{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:FY7XKCPDIB2RFDHSMQO75EI2PF","short_pith_number":"pith:FY7XKCPD","canonical_record":{"source":{"id":"2604.18701","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-20T18:01:15Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"6168d3d9a9a87b910e40adb8d3458536f23bc9972783af382d101ed5f2e0bb99","abstract_canon_sha256":"02cb1f8bece5d1793abd1b5ac478bf11832fb7f3098d349cc55835e5e8912221"},"schema_version":"1.0"},"canonical_sha256":"2e3f7509e34075128cf2641dfe911a7969e38e3d397a8d6b2af24b7a6bd55575","source":{"kind":"arxiv","id":"2604.18701","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.18701","created_at":"2026-06-19T16:09:58Z"},{"alias_kind":"arxiv_version","alias_value":"2604.18701v3","created_at":"2026-06-19T16:09:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.18701","created_at":"2026-06-19T16:09:58Z"},{"alias_kind":"pith_short_12","alias_value":"FY7XKCPDIB2R","created_at":"2026-06-19T16:09:58Z"},{"alias_kind":"pith_short_16","alias_value":"FY7XKCPDIB2RFDHS","created_at":"2026-06-19T16:09:58Z"},{"alias_kind":"pith_short_8","alias_value":"FY7XKCPD","created_at":"2026-06-19T16:09:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:FY7XKCPDIB2RFDHSMQO75EI2PF","target":"record","payload":{"canonical_record":{"source":{"id":"2604.18701","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-20T18:01:15Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"6168d3d9a9a87b910e40adb8d3458536f23bc9972783af382d101ed5f2e0bb99","abstract_canon_sha256":"02cb1f8bece5d1793abd1b5ac478bf11832fb7f3098d349cc55835e5e8912221"},"schema_version":"1.0"},"canonical_sha256":"2e3f7509e34075128cf2641dfe911a7969e38e3d397a8d6b2af24b7a6bd55575","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:09:58.265021Z","signature_b64":"YLqFHlXyegHtFsSHLHOTqGTvyRGqrxMccLxqbT1m93wHVdw+iG8+yHSAmPE9WXWvNstU3ouP8wE5Txh38suTBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e3f7509e34075128cf2641dfe911a7969e38e3d397a8d6b2af24b7a6bd55575","last_reissued_at":"2026-06-19T16:09:58.264685Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:09:58.264685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.18701","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-19T16:09:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hhC6CHlyw+hpWlC0lWgvCZoiE2YIR3VwoKZ64u0DYMB0tHM0iTxKSPtpDY3Mg5poNG1N0NtHXadC2K/hiTbcCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T05:23:25.086912Z"},"content_sha256":"675957fcd0a608bb3eedbec9a7f92f4b8dc93333f43724e0856b9bf0bd842a44","schema_version":"1.0","event_id":"sha256:675957fcd0a608bb3eedbec9a7f92f4b8dc93333f43724e0856b9bf0bd842a44"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:FY7XKCPDIB2RFDHSMQO75EI2PF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Curiosity-Critic: Cumulative Prediction Error Improvement as a Tractable Intrinsic Reward for World Model Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Curiosity-Critic uses cumulative prediction error improvement as an intrinsic reward for world model training, estimated via a co-trained critic.","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Haicheng Wang, Vin Bhaskara","submitted_at":"2026-04-20T18:01:15Z","abstract_excerpt":"Local prediction-error-based curiosity rewards focus on the current transition without considering the world model's cumulative prediction error across all visited transitions. We introduce Curiosity-Critic, which grounds its intrinsic reward in the improvement of this cumulative objective, and show that it admits a tractable per-step surrogate: the difference between the current prediction error and the asymptotic error baseline of the current state transition. We estimate this error baseline online with a learned critic co-trained alongside the world model; since the critic only has to learn"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments on a stochastic grid world show that Curiosity-Critic outperforms prediction-error, visitation-count, and Random Network Distillation methods in training speed and final world model accuracy.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The learned critic converges well before the world model saturates, providing a reliable online estimate of the asymptotic error baseline without oracle knowledge of the noise floor.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Curiosity-Critic rewards the improvement in cumulative prediction error via a tractable per-step surrogate (current error minus learned asymptotic baseline), outperforming prior curiosity methods in a stochastic grid world.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Curiosity-Critic uses cumulative prediction error improvement as an intrinsic reward for world model training, estimated via a co-trained critic.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a78d93f27f069f70ac4fb48d564842099c6e64772ff643b43fabf7aabf99a32c"},"source":{"id":"2604.18701","kind":"arxiv","version":3},"verdict":{"id":"f2f8dde8-a915-4511-a4bd-067560a536f7","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T04:37:24.959327Z","strongest_claim":"Experiments on a stochastic grid world show that Curiosity-Critic outperforms prediction-error, visitation-count, and Random Network Distillation methods in training speed and final world model accuracy.","one_line_summary":"Curiosity-Critic rewards the improvement in cumulative prediction error via a tractable per-step surrogate (current error minus learned asymptotic baseline), outperforming prior curiosity methods in a stochastic grid world.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The learned critic converges well before the world model saturates, providing a reliable online estimate of the asymptotic error baseline without oracle knowledge of the noise floor.","pith_extraction_headline":"Curiosity-Critic uses cumulative prediction error improvement as an intrinsic reward for world model training, estimated via a co-trained critic."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.18701/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_compliance","ran_at":"2026-05-20T03:47:41.060560Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"b391193f5641f9d7723701897da469e69e25d531dc709ff9f77a287c0f5c8b96"},"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":"f2f8dde8-a915-4511-a4bd-067560a536f7"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-19T16:09:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cNyH+QK4HJOHglwAbsDbk+oyskz1z/jVYla6bfIpqz4Xz4ULBLvU8dRgfh1UCLK37KRK7p316Eg3xEF+gXScCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T05:23:25.087396Z"},"content_sha256":"76753d29bade39348016cd9227e39bab80fedabde3ae7ad90b92d2eae6496767","schema_version":"1.0","event_id":"sha256:76753d29bade39348016cd9227e39bab80fedabde3ae7ad90b92d2eae6496767"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FY7XKCPDIB2RFDHSMQO75EI2PF/bundle.json","state_url":"https://pith.science/pith/FY7XKCPDIB2RFDHSMQO75EI2PF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FY7XKCPDIB2RFDHSMQO75EI2PF/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":"2026-07-05T05:23:25Z","links":{"resolver":"https://pith.science/pith/FY7XKCPDIB2RFDHSMQO75EI2PF","bundle":"https://pith.science/pith/FY7XKCPDIB2RFDHSMQO75EI2PF/bundle.json","state":"https://pith.science/pith/FY7XKCPDIB2RFDHSMQO75EI2PF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FY7XKCPDIB2RFDHSMQO75EI2PF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FY7XKCPDIB2RFDHSMQO75EI2PF","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":"02cb1f8bece5d1793abd1b5ac478bf11832fb7f3098d349cc55835e5e8912221","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-20T18:01:15Z","title_canon_sha256":"6168d3d9a9a87b910e40adb8d3458536f23bc9972783af382d101ed5f2e0bb99"},"schema_version":"1.0","source":{"id":"2604.18701","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.18701","created_at":"2026-06-19T16:09:58Z"},{"alias_kind":"arxiv_version","alias_value":"2604.18701v3","created_at":"2026-06-19T16:09:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.18701","created_at":"2026-06-19T16:09:58Z"},{"alias_kind":"pith_short_12","alias_value":"FY7XKCPDIB2R","created_at":"2026-06-19T16:09:58Z"},{"alias_kind":"pith_short_16","alias_value":"FY7XKCPDIB2RFDHS","created_at":"2026-06-19T16:09:58Z"},{"alias_kind":"pith_short_8","alias_value":"FY7XKCPD","created_at":"2026-06-19T16:09:58Z"}],"graph_snapshots":[{"event_id":"sha256:76753d29bade39348016cd9227e39bab80fedabde3ae7ad90b92d2eae6496767","target":"graph","created_at":"2026-06-19T16:09:58Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Experiments on a stochastic grid world show that Curiosity-Critic outperforms prediction-error, visitation-count, and Random Network Distillation methods in training speed and final world model accuracy."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The learned critic converges well before the world model saturates, providing a reliable online estimate of the asymptotic error baseline without oracle knowledge of the noise floor."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Curiosity-Critic rewards the improvement in cumulative prediction error via a tractable per-step surrogate (current error minus learned asymptotic baseline), outperforming prior curiosity methods in a stochastic grid world."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Curiosity-Critic uses cumulative prediction error improvement as an intrinsic reward for world model training, estimated via a co-trained critic."}],"snapshot_sha256":"a78d93f27f069f70ac4fb48d564842099c6e64772ff643b43fabf7aabf99a32c"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-20T03:47:41.060560Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2604.18701/integrity.json","findings":[],"snapshot_sha256":"b391193f5641f9d7723701897da469e69e25d531dc709ff9f77a287c0f5c8b96","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Local prediction-error-based curiosity rewards focus on the current transition without considering the world model's cumulative prediction error across all visited transitions. We introduce Curiosity-Critic, which grounds its intrinsic reward in the improvement of this cumulative objective, and show that it admits a tractable per-step surrogate: the difference between the current prediction error and the asymptotic error baseline of the current state transition. We estimate this error baseline online with a learned critic co-trained alongside the world model; since the critic only has to learn","authors_text":"Haicheng Wang, Vin Bhaskara","cross_cats":["cs.AI","stat.ML"],"headline":"Curiosity-Critic uses cumulative prediction error improvement as an intrinsic reward for world model training, estimated via a co-trained critic.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-20T18:01:15Z","title":"Curiosity-Critic: Cumulative Prediction Error Improvement as a Tractable Intrinsic Reward for World Model Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.18701","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-10T04:37:24.959327Z","id":"f2f8dde8-a915-4511-a4bd-067560a536f7","model_set":{"reader":"grok-4.3"},"one_line_summary":"Curiosity-Critic rewards the improvement in cumulative prediction error via a tractable per-step surrogate (current error minus learned asymptotic baseline), outperforming prior curiosity methods in a stochastic grid world.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Curiosity-Critic uses cumulative prediction error improvement as an intrinsic reward for world model training, estimated via a co-trained critic.","strongest_claim":"Experiments on a stochastic grid world show that Curiosity-Critic outperforms prediction-error, visitation-count, and Random Network Distillation methods in training speed and final world model accuracy.","weakest_assumption":"The learned critic converges well before the world model saturates, providing a reliable online estimate of the asymptotic error baseline without oracle knowledge of the noise floor."}},"verdict_id":"f2f8dde8-a915-4511-a4bd-067560a536f7"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:675957fcd0a608bb3eedbec9a7f92f4b8dc93333f43724e0856b9bf0bd842a44","target":"record","created_at":"2026-06-19T16:09:58Z","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":"02cb1f8bece5d1793abd1b5ac478bf11832fb7f3098d349cc55835e5e8912221","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-20T18:01:15Z","title_canon_sha256":"6168d3d9a9a87b910e40adb8d3458536f23bc9972783af382d101ed5f2e0bb99"},"schema_version":"1.0","source":{"id":"2604.18701","kind":"arxiv","version":3}},"canonical_sha256":"2e3f7509e34075128cf2641dfe911a7969e38e3d397a8d6b2af24b7a6bd55575","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e3f7509e34075128cf2641dfe911a7969e38e3d397a8d6b2af24b7a6bd55575","first_computed_at":"2026-06-19T16:09:58.264685Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:09:58.264685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YLqFHlXyegHtFsSHLHOTqGTvyRGqrxMccLxqbT1m93wHVdw+iG8+yHSAmPE9WXWvNstU3ouP8wE5Txh38suTBw==","signature_status":"signed_v1","signed_at":"2026-06-19T16:09:58.265021Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.18701","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:675957fcd0a608bb3eedbec9a7f92f4b8dc93333f43724e0856b9bf0bd842a44","sha256:76753d29bade39348016cd9227e39bab80fedabde3ae7ad90b92d2eae6496767"],"state_sha256":"c920db2ad1ec2e622abf267f2f4270c8db7539ed12b73720cd189fee9d553ac3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N8vQzHCuBxmnHcPR2LypeavfyxevWYfrZ8X7iZigsfYFDtXUM+8B1CPRpKIy0co4MwfBGABi4jcTWcaPmLJtDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T05:23:25.089612Z","bundle_sha256":"34041f7017116bd10b11832964cf4315779eff7746844c555ccefb8544c68b0b"}}