{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:HVDRPKNYM7SZ65PF77YWIFFA7K","short_pith_number":"pith:HVDRPKNY","canonical_record":{"source":{"id":"2304.12778","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-25T13:01:21Z","cross_cats_sorted":["cs.AI","cs.DC"],"title_canon_sha256":"026f82ca5ceb3c79f9e6d0ebe241b589cc90ae90af9719c67bab302b1250cf56","abstract_canon_sha256":"10cecef2c5417c804e398d1d0287039fe70708a703aedd99fa7e3ed4d8416fd0"},"schema_version":"1.0"},"canonical_sha256":"3d4717a9b867e59f75e5fff16414a0faa011e9c98c4aa02e605b2bffbbfa75b1","source":{"kind":"arxiv","id":"2304.12778","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.12778","created_at":"2026-07-05T08:56:12Z"},{"alias_kind":"arxiv_version","alias_value":"2304.12778v2","created_at":"2026-07-05T08:56:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.12778","created_at":"2026-07-05T08:56:12Z"},{"alias_kind":"pith_short_12","alias_value":"HVDRPKNYM7SZ","created_at":"2026-07-05T08:56:12Z"},{"alias_kind":"pith_short_16","alias_value":"HVDRPKNYM7SZ65PF","created_at":"2026-07-05T08:56:12Z"},{"alias_kind":"pith_short_8","alias_value":"HVDRPKNY","created_at":"2026-07-05T08:56:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:HVDRPKNYM7SZ65PF77YWIFFA7K","target":"record","payload":{"canonical_record":{"source":{"id":"2304.12778","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-25T13:01:21Z","cross_cats_sorted":["cs.AI","cs.DC"],"title_canon_sha256":"026f82ca5ceb3c79f9e6d0ebe241b589cc90ae90af9719c67bab302b1250cf56","abstract_canon_sha256":"10cecef2c5417c804e398d1d0287039fe70708a703aedd99fa7e3ed4d8416fd0"},"schema_version":"1.0"},"canonical_sha256":"3d4717a9b867e59f75e5fff16414a0faa011e9c98c4aa02e605b2bffbbfa75b1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:12.360819Z","signature_b64":"fpUG60bAUdmbMXbnmzu6+4RbXaIl7OKvRa9gSwyNonL7Smzq17hPiSTDgzkcGSYTWqMaPLZpmIQvA262zigPDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d4717a9b867e59f75e5fff16414a0faa011e9c98c4aa02e605b2bffbbfa75b1","last_reissued_at":"2026-07-05T08:56:12.360334Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:12.360334Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.12778","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":"2026-07-05T08:56:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HgxiSvjdfSyLTPRNNvagQjzA5/MZkU0w7lfYbjsbg6giovk7LzSBCtCDlsnxGVaGQ8s5m+I/ENOU8nju3HrMBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T05:47:06.048381Z"},"content_sha256":"c55c2d1f60d6fb325b65bd733f0a7df377cb8443f75c2050fda4bfec1f49f1cb","schema_version":"1.0","event_id":"sha256:c55c2d1f60d6fb325b65bd733f0a7df377cb8443f75c2050fda4bfec1f49f1cb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:HVDRPKNYM7SZ65PF77YWIFFA7K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Loss- and Reward-Weighting for Efficient Distributed Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Kristian Muri Knausg{\\aa}rd, Martin Holen, Morten Goodwin, Per-Arne Andersen","submitted_at":"2023-04-25T13:01:21Z","abstract_excerpt":"This paper introduces two learning schemes for distributed agents in Reinforcement Learning (RL) environments, namely Reward-Weighted (R-Weighted) and Loss-Weighted (L-Weighted) gradient merger. The R/L weighted methods replace standard practices for training multiple agents, such as summing or averaging the gradients. The core of our methods is to scale the gradient of each actor based on how high the reward (for R-Weighted) or the loss (for L-Weighted) is compared to the other actors. During training, each agent operates in differently initialized versions of the same environment, which give"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.12778","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/2304.12778/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":"2026-07-05T08:56:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kixx/10WicwEDRYT1SakBS7qRsC37CkAsN6gTJCdfwBjMzKkgKEckxkAV6EkhSJAO4GfW1Z9OOOk0zdTwLBdCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T05:47:06.049079Z"},"content_sha256":"a2389bc8e863200198c29af32cd2a35ee3019128fb3de01d6fb92f870bf9028b","schema_version":"1.0","event_id":"sha256:a2389bc8e863200198c29af32cd2a35ee3019128fb3de01d6fb92f870bf9028b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HVDRPKNYM7SZ65PF77YWIFFA7K/bundle.json","state_url":"https://pith.science/pith/HVDRPKNYM7SZ65PF77YWIFFA7K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HVDRPKNYM7SZ65PF77YWIFFA7K/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":"2026-08-21T05:47:06Z","links":{"resolver":"https://pith.science/pith/HVDRPKNYM7SZ65PF77YWIFFA7K","bundle":"https://pith.science/pith/HVDRPKNYM7SZ65PF77YWIFFA7K/bundle.json","state":"https://pith.science/pith/HVDRPKNYM7SZ65PF77YWIFFA7K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HVDRPKNYM7SZ65PF77YWIFFA7K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HVDRPKNYM7SZ65PF77YWIFFA7K","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":"10cecef2c5417c804e398d1d0287039fe70708a703aedd99fa7e3ed4d8416fd0","cross_cats_sorted":["cs.AI","cs.DC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-25T13:01:21Z","title_canon_sha256":"026f82ca5ceb3c79f9e6d0ebe241b589cc90ae90af9719c67bab302b1250cf56"},"schema_version":"1.0","source":{"id":"2304.12778","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.12778","created_at":"2026-07-05T08:56:12Z"},{"alias_kind":"arxiv_version","alias_value":"2304.12778v2","created_at":"2026-07-05T08:56:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.12778","created_at":"2026-07-05T08:56:12Z"},{"alias_kind":"pith_short_12","alias_value":"HVDRPKNYM7SZ","created_at":"2026-07-05T08:56:12Z"},{"alias_kind":"pith_short_16","alias_value":"HVDRPKNYM7SZ65PF","created_at":"2026-07-05T08:56:12Z"},{"alias_kind":"pith_short_8","alias_value":"HVDRPKNY","created_at":"2026-07-05T08:56:12Z"}],"graph_snapshots":[{"event_id":"sha256:a2389bc8e863200198c29af32cd2a35ee3019128fb3de01d6fb92f870bf9028b","target":"graph","created_at":"2026-07-05T08:56:12Z","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/2304.12778/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces two learning schemes for distributed agents in Reinforcement Learning (RL) environments, namely Reward-Weighted (R-Weighted) and Loss-Weighted (L-Weighted) gradient merger. The R/L weighted methods replace standard practices for training multiple agents, such as summing or averaging the gradients. The core of our methods is to scale the gradient of each actor based on how high the reward (for R-Weighted) or the loss (for L-Weighted) is compared to the other actors. During training, each agent operates in differently initialized versions of the same environment, which give","authors_text":"Kristian Muri Knausg{\\aa}rd, Martin Holen, Morten Goodwin, Per-Arne Andersen","cross_cats":["cs.AI","cs.DC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-25T13:01:21Z","title":"Loss- and Reward-Weighting for Efficient Distributed Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.12778","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:c55c2d1f60d6fb325b65bd733f0a7df377cb8443f75c2050fda4bfec1f49f1cb","target":"record","created_at":"2026-07-05T08:56:12Z","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":"10cecef2c5417c804e398d1d0287039fe70708a703aedd99fa7e3ed4d8416fd0","cross_cats_sorted":["cs.AI","cs.DC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-25T13:01:21Z","title_canon_sha256":"026f82ca5ceb3c79f9e6d0ebe241b589cc90ae90af9719c67bab302b1250cf56"},"schema_version":"1.0","source":{"id":"2304.12778","kind":"arxiv","version":2}},"canonical_sha256":"3d4717a9b867e59f75e5fff16414a0faa011e9c98c4aa02e605b2bffbbfa75b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d4717a9b867e59f75e5fff16414a0faa011e9c98c4aa02e605b2bffbbfa75b1","first_computed_at":"2026-07-05T08:56:12.360334Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:56:12.360334Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fpUG60bAUdmbMXbnmzu6+4RbXaIl7OKvRa9gSwyNonL7Smzq17hPiSTDgzkcGSYTWqMaPLZpmIQvA262zigPDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:56:12.360819Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.12778","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c55c2d1f60d6fb325b65bd733f0a7df377cb8443f75c2050fda4bfec1f49f1cb","sha256:a2389bc8e863200198c29af32cd2a35ee3019128fb3de01d6fb92f870bf9028b"],"state_sha256":"a12ee0b4bdb1a1e9878095b38510bf93ec93a30a672dcc8109672f4040b8b57c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7LuXkhZymssMMMLMNspvzYVnl7gbdSGv5k71luoCCjCic5ByUtvlg6ab6jJIsKOwSUmJLoKPND4j+kd4RLPMBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T05:47:06.056391Z","bundle_sha256":"5fd9a74bfae92f2b9d70e94bbdeff954f8a9c69b170d349c842beaf37c0bb8af"}}