{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ZAPMIWALYOPZ66RWMCXM5I2W5G","short_pith_number":"pith:ZAPMIWAL","canonical_record":{"source":{"id":"2606.05152","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T17:54:04Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"16f9dba2dd3bcb13b6b67e2f61130416de9e3f83c968e067f12d7ab623cbf638","abstract_canon_sha256":"131a9f66f49bf099bd275726121e8b6d31e15d46ecf4a6bdaa77545834a00015"},"schema_version":"1.0"},"canonical_sha256":"c81ec4580bc39f9f7a3660aecea356e9973b194a9b80f047c57c43596788f6d7","source":{"kind":"arxiv","id":"2606.05152","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05152","created_at":"2026-06-04T02:07:54Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05152v1","created_at":"2026-06-04T02:07:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05152","created_at":"2026-06-04T02:07:54Z"},{"alias_kind":"pith_short_12","alias_value":"ZAPMIWALYOPZ","created_at":"2026-06-04T02:07:54Z"},{"alias_kind":"pith_short_16","alias_value":"ZAPMIWALYOPZ66RW","created_at":"2026-06-04T02:07:54Z"},{"alias_kind":"pith_short_8","alias_value":"ZAPMIWAL","created_at":"2026-06-04T02:07:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ZAPMIWALYOPZ66RWMCXM5I2W5G","target":"record","payload":{"canonical_record":{"source":{"id":"2606.05152","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T17:54:04Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"16f9dba2dd3bcb13b6b67e2f61130416de9e3f83c968e067f12d7ab623cbf638","abstract_canon_sha256":"131a9f66f49bf099bd275726121e8b6d31e15d46ecf4a6bdaa77545834a00015"},"schema_version":"1.0"},"canonical_sha256":"c81ec4580bc39f9f7a3660aecea356e9973b194a9b80f047c57c43596788f6d7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T02:07:54.175388Z","signature_b64":"oPNtsBd3txS/Eq+fXKhNp+QqfZ56j86d8fZvsmOyDzO6Q9HioCStL5RJUiplG8Itpb4CqyS/zMjwnheNuxbYDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c81ec4580bc39f9f7a3660aecea356e9973b194a9b80f047c57c43596788f6d7","last_reissued_at":"2026-06-04T02:07:54.174843Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T02:07:54.174843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.05152","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":"2026-06-04T02:07:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+2cUa540fDi2qsd76G89+vC+HNBtWBUOWXrQTiGRP0t+C88WELMiedp7CySEQUtxaQQSPAp12CrHZ9/901fPDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T22:43:11.781663Z"},"content_sha256":"c4a5a71e6214b2b325a0e20a8f773aab5daa241d86b9a02c5e3197126b5e5005","schema_version":"1.0","event_id":"sha256:c4a5a71e6214b2b325a0e20a8f773aab5daa241d86b9a02c5e3197126b5e5005"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ZAPMIWALYOPZ66RWMCXM5I2W5G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning from Rich Feedback with Distributional DAgger","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Jacob Fein-Ashley, Paria Rashidinejad, Rishabh Agrawal","submitted_at":"2026-06-03T17:54:04Z","abstract_excerpt":"Reasoning models have advanced rapidly, but the dominant reinforcement learning from verifiable rewards (RLVR) recipe remains surprisingly narrow: sample many responses and reward each with a single bit indicating whether the final answer is correct. Yet many settings provide rich feedback, including execution traces, tool outputs, expert corrections, and model self-evaluations. We study how to use such feedback through a distributional variant of the classic imitation learning algorithm DAgger, where the learner has local access to an expert distribution on states visited by the current polic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05152","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/2606.05152/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":"2026-06-04T02:07:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0G1NFLzH98NQr6YC7Kn3lY9YGYmgC26to+kda19cRT65QXlBbhFjbpRPMWhzTkOUUccPbp0XUkkceEuZGwNkBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T22:43:11.782043Z"},"content_sha256":"5a9223cf5857c319b41904ef0b93fe0035612d697e9cd4ba6ea7cf1a885d27ab","schema_version":"1.0","event_id":"sha256:5a9223cf5857c319b41904ef0b93fe0035612d697e9cd4ba6ea7cf1a885d27ab"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZAPMIWALYOPZ66RWMCXM5I2W5G/bundle.json","state_url":"https://pith.science/pith/ZAPMIWALYOPZ66RWMCXM5I2W5G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZAPMIWALYOPZ66RWMCXM5I2W5G/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":"2026-06-27T22:43:11Z","links":{"resolver":"https://pith.science/pith/ZAPMIWALYOPZ66RWMCXM5I2W5G","bundle":"https://pith.science/pith/ZAPMIWALYOPZ66RWMCXM5I2W5G/bundle.json","state":"https://pith.science/pith/ZAPMIWALYOPZ66RWMCXM5I2W5G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZAPMIWALYOPZ66RWMCXM5I2W5G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZAPMIWALYOPZ66RWMCXM5I2W5G","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":"131a9f66f49bf099bd275726121e8b6d31e15d46ecf4a6bdaa77545834a00015","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T17:54:04Z","title_canon_sha256":"16f9dba2dd3bcb13b6b67e2f61130416de9e3f83c968e067f12d7ab623cbf638"},"schema_version":"1.0","source":{"id":"2606.05152","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05152","created_at":"2026-06-04T02:07:54Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05152v1","created_at":"2026-06-04T02:07:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05152","created_at":"2026-06-04T02:07:54Z"},{"alias_kind":"pith_short_12","alias_value":"ZAPMIWALYOPZ","created_at":"2026-06-04T02:07:54Z"},{"alias_kind":"pith_short_16","alias_value":"ZAPMIWALYOPZ66RW","created_at":"2026-06-04T02:07:54Z"},{"alias_kind":"pith_short_8","alias_value":"ZAPMIWAL","created_at":"2026-06-04T02:07:54Z"}],"graph_snapshots":[{"event_id":"sha256:5a9223cf5857c319b41904ef0b93fe0035612d697e9cd4ba6ea7cf1a885d27ab","target":"graph","created_at":"2026-06-04T02:07:54Z","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/2606.05152/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reasoning models have advanced rapidly, but the dominant reinforcement learning from verifiable rewards (RLVR) recipe remains surprisingly narrow: sample many responses and reward each with a single bit indicating whether the final answer is correct. Yet many settings provide rich feedback, including execution traces, tool outputs, expert corrections, and model self-evaluations. We study how to use such feedback through a distributional variant of the classic imitation learning algorithm DAgger, where the learner has local access to an expert distribution on states visited by the current polic","authors_text":"Jacob Fein-Ashley, Paria Rashidinejad, Rishabh Agrawal","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T17:54:04Z","title":"Reinforcement Learning from Rich Feedback with Distributional DAgger"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05152","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:c4a5a71e6214b2b325a0e20a8f773aab5daa241d86b9a02c5e3197126b5e5005","target":"record","created_at":"2026-06-04T02:07:54Z","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":"131a9f66f49bf099bd275726121e8b6d31e15d46ecf4a6bdaa77545834a00015","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T17:54:04Z","title_canon_sha256":"16f9dba2dd3bcb13b6b67e2f61130416de9e3f83c968e067f12d7ab623cbf638"},"schema_version":"1.0","source":{"id":"2606.05152","kind":"arxiv","version":1}},"canonical_sha256":"c81ec4580bc39f9f7a3660aecea356e9973b194a9b80f047c57c43596788f6d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c81ec4580bc39f9f7a3660aecea356e9973b194a9b80f047c57c43596788f6d7","first_computed_at":"2026-06-04T02:07:54.174843Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T02:07:54.174843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oPNtsBd3txS/Eq+fXKhNp+QqfZ56j86d8fZvsmOyDzO6Q9HioCStL5RJUiplG8Itpb4CqyS/zMjwnheNuxbYDg==","signature_status":"signed_v1","signed_at":"2026-06-04T02:07:54.175388Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05152","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c4a5a71e6214b2b325a0e20a8f773aab5daa241d86b9a02c5e3197126b5e5005","sha256:5a9223cf5857c319b41904ef0b93fe0035612d697e9cd4ba6ea7cf1a885d27ab"],"state_sha256":"f55f3857b2a7209444671618c2a19ec7a2ef3558e2794c8e24cb0e3efa397a4b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qzJtaJKQWEW7uida3g4GVm+NCHU2BrDJSZW5zn46bairYkNNI9qOCnxvBCFjkYnxeOrRDDVum+MqQVYX6ieHDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T22:43:11.784476Z","bundle_sha256":"9cac0bb6edf5a42dde32c35ff506f24d2bb4d3490a4edba32ba57ba9313828c3"}}