{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ENI2C4HG6YH5NOAWMZI5AICLPA","short_pith_number":"pith:ENI2C4HG","schema_version":"1.0","canonical_sha256":"2351a170e6f60fd6b8166651d0204b78314b559b80823f0dbf86479c514efece","source":{"kind":"arxiv","id":"2106.01151","version":4},"attestation_state":"computed","paper":{"title":"Towards Deeper Deep Reinforcement Learning with Spectral Normalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Carla P. Gomes, Johan Bjorck, Kilian Q. Weinberger","submitted_at":"2021-06-02T13:41:02Z","abstract_excerpt":"In computer vision and natural language processing, innovations in model architecture that increase model capacity have reliably translated into gains in performance. In stark contrast with this trend, state-of-the-art reinforcement learning (RL) algorithms often use small MLPs, and gains in performance typically originate from algorithmic innovations. It is natural to hypothesize that small datasets in RL necessitate simple models to avoid overfitting; however, this hypothesis is untested. In this paper we investigate how RL agents are affected by exchanging the small MLPs with larger modern "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2106.01151","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-02T13:41:02Z","cross_cats_sorted":[],"title_canon_sha256":"57c1c605b33a66137b9dcb8ccdf1dfe8ddc362aaaa2218e7123d5dd1900254ed","abstract_canon_sha256":"f302910edb81659b06fa2010b4715d6941c8ad48e5193f951c24e4b17e821e44"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:45:09.372647Z","signature_b64":"PcQVLsE/b95utTkDX2LvS68DotGf0qEnc89w+cNIRi93EbFl3c2aNDrdbijK+uxak1eOMokUm5LzAo5d1TS5Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2351a170e6f60fd6b8166651d0204b78314b559b80823f0dbf86479c514efece","last_reissued_at":"2026-07-05T03:45:09.372206Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:45:09.372206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Deeper Deep Reinforcement Learning with Spectral Normalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Carla P. Gomes, Johan Bjorck, Kilian Q. Weinberger","submitted_at":"2021-06-02T13:41:02Z","abstract_excerpt":"In computer vision and natural language processing, innovations in model architecture that increase model capacity have reliably translated into gains in performance. In stark contrast with this trend, state-of-the-art reinforcement learning (RL) algorithms often use small MLPs, and gains in performance typically originate from algorithmic innovations. It is natural to hypothesize that small datasets in RL necessitate simple models to avoid overfitting; however, this hypothesis is untested. In this paper we investigate how RL agents are affected by exchanging the small MLPs with larger modern "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.01151","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/2106.01151/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2106.01151","created_at":"2026-07-05T03:45:09.372259+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.01151v4","created_at":"2026-07-05T03:45:09.372259+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.01151","created_at":"2026-07-05T03:45:09.372259+00:00"},{"alias_kind":"pith_short_12","alias_value":"ENI2C4HG6YH5","created_at":"2026-07-05T03:45:09.372259+00:00"},{"alias_kind":"pith_short_16","alias_value":"ENI2C4HG6YH5NOAW","created_at":"2026-07-05T03:45:09.372259+00:00"},{"alias_kind":"pith_short_8","alias_value":"ENI2C4HG","created_at":"2026-07-05T03:45:09.372259+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ENI2C4HG6YH5NOAWMZI5AICLPA","json":"https://pith.science/pith/ENI2C4HG6YH5NOAWMZI5AICLPA.json","graph_json":"https://pith.science/api/pith-number/ENI2C4HG6YH5NOAWMZI5AICLPA/graph.json","events_json":"https://pith.science/api/pith-number/ENI2C4HG6YH5NOAWMZI5AICLPA/events.json","paper":"https://pith.science/paper/ENI2C4HG"},"agent_actions":{"view_html":"https://pith.science/pith/ENI2C4HG6YH5NOAWMZI5AICLPA","download_json":"https://pith.science/pith/ENI2C4HG6YH5NOAWMZI5AICLPA.json","view_paper":"https://pith.science/paper/ENI2C4HG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.01151&json=true","fetch_graph":"https://pith.science/api/pith-number/ENI2C4HG6YH5NOAWMZI5AICLPA/graph.json","fetch_events":"https://pith.science/api/pith-number/ENI2C4HG6YH5NOAWMZI5AICLPA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ENI2C4HG6YH5NOAWMZI5AICLPA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ENI2C4HG6YH5NOAWMZI5AICLPA/action/storage_attestation","attest_author":"https://pith.science/pith/ENI2C4HG6YH5NOAWMZI5AICLPA/action/author_attestation","sign_citation":"https://pith.science/pith/ENI2C4HG6YH5NOAWMZI5AICLPA/action/citation_signature","submit_replication":"https://pith.science/pith/ENI2C4HG6YH5NOAWMZI5AICLPA/action/replication_record"}},"created_at":"2026-07-05T03:45:09.372259+00:00","updated_at":"2026-07-05T03:45:09.372259+00:00"}