ojGKjRHQ5ZDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb9a03b0cc90af5cb36418c0f1b7228c5a9880bca7afbf652e0e3bcb6a716fea","last_reissued_at":"2026-07-05T11:29:35.377831Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:35.377831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.00030","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":"2026-07-05T11:29:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SfAROkjij3l5WY9uHORBpm8/fUX8DnomPD61i/jcBRK9JkNfwCyA6xtblt9KRuxgBq2+8rkFqF4/h8qmmCx6Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T09:31:29.638531Z"},"content_sha256":"88eeba4d90d1874d25ad286c00dbbbde5d42740727af52535581aaebc72111c7","schema_version":"1.0","event_id":"sha256:88eeba4d90d1874d25ad286c00dbbbde5d42740727af52535581aaebc72111c7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XONAHMGMSCXVZM3EDDAPDNZCRR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adaptive Action Duration with Contextual Bandits for Deep Reinforcement Learning in Dynamic Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Abhishek Verma, Balaraman Ravindran, Nallarasan V","submitted_at":"2025-06-17T20:04:53Z","abstract_excerpt":"Deep Reinforcement Learning (DRL) has achieved remarkable success in complex sequential decision-making tasks, such as playing Atari 2600 games and mastering board games. A critical yet underexplored aspect of DRL is the temporal scale of action execution. We propose a novel paradigm that integrates contextual bandits with DRL to adaptively select action durations, enhancing policy flexibility and computational efficiency. Our approach augments a Deep Q-Network (DQN) with a contextual bandit module that learns to choose optimal action repetition rates based on state contexts. Experiments on At"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00030","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/2507.00030/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":"2026-07-05T11:29:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+uWFxE9O1uSLmJ60+2p2S4WJsqHzsOC7sVkbE32wOXw7PSQ+VtPx3wiM/1sPMEPXWHhm855Q4G9WCyv6lUNvCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T09:31:29.639021Z"},"content_sha256":"e421196ce1e96e9d27b8bb2cd839b8fc17e4c2c53e3fe478f5cd717d351538c3","schema_version":"1.0","event_id":"sha256:e421196ce1e96e9d27b8bb2cd839b8fc17e4c2c53e3fe478f5cd717d351538c3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XONAHMGMSCXVZM3EDDAPDNZCRR/bundle.json","state_url":"https://pith.science/pith/XONAHMGMSCXVZM3EDDAPDNZCRR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XONAHMGMSCXVZM3EDDAPDNZCRR/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":"2026-08-12T09:31:29Z","links":{"resolver":"https://pith.science/pith/XONAHMGMSCXVZM3EDDAPDNZCRR","bundle":"https://pith.science/pith/XONAHMGMSCXVZM3EDDAPDNZCRR/bundle.json","state":"https://pith.science/pith/XONAHMGMSCXVZM3EDDAPDNZCRR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XONAHMGMSCXVZM3EDDAPDNZCRR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XONAHMGMSCXVZM3EDDAPDNZCRR","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":"cf38bfa0586ea482e4cadce19a15f4d42075964dc55e31d95d126f8f79bd53c9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T20:04:53Z","title_canon_sha256":"41f8d2748ea15f7d1214c37fbe4618dd49e4ecf7e83019dd631373083bac3806"},"schema_version":"1.0","source":{"id":"2507.00030","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.00030","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"arxiv_version","alias_value":"2507.00030v1","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00030","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"pith_short_12","alias_value":"XONAHMGMSCXV","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"pith_short_16","alias_value":"XONAHMGMSCXVZM3E","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"pith_short_8","alias_value":"XONAHMGM","created_at":"2026-07-05T11:29:35Z"}],"graph_snapshots":[{"event_id":"sha256:e421196ce1e96e9d27b8bb2cd839b8fc17e4c2c53e3fe478f5cd717d351538c3","target":"graph","created_at":"2026-07-05T11:29:35Z","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/2507.00030/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep Reinforcement Learning (DRL) has achieved remarkable success in complex sequential decision-making tasks, such as playing Atari 2600 games and mastering board games. A critical yet underexplored aspect of DRL is the temporal scale of action execution. We propose a novel paradigm that integrates contextual bandits with DRL to adaptively select action durations, enhancing policy flexibility and computational efficiency. Our approach augments a Deep Q-Network (DQN) with a contextual bandit module that learns to choose optimal action repetition rates based on state contexts. Experiments on At","authors_text":"Abhishek Verma, Balaraman Ravindran, Nallarasan V","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T20:04:53Z","title":"Adaptive Action Duration with Contextual Bandits for Deep Reinforcement Learning in Dynamic Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00030","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":"sha256:88eeba4d90d1874d25ad286c00dbbbde5d42740727af52535581aaebc72111c7","target":"record","created_at":"2026-07-05T11:29:35Z","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":"cf38bfa0586ea482e4cadce19a15f4d42075964dc55e31d95d126f8f79bd53c9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T20:04:53Z","title_canon_sha256":"41f8d2748ea15f7d1214c37fbe4618dd49e4ecf7e83019dd631373083bac3806"},"schema_version":"1.0","source":{"id":"2507.00030","kind":"arxiv","version":1}},"canonical_sha256":"bb9a03b0cc90af5cb36418c0f1b7228c5a9880bca7afbf652e0e3bcb6a716fea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb9a03b0cc90af5cb36418c0f1b7228c5a9880bca7afbf652e0e3bcb6a716fea","first_computed_at":"2026-07-05T11:29:35.377831Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:35.377831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4h+OWp4ZrrYlfZWdVxQyF53o2NGzDRLfyLTPhAhSuR2G3KWHygK+6l1opxxBJMZl2Cp+0c8dO/ojGKjRHQ5ZDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:35.378327Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.00030","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:88eeba4d90d1874d25ad286c00dbbbde5d42740727af52535581aaebc72111c7","sha256:e421196ce1e96e9d27b8bb2cd839b8fc17e4c2c53e3fe478f5cd717d351538c3"],"state_sha256":"4183f48a3bb41e8e27ba78dc506627438fac8a0157ff2aa9442b32651bcfbcc0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WKX4BMQIr7HcPxiFglU2V4ziC7Hm+o+obTiZRViSg5WAd5Hk9E+4ycIcDav3dmIL1S1OneJ1wbEaDeDb2CNvBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T09:31:29.643839Z","bundle_sha256":"4a6591b062fe5328d5f34686d749205914b8f86ac1623aa370fe38e5ab6236cb"}}