{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BOEINB4OKFFUL2SMM6YSIPFUUP","short_pith_number":"pith:BOEINB4O","schema_version":"1.0","canonical_sha256":"0b8886878e514b45ea4c67b1243cb4a3c4853442d09c75362da69c055fff8881","source":{"kind":"arxiv","id":"2606.00838","version":1},"attestation_state":"computed","paper":{"title":"Decoupled Behavioral Cloning for Scalable Inductive Generalization in RL from Specifications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Subhajit Roy, Suguman Bansal, Vignesh Subramanian","submitted_at":"2026-05-30T18:26:59Z","abstract_excerpt":"Inductive generalization is a framework for reinforcement learning (RL) generalization in which inductively related task instances admit inductively related policies. Prior work captures this structure via a higher-order policy-evolution function learned directly with RL, but suffers from poor training scalability: as training tasks grow, aggregated reward feedback becomes noisy and conflicting, destabilizing training and weakening generalization. We propose DIBS, a decoupled behavioral cloning approach that separates learning task-specific policies from learning the evolution function. We fir"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.00838","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-30T18:26:59Z","cross_cats_sorted":[],"title_canon_sha256":"38afd3a27d767b757903f974823f62767a072cb82a4a75323c4114890f96b5bd","abstract_canon_sha256":"370ffc051d1a8a2621ae2237aedd2ce7897f4c6f28d9cbe3fec19f44d2571c39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:04:07.289446Z","signature_b64":"Yx95qaDRrqQsky4WRHQKUYvD8f/dlECQDDdbsYHGoLydRc4poCDc1eU7ucIs+wdd0TL+Nx7JkWrUwUiQRw4ECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b8886878e514b45ea4c67b1243cb4a3c4853442d09c75362da69c055fff8881","last_reissued_at":"2026-06-02T01:04:07.288928Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:04:07.288928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decoupled Behavioral Cloning for Scalable Inductive Generalization in RL from Specifications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Subhajit Roy, Suguman Bansal, Vignesh Subramanian","submitted_at":"2026-05-30T18:26:59Z","abstract_excerpt":"Inductive generalization is a framework for reinforcement learning (RL) generalization in which inductively related task instances admit inductively related policies. Prior work captures this structure via a higher-order policy-evolution function learned directly with RL, but suffers from poor training scalability: as training tasks grow, aggregated reward feedback becomes noisy and conflicting, destabilizing training and weakening generalization. We propose DIBS, a decoupled behavioral cloning approach that separates learning task-specific policies from learning the evolution function. We fir"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00838","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/2606.00838/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.00838","created_at":"2026-06-02T01:04:07.288993+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00838v1","created_at":"2026-06-02T01:04:07.288993+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00838","created_at":"2026-06-02T01:04:07.288993+00:00"},{"alias_kind":"pith_short_12","alias_value":"BOEINB4OKFFU","created_at":"2026-06-02T01:04:07.288993+00:00"},{"alias_kind":"pith_short_16","alias_value":"BOEINB4OKFFUL2SM","created_at":"2026-06-02T01:04:07.288993+00:00"},{"alias_kind":"pith_short_8","alias_value":"BOEINB4O","created_at":"2026-06-02T01:04:07.288993+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BOEINB4OKFFUL2SMM6YSIPFUUP","json":"https://pith.science/pith/BOEINB4OKFFUL2SMM6YSIPFUUP.json","graph_json":"https://pith.science/api/pith-number/BOEINB4OKFFUL2SMM6YSIPFUUP/graph.json","events_json":"https://pith.science/api/pith-number/BOEINB4OKFFUL2SMM6YSIPFUUP/events.json","paper":"https://pith.science/paper/BOEINB4O"},"agent_actions":{"view_html":"https://pith.science/pith/BOEINB4OKFFUL2SMM6YSIPFUUP","download_json":"https://pith.science/pith/BOEINB4OKFFUL2SMM6YSIPFUUP.json","view_paper":"https://pith.science/paper/BOEINB4O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00838&json=true","fetch_graph":"https://pith.science/api/pith-number/BOEINB4OKFFUL2SMM6YSIPFUUP/graph.json","fetch_events":"https://pith.science/api/pith-number/BOEINB4OKFFUL2SMM6YSIPFUUP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BOEINB4OKFFUL2SMM6YSIPFUUP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BOEINB4OKFFUL2SMM6YSIPFUUP/action/storage_attestation","attest_author":"https://pith.science/pith/BOEINB4OKFFUL2SMM6YSIPFUUP/action/author_attestation","sign_citation":"https://pith.science/pith/BOEINB4OKFFUL2SMM6YSIPFUUP/action/citation_signature","submit_replication":"https://pith.science/pith/BOEINB4OKFFUL2SMM6YSIPFUUP/action/replication_record"}},"created_at":"2026-06-02T01:04:07.288993+00:00","updated_at":"2026-06-02T01:04:07.288993+00:00"}