{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TGBTB2W2W4WC6BBYB2AM6MU72M","short_pith_number":"pith:TGBTB2W2","canonical_record":{"source":{"id":"2505.23150","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T06:41:45Z","cross_cats_sorted":[],"title_canon_sha256":"93c7a6d8e9fde778087dcc5a4b572671f18b6961fe8983072712275e03b7f873","abstract_canon_sha256":"0827efdcd92357dc2623bccb295810cfd21885526ab1031377e04c20d5f373f3"},"schema_version":"1.0"},"canonical_sha256":"998330eadab72c2f04380e80cf329fd320e191d4984bfa9fa01d917cbfdf4d2c","source":{"kind":"arxiv","id":"2505.23150","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23150","created_at":"2026-07-05T11:11:56Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23150v1","created_at":"2026-07-05T11:11:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23150","created_at":"2026-07-05T11:11:56Z"},{"alias_kind":"pith_short_12","alias_value":"TGBTB2W2W4WC","created_at":"2026-07-05T11:11:56Z"},{"alias_kind":"pith_short_16","alias_value":"TGBTB2W2W4WC6BBY","created_at":"2026-07-05T11:11:56Z"},{"alias_kind":"pith_short_8","alias_value":"TGBTB2W2","created_at":"2026-07-05T11:11:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TGBTB2W2W4WC6BBYB2AM6MU72M","target":"record","payload":{"canonical_record":{"source":{"id":"2505.23150","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T06:41:45Z","cross_cats_sorted":[],"title_canon_sha256":"93c7a6d8e9fde778087dcc5a4b572671f18b6961fe8983072712275e03b7f873","abstract_canon_sha256":"0827efdcd92357dc2623bccb295810cfd21885526ab1031377e04c20d5f373f3"},"schema_version":"1.0"},"canonical_sha256":"998330eadab72c2f04380e80cf329fd320e191d4984bfa9fa01d917cbfdf4d2c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:56.342674Z","signature_b64":"A6K2zAQ0E0/IMzX0Ij3qlKJk3YxgW7XLi1/TvveUtdY2ePRs/wX74Zgo0avtWUtbg6avs+O2gkLCcUMuHZvrBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"998330eadab72c2f04380e80cf329fd320e191d4984bfa9fa01d917cbfdf4d2c","last_reissued_at":"2026-07-05T11:11:56.342217Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:56.342217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.23150","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:11:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"juZSiR57PAUhrF+bCQWrw6RdI5lzg9Rqj7TOAPPiQwyKsAfMDqyy5rhkEso3O5e9feKTZpsOT1I3BMfDPig4Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:01:31.789003Z"},"content_sha256":"5f45df40fad67d010f08d38701c674c1b121f0bf85463d4c3a4930719858c6ec","schema_version":"1.0","event_id":"sha256:5f45df40fad67d010f08d38701c674c1b121f0bf85463d4c3a4930719858c6ec"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TGBTB2W2W4WC6BBYB2AM6MU72M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aviral Kumar, Carmelo Sferrazza, Marek Cygan, Michal Nauman, Pieter Abbeel","submitted_at":"2025-05-29T06:41:45Z","abstract_excerpt":"Recent advances in language modeling and vision stem from training large models on diverse, multi-task data. This paradigm has had limited impact in value-based reinforcement learning (RL), where improvements are often driven by small models trained in a single-task context. This is because in multi-task RL sparse rewards and gradient conflicts make optimization of temporal difference brittle. Practical workflows for generalist policies therefore avoid online training, instead cloning expert trajectories or distilling collections of single-task policies into one agent. In this work, we show th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23150","kind":"arxiv","version":1},"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/2505.23150/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":"2026-07-05T11:11:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LvvP5iGQcGpgTjquHU2tc5n18mCe+7KEGGpZRnkO+lwDl7bv17j3f/ajlls9kgpcPQn8xve4jeer0/8Z1XajBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:01:31.789378Z"},"content_sha256":"e23302eb974836ec6183d64f63e1566385126a47b8a2ac0f013c7865de206018","schema_version":"1.0","event_id":"sha256:e23302eb974836ec6183d64f63e1566385126a47b8a2ac0f013c7865de206018"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TGBTB2W2W4WC6BBYB2AM6MU72M/bundle.json","state_url":"https://pith.science/pith/TGBTB2W2W4WC6BBYB2AM6MU72M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TGBTB2W2W4WC6BBYB2AM6MU72M/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":"2026-07-06T19:01:31Z","links":{"resolver":"https://pith.science/pith/TGBTB2W2W4WC6BBYB2AM6MU72M","bundle":"https://pith.science/pith/TGBTB2W2W4WC6BBYB2AM6MU72M/bundle.json","state":"https://pith.science/pith/TGBTB2W2W4WC6BBYB2AM6MU72M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TGBTB2W2W4WC6BBYB2AM6MU72M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TGBTB2W2W4WC6BBYB2AM6MU72M","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":"0827efdcd92357dc2623bccb295810cfd21885526ab1031377e04c20d5f373f3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T06:41:45Z","title_canon_sha256":"93c7a6d8e9fde778087dcc5a4b572671f18b6961fe8983072712275e03b7f873"},"schema_version":"1.0","source":{"id":"2505.23150","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23150","created_at":"2026-07-05T11:11:56Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23150v1","created_at":"2026-07-05T11:11:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23150","created_at":"2026-07-05T11:11:56Z"},{"alias_kind":"pith_short_12","alias_value":"TGBTB2W2W4WC","created_at":"2026-07-05T11:11:56Z"},{"alias_kind":"pith_short_16","alias_value":"TGBTB2W2W4WC6BBY","created_at":"2026-07-05T11:11:56Z"},{"alias_kind":"pith_short_8","alias_value":"TGBTB2W2","created_at":"2026-07-05T11:11:56Z"}],"graph_snapshots":[{"event_id":"sha256:e23302eb974836ec6183d64f63e1566385126a47b8a2ac0f013c7865de206018","target":"graph","created_at":"2026-07-05T11:11:56Z","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/2505.23150/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in language modeling and vision stem from training large models on diverse, multi-task data. This paradigm has had limited impact in value-based reinforcement learning (RL), where improvements are often driven by small models trained in a single-task context. This is because in multi-task RL sparse rewards and gradient conflicts make optimization of temporal difference brittle. Practical workflows for generalist policies therefore avoid online training, instead cloning expert trajectories or distilling collections of single-task policies into one agent. In this work, we show th","authors_text":"Aviral Kumar, Carmelo Sferrazza, Marek Cygan, Michal Nauman, Pieter Abbeel","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T06:41:45Z","title":"Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23150","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":"sha256:5f45df40fad67d010f08d38701c674c1b121f0bf85463d4c3a4930719858c6ec","target":"record","created_at":"2026-07-05T11:11:56Z","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":"0827efdcd92357dc2623bccb295810cfd21885526ab1031377e04c20d5f373f3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T06:41:45Z","title_canon_sha256":"93c7a6d8e9fde778087dcc5a4b572671f18b6961fe8983072712275e03b7f873"},"schema_version":"1.0","source":{"id":"2505.23150","kind":"arxiv","version":1}},"canonical_sha256":"998330eadab72c2f04380e80cf329fd320e191d4984bfa9fa01d917cbfdf4d2c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"998330eadab72c2f04380e80cf329fd320e191d4984bfa9fa01d917cbfdf4d2c","first_computed_at":"2026-07-05T11:11:56.342217Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:56.342217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A6K2zAQ0E0/IMzX0Ij3qlKJk3YxgW7XLi1/TvveUtdY2ePRs/wX74Zgo0avtWUtbg6avs+O2gkLCcUMuHZvrBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:56.342674Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.23150","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f45df40fad67d010f08d38701c674c1b121f0bf85463d4c3a4930719858c6ec","sha256:e23302eb974836ec6183d64f63e1566385126a47b8a2ac0f013c7865de206018"],"state_sha256":"199b5b9fc8b05d36ce0f1241b02947b1f967058f3f9825c08743441160e00783"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UJ3TJHe4QU8PKrRF4j4cZGySK2+QeHpm3jyFtYbjJOdbk62uEOm55tz0ewRkpmkNhM65VLkmaFa8LYr0aZNEBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T19:01:31.791402Z","bundle_sha256":"2e4477041e69bf285eff57493899947a168d09b74374070a364c9520901dcb8f"}}