{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:DTZBFXYXG5JMNJCMQD7FX3ECV2","short_pith_number":"pith:DTZBFXYX","canonical_record":{"source":{"id":"2607.16421","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-17T18:13:38Z","cross_cats_sorted":[],"title_canon_sha256":"978c75f15b206410cf746c8b998e2647c6c61c5ad5ccdaa78b0a65aae92b62c8","abstract_canon_sha256":"0b1de378c95352ff007f174735569c739d56045cca35e57f4dea7e5eea055084"},"schema_version":"1.0"},"canonical_sha256":"1cf212df173752c6a44c80fe5bec82aeb1520a29ee419c36f7c9deaf52cf9ff9","source":{"kind":"arxiv","id":"2607.16421","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.16421","created_at":"2026-07-21T00:20:17Z"},{"alias_kind":"arxiv_version","alias_value":"2607.16421v1","created_at":"2026-07-21T00:20:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16421","created_at":"2026-07-21T00:20:17Z"},{"alias_kind":"pith_short_12","alias_value":"DTZBFXYXG5JM","created_at":"2026-07-21T00:20:17Z"},{"alias_kind":"pith_short_16","alias_value":"DTZBFXYXG5JMNJCM","created_at":"2026-07-21T00:20:17Z"},{"alias_kind":"pith_short_8","alias_value":"DTZBFXYX","created_at":"2026-07-21T00:20:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:DTZBFXYXG5JMNJCMQD7FX3ECV2","target":"record","payload":{"canonical_record":{"source":{"id":"2607.16421","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-17T18:13:38Z","cross_cats_sorted":[],"title_canon_sha256":"978c75f15b206410cf746c8b998e2647c6c61c5ad5ccdaa78b0a65aae92b62c8","abstract_canon_sha256":"0b1de378c95352ff007f174735569c739d56045cca35e57f4dea7e5eea055084"},"schema_version":"1.0"},"canonical_sha256":"1cf212df173752c6a44c80fe5bec82aeb1520a29ee419c36f7c9deaf52cf9ff9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T00:20:17.467336Z","signature_b64":"Fv8t11jCShEuXzEUNIsK2W/XiCJdg3xndh6E2MqhDKv1sXKSI/IP7Lne2tR3ZZdY35b+FnVw9c92gCjuwB9nCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cf212df173752c6a44c80fe5bec82aeb1520a29ee419c36f7c9deaf52cf9ff9","last_reissued_at":"2026-07-21T00:20:17.466415Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T00:20:17.466415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.16421","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":"2026-07-21T00:20:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EMH+ot4BwvEiPUGl/fXHt6/U/LlyRWdhmWTox+YR84vxnOzUP/DcccDGkOA/NoeVUwTuGSYVWxePp4XVr8L8Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T09:05:31.674349Z"},"content_sha256":"a4116a90b3cb0438e9c2db599924e951d8fc0e8b2ed2c7eef4fc50eaaace6a36","schema_version":"1.0","event_id":"sha256:a4116a90b3cb0438e9c2db599924e951d8fc0e8b2ed2c7eef4fc50eaaace6a36"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:DTZBFXYXG5JMNJCMQD7FX3ECV2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When to Plan: Learning to Select Between Reactive Control and Deliberative Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Adam Labiosa, Josiah P. Hanna","submitted_at":"2026-07-17T18:13:38Z","abstract_excerpt":"It has long been recognized that humans have the ability to switch between fast, reactive decision-making and slower, deliberative planning. In this paper, we study the question of how to learn this ability, known as meta-reasoning, in artificial agents. We model reactive decision-making as a policy that directly maps state observations to actions. Such policies can be trained with reinforcement learning (RL) or imitation learning, but may generalize poorly outside of their training distribution. Alternatively, model-based decision-time planning is more likely to produce good actions across a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16421","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/2607.16421/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":"2026-07-21T00:20:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ApYrP5EoTQYgx+7XmlcYaMSrDNaX1PULeGQCKD2PcZZ5C5i4lRCJ8b71CLhALbbZ6mOESzv+kLysQ82g+cCDBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T09:05:31.674739Z"},"content_sha256":"1b2a4df19fc9882a111f390d669ab227bd3bdd20e87c768ce0b66ec507f8526d","schema_version":"1.0","event_id":"sha256:1b2a4df19fc9882a111f390d669ab227bd3bdd20e87c768ce0b66ec507f8526d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DTZBFXYXG5JMNJCMQD7FX3ECV2/bundle.json","state_url":"https://pith.science/pith/DTZBFXYXG5JMNJCMQD7FX3ECV2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DTZBFXYXG5JMNJCMQD7FX3ECV2/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":"2026-08-03T09:05:31Z","links":{"resolver":"https://pith.science/pith/DTZBFXYXG5JMNJCMQD7FX3ECV2","bundle":"https://pith.science/pith/DTZBFXYXG5JMNJCMQD7FX3ECV2/bundle.json","state":"https://pith.science/pith/DTZBFXYXG5JMNJCMQD7FX3ECV2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DTZBFXYXG5JMNJCMQD7FX3ECV2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DTZBFXYXG5JMNJCMQD7FX3ECV2","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":"0b1de378c95352ff007f174735569c739d56045cca35e57f4dea7e5eea055084","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-17T18:13:38Z","title_canon_sha256":"978c75f15b206410cf746c8b998e2647c6c61c5ad5ccdaa78b0a65aae92b62c8"},"schema_version":"1.0","source":{"id":"2607.16421","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.16421","created_at":"2026-07-21T00:20:17Z"},{"alias_kind":"arxiv_version","alias_value":"2607.16421v1","created_at":"2026-07-21T00:20:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16421","created_at":"2026-07-21T00:20:17Z"},{"alias_kind":"pith_short_12","alias_value":"DTZBFXYXG5JM","created_at":"2026-07-21T00:20:17Z"},{"alias_kind":"pith_short_16","alias_value":"DTZBFXYXG5JMNJCM","created_at":"2026-07-21T00:20:17Z"},{"alias_kind":"pith_short_8","alias_value":"DTZBFXYX","created_at":"2026-07-21T00:20:17Z"}],"graph_snapshots":[{"event_id":"sha256:1b2a4df19fc9882a111f390d669ab227bd3bdd20e87c768ce0b66ec507f8526d","target":"graph","created_at":"2026-07-21T00:20:17Z","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/2607.16421/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"It has long been recognized that humans have the ability to switch between fast, reactive decision-making and slower, deliberative planning. In this paper, we study the question of how to learn this ability, known as meta-reasoning, in artificial agents. We model reactive decision-making as a policy that directly maps state observations to actions. Such policies can be trained with reinforcement learning (RL) or imitation learning, but may generalize poorly outside of their training distribution. Alternatively, model-based decision-time planning is more likely to produce good actions across a ","authors_text":"Adam Labiosa, Josiah P. Hanna","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-17T18:13:38Z","title":"When to Plan: Learning to Select Between Reactive Control and Deliberative Planning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16421","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:a4116a90b3cb0438e9c2db599924e951d8fc0e8b2ed2c7eef4fc50eaaace6a36","target":"record","created_at":"2026-07-21T00:20:17Z","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":"0b1de378c95352ff007f174735569c739d56045cca35e57f4dea7e5eea055084","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-17T18:13:38Z","title_canon_sha256":"978c75f15b206410cf746c8b998e2647c6c61c5ad5ccdaa78b0a65aae92b62c8"},"schema_version":"1.0","source":{"id":"2607.16421","kind":"arxiv","version":1}},"canonical_sha256":"1cf212df173752c6a44c80fe5bec82aeb1520a29ee419c36f7c9deaf52cf9ff9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1cf212df173752c6a44c80fe5bec82aeb1520a29ee419c36f7c9deaf52cf9ff9","first_computed_at":"2026-07-21T00:20:17.466415Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T00:20:17.466415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fv8t11jCShEuXzEUNIsK2W/XiCJdg3xndh6E2MqhDKv1sXKSI/IP7Lne2tR3ZZdY35b+FnVw9c92gCjuwB9nCw==","signature_status":"signed_v1","signed_at":"2026-07-21T00:20:17.467336Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.16421","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a4116a90b3cb0438e9c2db599924e951d8fc0e8b2ed2c7eef4fc50eaaace6a36","sha256:1b2a4df19fc9882a111f390d669ab227bd3bdd20e87c768ce0b66ec507f8526d"],"state_sha256":"ab5c9f5efe1f39f5b37d68eec8726a9998149ce7d731b98e1f557040cdf17539"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SLe3WfW/FBEYJFzp1RB4okqF3cafzZbEfnCCrUfK3pU10BN3BAlwcjUQ3oUrZ21Pesucljm9rBbfZTuo1VUTCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T09:05:31.677834Z","bundle_sha256":"84ff312d87d5a9e9159b49b7db84188ead009d68b011854c45b9808ab63228aa"}}