{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:LC3MN37BFOENZTRHXYCI5XEWJN","short_pith_number":"pith:LC3MN37B","canonical_record":{"source":{"id":"2205.15043","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-30T12:18:43Z","cross_cats_sorted":[],"title_canon_sha256":"6252a5d1b3c605ae38244d6a20e96b873894aac0225890fbd73bb56853b20e6b","abstract_canon_sha256":"da5bca86236da87545d238775c36aae4455aafd643e4c7f538436e8dadd6c2bb"},"schema_version":"1.0"},"canonical_sha256":"58b6c6efe12b88dcce27be048edc964b6b8f0df4aefd7c1b86d8db0a6103db27","source":{"kind":"arxiv","id":"2205.15043","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.15043","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"arxiv_version","alias_value":"2205.15043v2","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.15043","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"pith_short_12","alias_value":"LC3MN37BFOEN","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"pith_short_16","alias_value":"LC3MN37BFOENZTRH","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"pith_short_8","alias_value":"LC3MN37B","created_at":"2026-07-05T05:49:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:LC3MN37BFOENZTRHXYCI5XEWJN","target":"record","payload":{"canonical_record":{"source":{"id":"2205.15043","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-30T12:18:43Z","cross_cats_sorted":[],"title_canon_sha256":"6252a5d1b3c605ae38244d6a20e96b873894aac0225890fbd73bb56853b20e6b","abstract_canon_sha256":"da5bca86236da87545d238775c36aae4455aafd643e4c7f538436e8dadd6c2bb"},"schema_version":"1.0"},"canonical_sha256":"58b6c6efe12b88dcce27be048edc964b6b8f0df4aefd7c1b86d8db0a6103db27","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:49:13.379273Z","signature_b64":"+usRSYJw7/y643nxoNz633nNiEDehcLBl3c1xNKIQbwp9zeYYkrsU3e+APE83kOepj9XpWHhFz4uISyxQJySAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58b6c6efe12b88dcce27be048edc964b6b8f0df4aefd7c1b86d8db0a6103db27","last_reissued_at":"2026-07-05T05:49:13.378841Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:49:13.378841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.15043","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":"2026-07-05T05:49:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BwjwmMzQxeufDfoiZVfUOkccZuZwHHELx5qJ3LuODJb7Klg0ct5llsX2PdhnXpFmLdXr2fHBFRsi+VKoU6W5Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:54:26.849527Z"},"content_sha256":"e4c206197b705ffecf33e82c48898d9607ab6f53af431ba53a79f530df7f5ac5","schema_version":"1.0","event_id":"sha256:e4c206197b705ffecf33e82c48898d9607ab6f53af431ba53a79f530df7f5ac5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:LC3MN37BFOENZTRHXYCI5XEWJN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiatai Huang, Ling Pan, Longbo Huang, Pihe Hu, Yiqin Tan","submitted_at":"2022-05-30T12:18:43Z","abstract_excerpt":"Training deep reinforcement learning (DRL) models usually requires high computation costs. Therefore, compressing DRL models possesses immense potential for training acceleration and model deployment. However, existing methods that generate small models mainly adopt the knowledge distillation-based approach by iteratively training a dense network. As a result, the training process still demands massive computing resources. Indeed, sparse training from scratch in DRL has not been well explored and is particularly challenging due to non-stationarity in bootstrap training. In this work, we propos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.15043","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/2205.15043/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":"2026-07-05T05:49:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rMrifcpNtPpTiYw2sPMO/YOpsilJZkzubKNaN1S82RMTSS6n96FMzB+4cnP7cDKUK0wAeiYiG9zBakro/h4pDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:54:26.850403Z"},"content_sha256":"7a2ce68b9a09590cec962830fc824a0f69ab8617f8b4c470c1110df93daa35a4","schema_version":"1.0","event_id":"sha256:7a2ce68b9a09590cec962830fc824a0f69ab8617f8b4c470c1110df93daa35a4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LC3MN37BFOENZTRHXYCI5XEWJN/bundle.json","state_url":"https://pith.science/pith/LC3MN37BFOENZTRHXYCI5XEWJN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LC3MN37BFOENZTRHXYCI5XEWJN/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":"2026-08-08T02:54:26Z","links":{"resolver":"https://pith.science/pith/LC3MN37BFOENZTRHXYCI5XEWJN","bundle":"https://pith.science/pith/LC3MN37BFOENZTRHXYCI5XEWJN/bundle.json","state":"https://pith.science/pith/LC3MN37BFOENZTRHXYCI5XEWJN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LC3MN37BFOENZTRHXYCI5XEWJN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:LC3MN37BFOENZTRHXYCI5XEWJN","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":"da5bca86236da87545d238775c36aae4455aafd643e4c7f538436e8dadd6c2bb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-30T12:18:43Z","title_canon_sha256":"6252a5d1b3c605ae38244d6a20e96b873894aac0225890fbd73bb56853b20e6b"},"schema_version":"1.0","source":{"id":"2205.15043","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.15043","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"arxiv_version","alias_value":"2205.15043v2","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.15043","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"pith_short_12","alias_value":"LC3MN37BFOEN","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"pith_short_16","alias_value":"LC3MN37BFOENZTRH","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"pith_short_8","alias_value":"LC3MN37B","created_at":"2026-07-05T05:49:13Z"}],"graph_snapshots":[{"event_id":"sha256:7a2ce68b9a09590cec962830fc824a0f69ab8617f8b4c470c1110df93daa35a4","target":"graph","created_at":"2026-07-05T05:49:13Z","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/2205.15043/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training deep reinforcement learning (DRL) models usually requires high computation costs. Therefore, compressing DRL models possesses immense potential for training acceleration and model deployment. However, existing methods that generate small models mainly adopt the knowledge distillation-based approach by iteratively training a dense network. As a result, the training process still demands massive computing resources. Indeed, sparse training from scratch in DRL has not been well explored and is particularly challenging due to non-stationarity in bootstrap training. In this work, we propos","authors_text":"Jiatai Huang, Ling Pan, Longbo Huang, Pihe Hu, Yiqin Tan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-30T12:18:43Z","title":"RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.15043","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:e4c206197b705ffecf33e82c48898d9607ab6f53af431ba53a79f530df7f5ac5","target":"record","created_at":"2026-07-05T05:49:13Z","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":"da5bca86236da87545d238775c36aae4455aafd643e4c7f538436e8dadd6c2bb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-30T12:18:43Z","title_canon_sha256":"6252a5d1b3c605ae38244d6a20e96b873894aac0225890fbd73bb56853b20e6b"},"schema_version":"1.0","source":{"id":"2205.15043","kind":"arxiv","version":2}},"canonical_sha256":"58b6c6efe12b88dcce27be048edc964b6b8f0df4aefd7c1b86d8db0a6103db27","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"58b6c6efe12b88dcce27be048edc964b6b8f0df4aefd7c1b86d8db0a6103db27","first_computed_at":"2026-07-05T05:49:13.378841Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:49:13.378841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+usRSYJw7/y643nxoNz633nNiEDehcLBl3c1xNKIQbwp9zeYYkrsU3e+APE83kOepj9XpWHhFz4uISyxQJySAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:49:13.379273Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.15043","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e4c206197b705ffecf33e82c48898d9607ab6f53af431ba53a79f530df7f5ac5","sha256:7a2ce68b9a09590cec962830fc824a0f69ab8617f8b4c470c1110df93daa35a4"],"state_sha256":"1cd9b4e35b9c1b0d098fccf7aadcc885e61c0c0cb6aebec4e4bdc16bb9591bff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7MVohrB/vDrTGcE/e3WwChvJRihY11jVqznqbDDgkbQCykXKmwyTlYs2/SXx1FoEnfOn46ZSKBCPb+PL67NkCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T02:54:26.855759Z","bundle_sha256":"636f1d5cc262b0eb5c40bea40c2e1266fd5f5550b9ae03dba07019348d55cf48"}}