{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:DS5XIDUCNVDQIPAZKAJLEBXPZK","short_pith_number":"pith:DS5XIDUC","canonical_record":{"source":{"id":"2105.08666","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-18T16:50:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9387f2482b6daff155316c09ac3b5fadce70ce09fc663e3fb9e94eca34e097c5","abstract_canon_sha256":"dc5591396d7dbf87362e033b8dee303432b1ce846280bdc183abb1af4a621dae"},"schema_version":"1.0"},"canonical_sha256":"1cbb740e826d47043c195012b206efca8e4215cf296a1eb38f64f3f5e509ddfb","source":{"kind":"arxiv","id":"2105.08666","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.08666","created_at":"2026-07-05T08:46:14Z"},{"alias_kind":"arxiv_version","alias_value":"2105.08666v4","created_at":"2026-07-05T08:46:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.08666","created_at":"2026-07-05T08:46:14Z"},{"alias_kind":"pith_short_12","alias_value":"DS5XIDUCNVDQ","created_at":"2026-07-05T08:46:14Z"},{"alias_kind":"pith_short_16","alias_value":"DS5XIDUCNVDQIPAZ","created_at":"2026-07-05T08:46:14Z"},{"alias_kind":"pith_short_8","alias_value":"DS5XIDUC","created_at":"2026-07-05T08:46:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:DS5XIDUCNVDQIPAZKAJLEBXPZK","target":"record","payload":{"canonical_record":{"source":{"id":"2105.08666","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-18T16:50:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9387f2482b6daff155316c09ac3b5fadce70ce09fc663e3fb9e94eca34e097c5","abstract_canon_sha256":"dc5591396d7dbf87362e033b8dee303432b1ce846280bdc183abb1af4a621dae"},"schema_version":"1.0"},"canonical_sha256":"1cbb740e826d47043c195012b206efca8e4215cf296a1eb38f64f3f5e509ddfb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:14.395721Z","signature_b64":"30PF4v6b2Rycb9g+0XLgGzvOdxXejcT7eFHyQKTxQMJipgrmR23yS1A5VJfvpiQoV/Eub8SzMN3Fm5ru1MXqBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cbb740e826d47043c195012b206efca8e4215cf296a1eb38f64f3f5e509ddfb","last_reissued_at":"2026-07-05T08:46:14.395345Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:14.395345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.08666","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:46:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kcnES4TPbXr0mIkRrIrMTubNY+oa6zBaUAzlk+WtDGcUE5rP8+FLAZH2C2eu6+26fbvUE8k1PfDulMG2beSCDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T15:40:13.826303Z"},"content_sha256":"c3c8a57c4527805dee0a740520bf8be08e24f54e31286d9fe6c7bf3ac7abafa7","schema_version":"1.0","event_id":"sha256:c3c8a57c4527805dee0a740520bf8be08e24f54e31286d9fe6c7bf3ac7abafa7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:DS5XIDUCNVDQIPAZKAJLEBXPZK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning With Sparse-Executing Actions via Sparsity Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jing-cheng Pang, Shengyi Jiang, Tian Xu, Yang Yu, Yu-Ren Liu","submitted_at":"2021-05-18T16:50:42Z","abstract_excerpt":"Reinforcement learning (RL) has demonstrated impressive performance in decision-making tasks like embodied control, autonomous driving and financial trading. In many decision-making tasks, the agents often encounter the problem of executing actions under limited budgets. However, classic RL methods typically overlook the challenges posed by such sparse-executing actions. They operate under the assumption that all actions can be taken for a unlimited number of times, both in the formulation of the problem and in the development of effective algorithms. To tackle the issue of limited action exec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.08666","kind":"arxiv","version":4},"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/2105.08666/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":"2026-07-05T08:46:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oTyITzIUnaOV4Aw8dnKNSRMdzDONWMag40xer4D7Zh/YXKrbtL+tGNgKpH/N6pCPHtBMh6uqIslb9nTEQcLaDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T15:40:13.826845Z"},"content_sha256":"772f02b4c8d3d90755f24d6e57d134068a4f1aad13f66f7daa9b9542ce57f705","schema_version":"1.0","event_id":"sha256:772f02b4c8d3d90755f24d6e57d134068a4f1aad13f66f7daa9b9542ce57f705"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DS5XIDUCNVDQIPAZKAJLEBXPZK/bundle.json","state_url":"https://pith.science/pith/DS5XIDUCNVDQIPAZKAJLEBXPZK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DS5XIDUCNVDQIPAZKAJLEBXPZK/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":"2026-08-12T15:40:13Z","links":{"resolver":"https://pith.science/pith/DS5XIDUCNVDQIPAZKAJLEBXPZK","bundle":"https://pith.science/pith/DS5XIDUCNVDQIPAZKAJLEBXPZK/bundle.json","state":"https://pith.science/pith/DS5XIDUCNVDQIPAZKAJLEBXPZK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DS5XIDUCNVDQIPAZKAJLEBXPZK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:DS5XIDUCNVDQIPAZKAJLEBXPZK","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":"dc5591396d7dbf87362e033b8dee303432b1ce846280bdc183abb1af4a621dae","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-18T16:50:42Z","title_canon_sha256":"9387f2482b6daff155316c09ac3b5fadce70ce09fc663e3fb9e94eca34e097c5"},"schema_version":"1.0","source":{"id":"2105.08666","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.08666","created_at":"2026-07-05T08:46:14Z"},{"alias_kind":"arxiv_version","alias_value":"2105.08666v4","created_at":"2026-07-05T08:46:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.08666","created_at":"2026-07-05T08:46:14Z"},{"alias_kind":"pith_short_12","alias_value":"DS5XIDUCNVDQ","created_at":"2026-07-05T08:46:14Z"},{"alias_kind":"pith_short_16","alias_value":"DS5XIDUCNVDQIPAZ","created_at":"2026-07-05T08:46:14Z"},{"alias_kind":"pith_short_8","alias_value":"DS5XIDUC","created_at":"2026-07-05T08:46:14Z"}],"graph_snapshots":[{"event_id":"sha256:772f02b4c8d3d90755f24d6e57d134068a4f1aad13f66f7daa9b9542ce57f705","target":"graph","created_at":"2026-07-05T08:46:14Z","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/2105.08666/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has demonstrated impressive performance in decision-making tasks like embodied control, autonomous driving and financial trading. In many decision-making tasks, the agents often encounter the problem of executing actions under limited budgets. However, classic RL methods typically overlook the challenges posed by such sparse-executing actions. They operate under the assumption that all actions can be taken for a unlimited number of times, both in the formulation of the problem and in the development of effective algorithms. To tackle the issue of limited action exec","authors_text":"Jing-cheng Pang, Shengyi Jiang, Tian Xu, Yang Yu, Yu-Ren Liu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-18T16:50:42Z","title":"Reinforcement Learning With Sparse-Executing Actions via Sparsity Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.08666","kind":"arxiv","version":4},"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:c3c8a57c4527805dee0a740520bf8be08e24f54e31286d9fe6c7bf3ac7abafa7","target":"record","created_at":"2026-07-05T08:46:14Z","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":"dc5591396d7dbf87362e033b8dee303432b1ce846280bdc183abb1af4a621dae","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-18T16:50:42Z","title_canon_sha256":"9387f2482b6daff155316c09ac3b5fadce70ce09fc663e3fb9e94eca34e097c5"},"schema_version":"1.0","source":{"id":"2105.08666","kind":"arxiv","version":4}},"canonical_sha256":"1cbb740e826d47043c195012b206efca8e4215cf296a1eb38f64f3f5e509ddfb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1cbb740e826d47043c195012b206efca8e4215cf296a1eb38f64f3f5e509ddfb","first_computed_at":"2026-07-05T08:46:14.395345Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:46:14.395345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"30PF4v6b2Rycb9g+0XLgGzvOdxXejcT7eFHyQKTxQMJipgrmR23yS1A5VJfvpiQoV/Eub8SzMN3Fm5ru1MXqBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:46:14.395721Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.08666","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c3c8a57c4527805dee0a740520bf8be08e24f54e31286d9fe6c7bf3ac7abafa7","sha256:772f02b4c8d3d90755f24d6e57d134068a4f1aad13f66f7daa9b9542ce57f705"],"state_sha256":"ef99d3c1590a262989534ba93afba358c3118f936f2dc3fcda4fbc4784f37631"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G3yprdFw9fk9uPgW8vqPqHwEZ7se4QIE6K51FAD4Nuemb96EIWQBGTRIwAT65zhQ+7EfPFWnvKU6fk3aFeRwDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T15:40:13.831531Z","bundle_sha256":"693e27ee6da6dedbf8d985fe2bb8b588b1d556cf715d4f25fc0d6afc3e81050e"}}