{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ENI2C4HG6YH5NOAWMZI5AICLPA","short_pith_number":"pith:ENI2C4HG","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"},"canonical_sha256":"2351a170e6f60fd6b8166651d0204b78314b559b80823f0dbf86479c514efece","source":{"kind":"arxiv","id":"2106.01151","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.01151","created_at":"2026-07-05T03:45:09Z"},{"alias_kind":"arxiv_version","alias_value":"2106.01151v4","created_at":"2026-07-05T03:45:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.01151","created_at":"2026-07-05T03:45:09Z"},{"alias_kind":"pith_short_12","alias_value":"ENI2C4HG6YH5","created_at":"2026-07-05T03:45:09Z"},{"alias_kind":"pith_short_16","alias_value":"ENI2C4HG6YH5NOAW","created_at":"2026-07-05T03:45:09Z"},{"alias_kind":"pith_short_8","alias_value":"ENI2C4HG","created_at":"2026-07-05T03:45:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ENI2C4HG6YH5NOAWMZI5AICLPA","target":"record","payload":{"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"},"canonical_sha256":"2351a170e6f60fd6b8166651d0204b78314b559b80823f0dbf86479c514efece","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"},"source_kind":"arxiv","source_id":"2106.01151","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":"2026-07-05T03:45:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h/2uO60qydFVEkkF/Via6tSMIGMaOvxqZPTRcLqMKEhtKcUkTeDbLnX12uwHJT9MHrpz3WtkLP1B+Ld2PwhjCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:54:37.905751Z"},"content_sha256":"fe618a7c97f1acc3606bc685bdcfd2adc14cc504fe713955c145b4fc80fc74dd","schema_version":"1.0","event_id":"sha256:fe618a7c97f1acc3606bc685bdcfd2adc14cc504fe713955c145b4fc80fc74dd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ENI2C4HG6YH5NOAWMZI5AICLPA","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:45:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"38DUT6VNET7o07BdetAGC+AqCw/nrl97kw6WMEkeDj72AhDoifOm8ePuThMXNE7KyYWXQ7385nkvE/XtchaUDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:54:37.906326Z"},"content_sha256":"fbbe5e877e1ec9516b2d86416e178d43c20f8de6db07dfc24030e892630fe81e","schema_version":"1.0","event_id":"sha256:fbbe5e877e1ec9516b2d86416e178d43c20f8de6db07dfc24030e892630fe81e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ENI2C4HG6YH5NOAWMZI5AICLPA/bundle.json","state_url":"https://pith.science/pith/ENI2C4HG6YH5NOAWMZI5AICLPA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ENI2C4HG6YH5NOAWMZI5AICLPA/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":"2026-08-04T04:54:37Z","links":{"resolver":"https://pith.science/pith/ENI2C4HG6YH5NOAWMZI5AICLPA","bundle":"https://pith.science/pith/ENI2C4HG6YH5NOAWMZI5AICLPA/bundle.json","state":"https://pith.science/pith/ENI2C4HG6YH5NOAWMZI5AICLPA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ENI2C4HG6YH5NOAWMZI5AICLPA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ENI2C4HG6YH5NOAWMZI5AICLPA","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":"f302910edb81659b06fa2010b4715d6941c8ad48e5193f951c24e4b17e821e44","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-02T13:41:02Z","title_canon_sha256":"57c1c605b33a66137b9dcb8ccdf1dfe8ddc362aaaa2218e7123d5dd1900254ed"},"schema_version":"1.0","source":{"id":"2106.01151","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.01151","created_at":"2026-07-05T03:45:09Z"},{"alias_kind":"arxiv_version","alias_value":"2106.01151v4","created_at":"2026-07-05T03:45:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.01151","created_at":"2026-07-05T03:45:09Z"},{"alias_kind":"pith_short_12","alias_value":"ENI2C4HG6YH5","created_at":"2026-07-05T03:45:09Z"},{"alias_kind":"pith_short_16","alias_value":"ENI2C4HG6YH5NOAW","created_at":"2026-07-05T03:45:09Z"},{"alias_kind":"pith_short_8","alias_value":"ENI2C4HG","created_at":"2026-07-05T03:45:09Z"}],"graph_snapshots":[{"event_id":"sha256:fbbe5e877e1ec9516b2d86416e178d43c20f8de6db07dfc24030e892630fe81e","target":"graph","created_at":"2026-07-05T03:45:09Z","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/2106.01151/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Carla P. Gomes, Johan Bjorck, Kilian Q. Weinberger","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-02T13:41:02Z","title":"Towards Deeper Deep Reinforcement Learning with Spectral Normalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.01151","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:fe618a7c97f1acc3606bc685bdcfd2adc14cc504fe713955c145b4fc80fc74dd","target":"record","created_at":"2026-07-05T03:45:09Z","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":"f302910edb81659b06fa2010b4715d6941c8ad48e5193f951c24e4b17e821e44","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-02T13:41:02Z","title_canon_sha256":"57c1c605b33a66137b9dcb8ccdf1dfe8ddc362aaaa2218e7123d5dd1900254ed"},"schema_version":"1.0","source":{"id":"2106.01151","kind":"arxiv","version":4}},"canonical_sha256":"2351a170e6f60fd6b8166651d0204b78314b559b80823f0dbf86479c514efece","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2351a170e6f60fd6b8166651d0204b78314b559b80823f0dbf86479c514efece","first_computed_at":"2026-07-05T03:45:09.372206Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:45:09.372206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PcQVLsE/b95utTkDX2LvS68DotGf0qEnc89w+cNIRi93EbFl3c2aNDrdbijK+uxak1eOMokUm5LzAo5d1TS5Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:45:09.372647Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.01151","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe618a7c97f1acc3606bc685bdcfd2adc14cc504fe713955c145b4fc80fc74dd","sha256:fbbe5e877e1ec9516b2d86416e178d43c20f8de6db07dfc24030e892630fe81e"],"state_sha256":"7a9680bb79709f8a10fb72871948ba55aade14d63bba64c6de5a72f0d78d38c4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Suk+axaG0Ft3v4AczwXkVu9vGTDgJ/MAxpxKmmp1sr3Idm2SIGWM+4hvH9eL04YWqZWumGARMxU5YkUxxjKcAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T04:54:37.912688Z","bundle_sha256":"dac17af2df829e695c8d063426d99a6745e1487a889bd338bbeb776e380084db"}}