{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:K5R2ZHIKZWCZ4YTPG3XG4SQ5FA","short_pith_number":"pith:K5R2ZHIK","canonical_record":{"source":{"id":"2406.06309","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-10T14:25:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1d854a3d02431c5386e077d1fb82c0336d1defcb6843e4c9e162d8f6efec38bd","abstract_canon_sha256":"a4ef46cef4a583ff5227f9d2bf2a21b9966db4baf372e787427fc70f62d71360"},"schema_version":"1.0"},"canonical_sha256":"5763ac9d0acd859e626f36ee6e4a1d282faa926c26b1dbca8b4f95184cb4c190","source":{"kind":"arxiv","id":"2406.06309","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.06309","created_at":"2026-07-05T09:36:12Z"},{"alias_kind":"arxiv_version","alias_value":"2406.06309v2","created_at":"2026-07-05T09:36:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06309","created_at":"2026-07-05T09:36:12Z"},{"alias_kind":"pith_short_12","alias_value":"K5R2ZHIKZWCZ","created_at":"2026-07-05T09:36:12Z"},{"alias_kind":"pith_short_16","alias_value":"K5R2ZHIKZWCZ4YTP","created_at":"2026-07-05T09:36:12Z"},{"alias_kind":"pith_short_8","alias_value":"K5R2ZHIK","created_at":"2026-07-05T09:36:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:K5R2ZHIKZWCZ4YTPG3XG4SQ5FA","target":"record","payload":{"canonical_record":{"source":{"id":"2406.06309","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-10T14:25:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1d854a3d02431c5386e077d1fb82c0336d1defcb6843e4c9e162d8f6efec38bd","abstract_canon_sha256":"a4ef46cef4a583ff5227f9d2bf2a21b9966db4baf372e787427fc70f62d71360"},"schema_version":"1.0"},"canonical_sha256":"5763ac9d0acd859e626f36ee6e4a1d282faa926c26b1dbca8b4f95184cb4c190","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:12.263513Z","signature_b64":"D0LZYPrhn9hn3CD/VICOgcTga9rVW/kaRIN39CLhMA4gKSf8dI411IO7X+LMOtRbtgHDRxh5mU6gzRk3gy7KBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5763ac9d0acd859e626f36ee6e4a1d282faa926c26b1dbca8b4f95184cb4c190","last_reissued_at":"2026-07-05T09:36:12.263058Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:12.263058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.06309","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":"2026-07-05T09:36:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mxdr7x8UpJPb2CDOeP0yviBV7MsskoU3h26jcZKVm/vwLHkNMhSc7Fkxy/lWZPX62Q8WQJo8OUVfTVSopTA8DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T21:50:29.771415Z"},"content_sha256":"039da53494411cc6c8408b2702024c58e14384e46dfc9bc07facb13a1e298766","schema_version":"1.0","event_id":"sha256:039da53494411cc6c8408b2702024c58e14384e46dfc9bc07facb13a1e298766"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:K5R2ZHIKZWCZ4YTPG3XG4SQ5FA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Is Value Functions Estimation with Classification Plug-and-play for Offline Reinforcement Learning?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Denis Tarasov, Dmitrii Kharlapenko, Kirill Brilliantov","submitted_at":"2024-06-10T14:25:11Z","abstract_excerpt":"In deep Reinforcement Learning (RL), value functions are typically approximated using deep neural networks and trained via mean squared error regression objectives to fit the true value functions. Recent research has proposed an alternative approach, utilizing the cross-entropy classification objective, which has demonstrated improved performance and scalability of RL algorithms. However, existing study have not extensively benchmarked the effects of this replacement across various domains, as the primary objective was to demonstrate the efficacy of the concept across a broad spectrum of tasks"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06309","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/2406.06309/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":"2026-07-05T09:36:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z7vuKe17GvW41haQ82u/1y4Gg6sBwOtUR+Td3fDHv3uza7LBp32jQ1omR9EiWn/S0bAPsLFjEBYG9EiS0IbcBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T21:50:29.772063Z"},"content_sha256":"3e17c1f5c12b69088e0493bd2bf82e7626172875aec424bc2d8493261a3f10e2","schema_version":"1.0","event_id":"sha256:3e17c1f5c12b69088e0493bd2bf82e7626172875aec424bc2d8493261a3f10e2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K5R2ZHIKZWCZ4YTPG3XG4SQ5FA/bundle.json","state_url":"https://pith.science/pith/K5R2ZHIKZWCZ4YTPG3XG4SQ5FA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K5R2ZHIKZWCZ4YTPG3XG4SQ5FA/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":"2026-08-21T21:50:29Z","links":{"resolver":"https://pith.science/pith/K5R2ZHIKZWCZ4YTPG3XG4SQ5FA","bundle":"https://pith.science/pith/K5R2ZHIKZWCZ4YTPG3XG4SQ5FA/bundle.json","state":"https://pith.science/pith/K5R2ZHIKZWCZ4YTPG3XG4SQ5FA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K5R2ZHIKZWCZ4YTPG3XG4SQ5FA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:K5R2ZHIKZWCZ4YTPG3XG4SQ5FA","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":"a4ef46cef4a583ff5227f9d2bf2a21b9966db4baf372e787427fc70f62d71360","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-10T14:25:11Z","title_canon_sha256":"1d854a3d02431c5386e077d1fb82c0336d1defcb6843e4c9e162d8f6efec38bd"},"schema_version":"1.0","source":{"id":"2406.06309","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.06309","created_at":"2026-07-05T09:36:12Z"},{"alias_kind":"arxiv_version","alias_value":"2406.06309v2","created_at":"2026-07-05T09:36:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06309","created_at":"2026-07-05T09:36:12Z"},{"alias_kind":"pith_short_12","alias_value":"K5R2ZHIKZWCZ","created_at":"2026-07-05T09:36:12Z"},{"alias_kind":"pith_short_16","alias_value":"K5R2ZHIKZWCZ4YTP","created_at":"2026-07-05T09:36:12Z"},{"alias_kind":"pith_short_8","alias_value":"K5R2ZHIK","created_at":"2026-07-05T09:36:12Z"}],"graph_snapshots":[{"event_id":"sha256:3e17c1f5c12b69088e0493bd2bf82e7626172875aec424bc2d8493261a3f10e2","target":"graph","created_at":"2026-07-05T09:36:12Z","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/2406.06309/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In deep Reinforcement Learning (RL), value functions are typically approximated using deep neural networks and trained via mean squared error regression objectives to fit the true value functions. Recent research has proposed an alternative approach, utilizing the cross-entropy classification objective, which has demonstrated improved performance and scalability of RL algorithms. However, existing study have not extensively benchmarked the effects of this replacement across various domains, as the primary objective was to demonstrate the efficacy of the concept across a broad spectrum of tasks","authors_text":"Denis Tarasov, Dmitrii Kharlapenko, Kirill Brilliantov","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-10T14:25:11Z","title":"Is Value Functions Estimation with Classification Plug-and-play for Offline Reinforcement Learning?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06309","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":"sha256:039da53494411cc6c8408b2702024c58e14384e46dfc9bc07facb13a1e298766","target":"record","created_at":"2026-07-05T09:36:12Z","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":"a4ef46cef4a583ff5227f9d2bf2a21b9966db4baf372e787427fc70f62d71360","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-10T14:25:11Z","title_canon_sha256":"1d854a3d02431c5386e077d1fb82c0336d1defcb6843e4c9e162d8f6efec38bd"},"schema_version":"1.0","source":{"id":"2406.06309","kind":"arxiv","version":2}},"canonical_sha256":"5763ac9d0acd859e626f36ee6e4a1d282faa926c26b1dbca8b4f95184cb4c190","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5763ac9d0acd859e626f36ee6e4a1d282faa926c26b1dbca8b4f95184cb4c190","first_computed_at":"2026-07-05T09:36:12.263058Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:36:12.263058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D0LZYPrhn9hn3CD/VICOgcTga9rVW/kaRIN39CLhMA4gKSf8dI411IO7X+LMOtRbtgHDRxh5mU6gzRk3gy7KBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:36:12.263513Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.06309","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:039da53494411cc6c8408b2702024c58e14384e46dfc9bc07facb13a1e298766","sha256:3e17c1f5c12b69088e0493bd2bf82e7626172875aec424bc2d8493261a3f10e2"],"state_sha256":"a8c26a430f86457dffd6a9255c93bd0ba17899c982adf6ef4ff17eab649c0a6c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ka+8AnHu1VlmutPe5BVFo5U47lzV/5IGlq/fniZQKTTX5xClNzM0InoPnpJVNlLT5RsvHEQlz9vZV0z5y6Q6Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T21:50:29.775978Z","bundle_sha256":"ef8090d3fc95c11ec8feb35b312677bf55b4cbd3ce3e89e506b821926272f82f"}}