{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:3NBCY6YT44BZS4DF63XPC4OJCF","short_pith_number":"pith:3NBCY6YT","canonical_record":{"source":{"id":"2212.05331","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-10T16:26:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1c1e08e6cfc58f5eb5a172d2da3b28a5577ede3f8d4d04aac8aa936cce3b78ef","abstract_canon_sha256":"c7aab14d5e8fae6674b64989a86db9295b804844e9ae0d0ea7beb9a867f5d7c1"},"schema_version":"1.0"},"canonical_sha256":"db422c7b13e703997065f6eef171c911563d541796662a1f44bc8f34fcd7aaff","source":{"kind":"arxiv","id":"2212.05331","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.05331","created_at":"2026-07-05T06:02:48Z"},{"alias_kind":"arxiv_version","alias_value":"2212.05331v2","created_at":"2026-07-05T06:02:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.05331","created_at":"2026-07-05T06:02:48Z"},{"alias_kind":"pith_short_12","alias_value":"3NBCY6YT44BZ","created_at":"2026-07-05T06:02:48Z"},{"alias_kind":"pith_short_16","alias_value":"3NBCY6YT44BZS4DF","created_at":"2026-07-05T06:02:48Z"},{"alias_kind":"pith_short_8","alias_value":"3NBCY6YT","created_at":"2026-07-05T06:02:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:3NBCY6YT44BZS4DF63XPC4OJCF","target":"record","payload":{"canonical_record":{"source":{"id":"2212.05331","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-10T16:26:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1c1e08e6cfc58f5eb5a172d2da3b28a5577ede3f8d4d04aac8aa936cce3b78ef","abstract_canon_sha256":"c7aab14d5e8fae6674b64989a86db9295b804844e9ae0d0ea7beb9a867f5d7c1"},"schema_version":"1.0"},"canonical_sha256":"db422c7b13e703997065f6eef171c911563d541796662a1f44bc8f34fcd7aaff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:02:48.294504Z","signature_b64":"Z+NfDSEOPG8tBAohMOvDBo43ZyxufEf6wlnMhCksTwpicWKezsEFpRFL8HFRMyNqgrwoolJi/ED4qKUTSVLFBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db422c7b13e703997065f6eef171c911563d541796662a1f44bc8f34fcd7aaff","last_reissued_at":"2026-07-05T06:02:48.294129Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:02:48.294129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.05331","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":"2026-07-05T06:02:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2HqTp2+SzpklxNNUy1gSlRB8Poa1M3+ThyRdaH4VGQtR+b/f4dZ0BK2kKv/tj908MqDSX0V3wtkf8wak0M2WAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T20:56:43.681542Z"},"content_sha256":"ada1538eaba7f260d8be00854f1dd8ab2f88c0ad3eb67851a7e5dc748e936620","schema_version":"1.0","event_id":"sha256:ada1538eaba7f260d8be00854f1dd8ab2f88c0ad3eb67851a7e5dc748e936620"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:3NBCY6YT44BZS4DF63XPC4OJCF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Effects of Spectral Normalization in Multi-agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anuj Mahajan, Kinal Mehta, Pawan Kumar","submitted_at":"2022-12-10T16:26:30Z","abstract_excerpt":"A reliable critic is central to on-policy actor-critic learning. But it becomes challenging to learn a reliable critic in a multi-agent sparse reward scenario due to two factors: 1) The joint action space grows exponentially with the number of agents 2) This, combined with the reward sparseness and environment noise, leads to large sample requirements for accurate learning. We show that regularising the critic with spectral normalization (SN) enables it to learn more robustly, even in multi-agent on-policy sparse reward scenarios. Our experiments show that the regularised critic is quickly abl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.05331","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/2212.05331/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":"2026-07-05T06:02:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sZQEeo/Zqi/0yoaKNuxMYiCBxbe1Topzsv5u3Fl5CUD+JhlCNCRjoNhZ2zdpyBzepETodnEdtnIlLyjrSqrWDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T20:56:43.681911Z"},"content_sha256":"c8bdbc745b30e9894f41d89973c07d8de58a3fe3ed2f1b5078d0da271d21bcf5","schema_version":"1.0","event_id":"sha256:c8bdbc745b30e9894f41d89973c07d8de58a3fe3ed2f1b5078d0da271d21bcf5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3NBCY6YT44BZS4DF63XPC4OJCF/bundle.json","state_url":"https://pith.science/pith/3NBCY6YT44BZS4DF63XPC4OJCF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3NBCY6YT44BZS4DF63XPC4OJCF/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":"2026-07-10T20:56:43Z","links":{"resolver":"https://pith.science/pith/3NBCY6YT44BZS4DF63XPC4OJCF","bundle":"https://pith.science/pith/3NBCY6YT44BZS4DF63XPC4OJCF/bundle.json","state":"https://pith.science/pith/3NBCY6YT44BZS4DF63XPC4OJCF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3NBCY6YT44BZS4DF63XPC4OJCF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:3NBCY6YT44BZS4DF63XPC4OJCF","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":"c7aab14d5e8fae6674b64989a86db9295b804844e9ae0d0ea7beb9a867f5d7c1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-10T16:26:30Z","title_canon_sha256":"1c1e08e6cfc58f5eb5a172d2da3b28a5577ede3f8d4d04aac8aa936cce3b78ef"},"schema_version":"1.0","source":{"id":"2212.05331","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.05331","created_at":"2026-07-05T06:02:48Z"},{"alias_kind":"arxiv_version","alias_value":"2212.05331v2","created_at":"2026-07-05T06:02:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.05331","created_at":"2026-07-05T06:02:48Z"},{"alias_kind":"pith_short_12","alias_value":"3NBCY6YT44BZ","created_at":"2026-07-05T06:02:48Z"},{"alias_kind":"pith_short_16","alias_value":"3NBCY6YT44BZS4DF","created_at":"2026-07-05T06:02:48Z"},{"alias_kind":"pith_short_8","alias_value":"3NBCY6YT","created_at":"2026-07-05T06:02:48Z"}],"graph_snapshots":[{"event_id":"sha256:c8bdbc745b30e9894f41d89973c07d8de58a3fe3ed2f1b5078d0da271d21bcf5","target":"graph","created_at":"2026-07-05T06:02:48Z","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/2212.05331/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A reliable critic is central to on-policy actor-critic learning. But it becomes challenging to learn a reliable critic in a multi-agent sparse reward scenario due to two factors: 1) The joint action space grows exponentially with the number of agents 2) This, combined with the reward sparseness and environment noise, leads to large sample requirements for accurate learning. We show that regularising the critic with spectral normalization (SN) enables it to learn more robustly, even in multi-agent on-policy sparse reward scenarios. Our experiments show that the regularised critic is quickly abl","authors_text":"Anuj Mahajan, Kinal Mehta, Pawan Kumar","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-10T16:26:30Z","title":"Effects of Spectral Normalization in Multi-agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.05331","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:ada1538eaba7f260d8be00854f1dd8ab2f88c0ad3eb67851a7e5dc748e936620","target":"record","created_at":"2026-07-05T06:02:48Z","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":"c7aab14d5e8fae6674b64989a86db9295b804844e9ae0d0ea7beb9a867f5d7c1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-10T16:26:30Z","title_canon_sha256":"1c1e08e6cfc58f5eb5a172d2da3b28a5577ede3f8d4d04aac8aa936cce3b78ef"},"schema_version":"1.0","source":{"id":"2212.05331","kind":"arxiv","version":2}},"canonical_sha256":"db422c7b13e703997065f6eef171c911563d541796662a1f44bc8f34fcd7aaff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db422c7b13e703997065f6eef171c911563d541796662a1f44bc8f34fcd7aaff","first_computed_at":"2026-07-05T06:02:48.294129Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:02:48.294129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z+NfDSEOPG8tBAohMOvDBo43ZyxufEf6wlnMhCksTwpicWKezsEFpRFL8HFRMyNqgrwoolJi/ED4qKUTSVLFBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:02:48.294504Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.05331","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ada1538eaba7f260d8be00854f1dd8ab2f88c0ad3eb67851a7e5dc748e936620","sha256:c8bdbc745b30e9894f41d89973c07d8de58a3fe3ed2f1b5078d0da271d21bcf5"],"state_sha256":"f5692153db5dd700d7becf2372529ac88bcf1ee9b7569d643ccbe53d705e537f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"obtYnElQqzkLWr09abZtc4FF70dmTSfbuHT5awqJ7Rj10QlZLtjUseopScnHwj74mJGXfaQ0Lamka3Z/4yn0Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T20:56:43.684031Z","bundle_sha256":"74ee06da5d17bd1b4bc9178e59956c343d0eab64006a39c0ac025f0fdb8982de"}}