{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:YBD22KY236OXSUHZA5XPDVIGDB","short_pith_number":"pith:YBD22KY2","canonical_record":{"source":{"id":"2205.08464","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-17T16:10:05Z","cross_cats_sorted":[],"title_canon_sha256":"c36b3dca15763250810fc1613f0063b0d3dc60e266e3ec40d2b734df2b5c75a4","abstract_canon_sha256":"141cec397e35c472044c2aa9a65f0a5f28ac7fcf172d64ad14c48cb544d7b0a6"},"schema_version":"1.0"},"canonical_sha256":"c047ad2b1adf9d7950f9076ef1d5061845537fa2c953990b3987aa8cc5f8eaff","source":{"kind":"arxiv","id":"2205.08464","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.08464","created_at":"2026-07-05T06:01:57Z"},{"alias_kind":"arxiv_version","alias_value":"2205.08464v2","created_at":"2026-07-05T06:01:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.08464","created_at":"2026-07-05T06:01:57Z"},{"alias_kind":"pith_short_12","alias_value":"YBD22KY236OX","created_at":"2026-07-05T06:01:57Z"},{"alias_kind":"pith_short_16","alias_value":"YBD22KY236OXSUHZ","created_at":"2026-07-05T06:01:57Z"},{"alias_kind":"pith_short_8","alias_value":"YBD22KY2","created_at":"2026-07-05T06:01:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:YBD22KY236OXSUHZA5XPDVIGDB","target":"record","payload":{"canonical_record":{"source":{"id":"2205.08464","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-17T16:10:05Z","cross_cats_sorted":[],"title_canon_sha256":"c36b3dca15763250810fc1613f0063b0d3dc60e266e3ec40d2b734df2b5c75a4","abstract_canon_sha256":"141cec397e35c472044c2aa9a65f0a5f28ac7fcf172d64ad14c48cb544d7b0a6"},"schema_version":"1.0"},"canonical_sha256":"c047ad2b1adf9d7950f9076ef1d5061845537fa2c953990b3987aa8cc5f8eaff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:01:57.082918Z","signature_b64":"AZMqRFCtNhv2sT83KO+5fYzqeoeHqFqJVGy6HvnNVc6XvVKScZVrXTObqCfAXTh88qOC65j/JbqOGbMW62ZQAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c047ad2b1adf9d7950f9076ef1d5061845537fa2c953990b3987aa8cc5f8eaff","last_reissued_at":"2026-07-05T06:01:57.082555Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:01:57.082555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.08464","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":"2026-07-05T06:01:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oL7WuRkpxA3lLhebMEE2iN8d0fmAF4eRIno5mWqcoTdijYH2+52WJcKbxjXVvQJSVoNQ+2riYLnIZo3VzAnfAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:20:05.848230Z"},"content_sha256":"b553b008776c1e3295b8ff49e31401907ecbb9e3bf9bfafbdde0a2dbc8cf814b","schema_version":"1.0","event_id":"sha256:b553b008776c1e3295b8ff49e31401907ecbb9e3bf9bfafbdde0a2dbc8cf814b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:YBD22KY236OXSUHZA5XPDVIGDB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Losses for Learning Value Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrew Patterson, Martha White, Victor Liao","submitted_at":"2022-05-17T16:10:05Z","abstract_excerpt":"Most value function learning algorithms in reinforcement learning are based on the mean squared (projected) Bellman error. However, squared errors are known to be sensitive to outliers, both skewing the solution of the objective and resulting in high-magnitude and high-variance gradients. To control these high-magnitude updates, typical strategies in RL involve clipping gradients, clipping rewards, rescaling rewards, or clipping errors. While these strategies appear to be related to robust losses -- like the Huber loss -- they are built on semi-gradient update rules which do not minimize a kno"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.08464","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/2205.08464/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":"2026-07-05T06:01:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GoW+KjdMGz1iPmw7Ep+rz6gOcTAIBwTKu8GinIGsuLf1pJoqbdQLqGjrmapUH9bveDHSnMRMUxDU91C/1l9sCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:20:05.848714Z"},"content_sha256":"ef9d2f49dd297c20b89536279dae20ad42741741939d166cf45201621aa530d8","schema_version":"1.0","event_id":"sha256:ef9d2f49dd297c20b89536279dae20ad42741741939d166cf45201621aa530d8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YBD22KY236OXSUHZA5XPDVIGDB/bundle.json","state_url":"https://pith.science/pith/YBD22KY236OXSUHZA5XPDVIGDB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YBD22KY236OXSUHZA5XPDVIGDB/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":"2026-08-07T01:20:05Z","links":{"resolver":"https://pith.science/pith/YBD22KY236OXSUHZA5XPDVIGDB","bundle":"https://pith.science/pith/YBD22KY236OXSUHZA5XPDVIGDB/bundle.json","state":"https://pith.science/pith/YBD22KY236OXSUHZA5XPDVIGDB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YBD22KY236OXSUHZA5XPDVIGDB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:YBD22KY236OXSUHZA5XPDVIGDB","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":"141cec397e35c472044c2aa9a65f0a5f28ac7fcf172d64ad14c48cb544d7b0a6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-17T16:10:05Z","title_canon_sha256":"c36b3dca15763250810fc1613f0063b0d3dc60e266e3ec40d2b734df2b5c75a4"},"schema_version":"1.0","source":{"id":"2205.08464","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.08464","created_at":"2026-07-05T06:01:57Z"},{"alias_kind":"arxiv_version","alias_value":"2205.08464v2","created_at":"2026-07-05T06:01:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.08464","created_at":"2026-07-05T06:01:57Z"},{"alias_kind":"pith_short_12","alias_value":"YBD22KY236OX","created_at":"2026-07-05T06:01:57Z"},{"alias_kind":"pith_short_16","alias_value":"YBD22KY236OXSUHZ","created_at":"2026-07-05T06:01:57Z"},{"alias_kind":"pith_short_8","alias_value":"YBD22KY2","created_at":"2026-07-05T06:01:57Z"}],"graph_snapshots":[{"event_id":"sha256:ef9d2f49dd297c20b89536279dae20ad42741741939d166cf45201621aa530d8","target":"graph","created_at":"2026-07-05T06:01:57Z","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/2205.08464/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most value function learning algorithms in reinforcement learning are based on the mean squared (projected) Bellman error. However, squared errors are known to be sensitive to outliers, both skewing the solution of the objective and resulting in high-magnitude and high-variance gradients. To control these high-magnitude updates, typical strategies in RL involve clipping gradients, clipping rewards, rescaling rewards, or clipping errors. While these strategies appear to be related to robust losses -- like the Huber loss -- they are built on semi-gradient update rules which do not minimize a kno","authors_text":"Andrew Patterson, Martha White, Victor Liao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-17T16:10:05Z","title":"Robust Losses for Learning Value Functions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.08464","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:b553b008776c1e3295b8ff49e31401907ecbb9e3bf9bfafbdde0a2dbc8cf814b","target":"record","created_at":"2026-07-05T06:01:57Z","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":"141cec397e35c472044c2aa9a65f0a5f28ac7fcf172d64ad14c48cb544d7b0a6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-17T16:10:05Z","title_canon_sha256":"c36b3dca15763250810fc1613f0063b0d3dc60e266e3ec40d2b734df2b5c75a4"},"schema_version":"1.0","source":{"id":"2205.08464","kind":"arxiv","version":2}},"canonical_sha256":"c047ad2b1adf9d7950f9076ef1d5061845537fa2c953990b3987aa8cc5f8eaff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c047ad2b1adf9d7950f9076ef1d5061845537fa2c953990b3987aa8cc5f8eaff","first_computed_at":"2026-07-05T06:01:57.082555Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:01:57.082555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AZMqRFCtNhv2sT83KO+5fYzqeoeHqFqJVGy6HvnNVc6XvVKScZVrXTObqCfAXTh88qOC65j/JbqOGbMW62ZQAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:01:57.082918Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.08464","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b553b008776c1e3295b8ff49e31401907ecbb9e3bf9bfafbdde0a2dbc8cf814b","sha256:ef9d2f49dd297c20b89536279dae20ad42741741939d166cf45201621aa530d8"],"state_sha256":"c09f2a1d2d4380f35df2bb988cf5221ae8b306d5ab27162a0432d84aae433fe5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iP57H8snUbhu+M/qLw3Icz76/efqN3rhyIi5Anbet7GHrVgSHWbGE8ERcMiTF9tIw3c4/bksboaq2gWroL6tCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T01:20:05.852302Z","bundle_sha256":"ff36530646590b4713376c457498cd075b3bab99174e01064fc2c06758b101a6"}}