{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XPM3SDEEKCQWY44JLNQ7JW26U5","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":"e50147a7ce73aae50d8a66ca3b6455e121ecab9f281ceca0f81383aae8de3085","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-06T18:55:47Z","title_canon_sha256":"a88da0c353e77a2275c00a4cc1c7c7c7c1db1bca18e72dae5539d8760949cca9"},"schema_version":"1.0","source":{"id":"2403.03950","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.03950","created_at":"2026-07-05T07:53:03Z"},{"alias_kind":"arxiv_version","alias_value":"2403.03950v1","created_at":"2026-07-05T07:53:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03950","created_at":"2026-07-05T07:53:03Z"},{"alias_kind":"pith_short_12","alias_value":"XPM3SDEEKCQW","created_at":"2026-07-05T07:53:03Z"},{"alias_kind":"pith_short_16","alias_value":"XPM3SDEEKCQWY44J","created_at":"2026-07-05T07:53:03Z"},{"alias_kind":"pith_short_8","alias_value":"XPM3SDEE","created_at":"2026-07-05T07:53:03Z"}],"graph_snapshots":[{"event_id":"sha256:aeddc6e0e23716169f7d7882c6c8043a18c2cbf8d349d7fb9529e6ef3aa925a4","target":"graph","created_at":"2026-07-05T07:53:03Z","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/2403.03950/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Value functions are a central component of deep reinforcement learning (RL). These functions, parameterized by neural networks, are trained using a mean squared error regression objective to match bootstrapped target values. However, scaling value-based RL methods that use regression to large networks, such as high-capacity Transformers, has proven challenging. This difficulty is in stark contrast to supervised learning: by leveraging a cross-entropy classification loss, supervised methods have scaled reliably to massive networks. Observing this discrepancy, in this paper, we investigate wheth","authors_text":"Adrien Ali Ta\\\"iga, Aleksandra Faust, Alex Irpan, Aviral Kumar, Jesse Farebrother, Jordi Orbay, Pablo Samuel Castro, Quan Vuong, Rishabh Agarwal, Sergey Levine, Ted Xiao, Yevgen Chebotar","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-06T18:55:47Z","title":"Stop Regressing: Training Value Functions via Classification for Scalable Deep RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03950","kind":"arxiv","version":1},"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:d7f0d35270e91cf76cff7f7393a1937e46867e0ea5464aea764ee28e9d53f708","target":"record","created_at":"2026-07-05T07:53:03Z","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":"e50147a7ce73aae50d8a66ca3b6455e121ecab9f281ceca0f81383aae8de3085","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-06T18:55:47Z","title_canon_sha256":"a88da0c353e77a2275c00a4cc1c7c7c7c1db1bca18e72dae5539d8760949cca9"},"schema_version":"1.0","source":{"id":"2403.03950","kind":"arxiv","version":1}},"canonical_sha256":"bbd9b90c8450a16c73895b61f4db5ea74eb659870166f9b4124f36bfd778de4b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bbd9b90c8450a16c73895b61f4db5ea74eb659870166f9b4124f36bfd778de4b","first_computed_at":"2026-07-05T07:53:03.969870Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:53:03.969870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iqSguVJSNPME8rFzkUqtVv5J0HWJQnkZZN4eyHa5ljuuMxAKItFMExx58HDkRssIY3uKfM9xeJITWubeEHByDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:53:03.970348Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.03950","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d7f0d35270e91cf76cff7f7393a1937e46867e0ea5464aea764ee28e9d53f708","sha256:aeddc6e0e23716169f7d7882c6c8043a18c2cbf8d349d7fb9529e6ef3aa925a4"],"state_sha256":"0eb41a8eb3c9ea2a4b81f29c0c91b961da3f8ef8531f442cae0875e9a828deae"}