{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:BOEINB4OKFFUL2SMM6YSIPFUUP","short_pith_number":"pith:BOEINB4O","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"},"canonical_sha256":"0b8886878e514b45ea4c67b1243cb4a3c4853442d09c75362da69c055fff8881","source":{"kind":"arxiv","id":"2606.00838","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.00838","created_at":"2026-06-02T01:04:07Z"},{"alias_kind":"arxiv_version","alias_value":"2606.00838v1","created_at":"2026-06-02T01:04:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00838","created_at":"2026-06-02T01:04:07Z"},{"alias_kind":"pith_short_12","alias_value":"BOEINB4OKFFU","created_at":"2026-06-02T01:04:07Z"},{"alias_kind":"pith_short_16","alias_value":"BOEINB4OKFFUL2SM","created_at":"2026-06-02T01:04:07Z"},{"alias_kind":"pith_short_8","alias_value":"BOEINB4O","created_at":"2026-06-02T01:04:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:BOEINB4OKFFUL2SMM6YSIPFUUP","target":"record","payload":{"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"},"canonical_sha256":"0b8886878e514b45ea4c67b1243cb4a3c4853442d09c75362da69c055fff8881","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"},"source_kind":"arxiv","source_id":"2606.00838","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":"2026-06-02T01:04:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wn3yVE+/g59UwwO1rXCUYuh+Kya/5SQw2bii9PFGFIOFn3WBTEya7FVBBSWEKbuXRK6WCOBwQJI4RCxy+JYQAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T08:31:50.062704Z"},"content_sha256":"ae71eff872160780dc39000064bedc0be0a675581fe02d0da0e1ea1b75439039","schema_version":"1.0","event_id":"sha256:ae71eff872160780dc39000064bedc0be0a675581fe02d0da0e1ea1b75439039"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:BOEINB4OKFFUL2SMM6YSIPFUUP","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T01:04:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wg9tW7ChYVYAe1HwEy+Mm9QhFP9ZCnDKdaVTGfSYLuoqS6sFfI7gjQKy7HuWTp3ILTROYIIwczhi7CASkwPYCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T08:31:50.063358Z"},"content_sha256":"1509379f88f5cb1419338003067e5b720eec91455c35031976e8d4c8d82d02b6","schema_version":"1.0","event_id":"sha256:1509379f88f5cb1419338003067e5b720eec91455c35031976e8d4c8d82d02b6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BOEINB4OKFFUL2SMM6YSIPFUUP/bundle.json","state_url":"https://pith.science/pith/BOEINB4OKFFUL2SMM6YSIPFUUP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BOEINB4OKFFUL2SMM6YSIPFUUP/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":"2026-06-07T08:31:50Z","links":{"resolver":"https://pith.science/pith/BOEINB4OKFFUL2SMM6YSIPFUUP","bundle":"https://pith.science/pith/BOEINB4OKFFUL2SMM6YSIPFUUP/bundle.json","state":"https://pith.science/pith/BOEINB4OKFFUL2SMM6YSIPFUUP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BOEINB4OKFFUL2SMM6YSIPFUUP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BOEINB4OKFFUL2SMM6YSIPFUUP","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":"370ffc051d1a8a2621ae2237aedd2ce7897f4c6f28d9cbe3fec19f44d2571c39","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-30T18:26:59Z","title_canon_sha256":"38afd3a27d767b757903f974823f62767a072cb82a4a75323c4114890f96b5bd"},"schema_version":"1.0","source":{"id":"2606.00838","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.00838","created_at":"2026-06-02T01:04:07Z"},{"alias_kind":"arxiv_version","alias_value":"2606.00838v1","created_at":"2026-06-02T01:04:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00838","created_at":"2026-06-02T01:04:07Z"},{"alias_kind":"pith_short_12","alias_value":"BOEINB4OKFFU","created_at":"2026-06-02T01:04:07Z"},{"alias_kind":"pith_short_16","alias_value":"BOEINB4OKFFUL2SM","created_at":"2026-06-02T01:04:07Z"},{"alias_kind":"pith_short_8","alias_value":"BOEINB4O","created_at":"2026-06-02T01:04:07Z"}],"graph_snapshots":[{"event_id":"sha256:1509379f88f5cb1419338003067e5b720eec91455c35031976e8d4c8d82d02b6","target":"graph","created_at":"2026-06-02T01:04:07Z","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/2606.00838/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Subhajit Roy, Suguman Bansal, Vignesh Subramanian","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-30T18:26:59Z","title":"Decoupled Behavioral Cloning for Scalable Inductive Generalization in RL from Specifications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00838","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:ae71eff872160780dc39000064bedc0be0a675581fe02d0da0e1ea1b75439039","target":"record","created_at":"2026-06-02T01:04:07Z","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":"370ffc051d1a8a2621ae2237aedd2ce7897f4c6f28d9cbe3fec19f44d2571c39","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-30T18:26:59Z","title_canon_sha256":"38afd3a27d767b757903f974823f62767a072cb82a4a75323c4114890f96b5bd"},"schema_version":"1.0","source":{"id":"2606.00838","kind":"arxiv","version":1}},"canonical_sha256":"0b8886878e514b45ea4c67b1243cb4a3c4853442d09c75362da69c055fff8881","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0b8886878e514b45ea4c67b1243cb4a3c4853442d09c75362da69c055fff8881","first_computed_at":"2026-06-02T01:04:07.288928Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:04:07.288928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Yx95qaDRrqQsky4WRHQKUYvD8f/dlECQDDdbsYHGoLydRc4poCDc1eU7ucIs+wdd0TL+Nx7JkWrUwUiQRw4ECQ==","signature_status":"signed_v1","signed_at":"2026-06-02T01:04:07.289446Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.00838","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae71eff872160780dc39000064bedc0be0a675581fe02d0da0e1ea1b75439039","sha256:1509379f88f5cb1419338003067e5b720eec91455c35031976e8d4c8d82d02b6"],"state_sha256":"70ad8a72557759a122f7b9aed815a5e499515b82082761384787a44a963eee8f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OxOoeXBP8Bcnja00Me5JENVan+Sj3nrzupUNfMimdjQc19wJxPkVBch6ZX+j1XeWb55mMzvGbsec+OvFmqPCCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T08:31:50.066676Z","bundle_sha256":"bf3701cb21e2f1ce2d5d333f78bfdb71a8ceeea398f5165a19b16bf536baba1d"}}