{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SNHBDF3EN5GTWPSZ3OBYSJ3UQO","short_pith_number":"pith:SNHBDF3E","canonical_record":{"source":{"id":"2504.01766","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2025-04-02T14:18:52Z","cross_cats_sorted":["cs.LG","cs.SY"],"title_canon_sha256":"7689fb6fe663b973e05354fb49a56c483eb81b6313ae5e82b3bc72035117d3d7","abstract_canon_sha256":"3eab46ec7ec607efc9428b2b809fa323bde607af93081a39f32795ee9804425c"},"schema_version":"1.0"},"canonical_sha256":"934e1197646f4d3b3e59db8389277483abed5f7a0bb7e1003af9ef3bbe06c261","source":{"kind":"arxiv","id":"2504.01766","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.01766","created_at":"2026-07-05T10:43:29Z"},{"alias_kind":"arxiv_version","alias_value":"2504.01766v1","created_at":"2026-07-05T10:43:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01766","created_at":"2026-07-05T10:43:29Z"},{"alias_kind":"pith_short_12","alias_value":"SNHBDF3EN5GT","created_at":"2026-07-05T10:43:29Z"},{"alias_kind":"pith_short_16","alias_value":"SNHBDF3EN5GTWPSZ","created_at":"2026-07-05T10:43:29Z"},{"alias_kind":"pith_short_8","alias_value":"SNHBDF3E","created_at":"2026-07-05T10:43:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SNHBDF3EN5GTWPSZ3OBYSJ3UQO","target":"record","payload":{"canonical_record":{"source":{"id":"2504.01766","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2025-04-02T14:18:52Z","cross_cats_sorted":["cs.LG","cs.SY"],"title_canon_sha256":"7689fb6fe663b973e05354fb49a56c483eb81b6313ae5e82b3bc72035117d3d7","abstract_canon_sha256":"3eab46ec7ec607efc9428b2b809fa323bde607af93081a39f32795ee9804425c"},"schema_version":"1.0"},"canonical_sha256":"934e1197646f4d3b3e59db8389277483abed5f7a0bb7e1003af9ef3bbe06c261","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:29.565819Z","signature_b64":"uXq72SiQ2l1Bki8qcTesJ3Q31it+9UT7hydxfCb6wnMo4wvhZfvyuUk6PCGD0E3RfXW/wJGJH112kGIhJYavDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"934e1197646f4d3b3e59db8389277483abed5f7a0bb7e1003af9ef3bbe06c261","last_reissued_at":"2026-07-05T10:43:29.565364Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:29.565364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.01766","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":"2026-07-05T10:43:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/HPBwPT0TGIUBKSW7/k33Q4L7kkbscRsFEs2i83X5ZA+2wm9zOjQQ9BSRHsdiWvmLqqkCJkLvhDCcw/DX6K5Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T20:54:00.844332Z"},"content_sha256":"e205a2f74976284a6019d498f3017faa1361b2762bf43fdd87b5d1bc3c5fde61","schema_version":"1.0","event_id":"sha256:e205a2f74976284a6019d498f3017faa1361b2762bf43fdd87b5d1bc3c5fde61"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SNHBDF3EN5GTWPSZ3OBYSJ3UQO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning with Imperfect Models: When Multi-step Prediction Mitigates Compounding Error","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SY"],"primary_cat":"eess.SY","authors_text":"Anne Somalwar, Bruce D. Lee, George J. Pappas, Nikolai Matni","submitted_at":"2025-04-02T14:18:52Z","abstract_excerpt":"Compounding error, where small prediction mistakes accumulate over time, presents a major challenge in learning-based control. For example, this issue often limits the performance of model-based reinforcement learning and imitation learning. One common approach to mitigate compounding error is to train multi-step predictors directly, rather than relying on autoregressive rollout of a single-step model. However, it is not well understood when the benefits of multi-step prediction outweigh the added complexity of learning a more complicated model. In this work, we provide a rigorous analysis of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.01766","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/2504.01766/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":"2026-07-05T10:43:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mcF0hJBnIjYwpekSDf14DCYcPAZS7C+Dglr5GfeZLhEe4qGBF09yF4DwXsB3BkPHw+10li0t6huZMbD1VUayCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T20:54:00.844874Z"},"content_sha256":"ac2fb8d6947fd363426ef73809a66db0f0e4670db654bfc00a1400dd470cf573","schema_version":"1.0","event_id":"sha256:ac2fb8d6947fd363426ef73809a66db0f0e4670db654bfc00a1400dd470cf573"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SNHBDF3EN5GTWPSZ3OBYSJ3UQO/bundle.json","state_url":"https://pith.science/pith/SNHBDF3EN5GTWPSZ3OBYSJ3UQO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SNHBDF3EN5GTWPSZ3OBYSJ3UQO/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":"2026-08-02T20:54:00Z","links":{"resolver":"https://pith.science/pith/SNHBDF3EN5GTWPSZ3OBYSJ3UQO","bundle":"https://pith.science/pith/SNHBDF3EN5GTWPSZ3OBYSJ3UQO/bundle.json","state":"https://pith.science/pith/SNHBDF3EN5GTWPSZ3OBYSJ3UQO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SNHBDF3EN5GTWPSZ3OBYSJ3UQO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SNHBDF3EN5GTWPSZ3OBYSJ3UQO","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":"3eab46ec7ec607efc9428b2b809fa323bde607af93081a39f32795ee9804425c","cross_cats_sorted":["cs.LG","cs.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2025-04-02T14:18:52Z","title_canon_sha256":"7689fb6fe663b973e05354fb49a56c483eb81b6313ae5e82b3bc72035117d3d7"},"schema_version":"1.0","source":{"id":"2504.01766","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.01766","created_at":"2026-07-05T10:43:29Z"},{"alias_kind":"arxiv_version","alias_value":"2504.01766v1","created_at":"2026-07-05T10:43:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01766","created_at":"2026-07-05T10:43:29Z"},{"alias_kind":"pith_short_12","alias_value":"SNHBDF3EN5GT","created_at":"2026-07-05T10:43:29Z"},{"alias_kind":"pith_short_16","alias_value":"SNHBDF3EN5GTWPSZ","created_at":"2026-07-05T10:43:29Z"},{"alias_kind":"pith_short_8","alias_value":"SNHBDF3E","created_at":"2026-07-05T10:43:29Z"}],"graph_snapshots":[{"event_id":"sha256:ac2fb8d6947fd363426ef73809a66db0f0e4670db654bfc00a1400dd470cf573","target":"graph","created_at":"2026-07-05T10:43:29Z","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/2504.01766/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Compounding error, where small prediction mistakes accumulate over time, presents a major challenge in learning-based control. For example, this issue often limits the performance of model-based reinforcement learning and imitation learning. One common approach to mitigate compounding error is to train multi-step predictors directly, rather than relying on autoregressive rollout of a single-step model. However, it is not well understood when the benefits of multi-step prediction outweigh the added complexity of learning a more complicated model. In this work, we provide a rigorous analysis of ","authors_text":"Anne Somalwar, Bruce D. Lee, George J. Pappas, Nikolai Matni","cross_cats":["cs.LG","cs.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2025-04-02T14:18:52Z","title":"Learning with Imperfect Models: When Multi-step Prediction Mitigates Compounding Error"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.01766","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:e205a2f74976284a6019d498f3017faa1361b2762bf43fdd87b5d1bc3c5fde61","target":"record","created_at":"2026-07-05T10:43:29Z","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":"3eab46ec7ec607efc9428b2b809fa323bde607af93081a39f32795ee9804425c","cross_cats_sorted":["cs.LG","cs.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2025-04-02T14:18:52Z","title_canon_sha256":"7689fb6fe663b973e05354fb49a56c483eb81b6313ae5e82b3bc72035117d3d7"},"schema_version":"1.0","source":{"id":"2504.01766","kind":"arxiv","version":1}},"canonical_sha256":"934e1197646f4d3b3e59db8389277483abed5f7a0bb7e1003af9ef3bbe06c261","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"934e1197646f4d3b3e59db8389277483abed5f7a0bb7e1003af9ef3bbe06c261","first_computed_at":"2026-07-05T10:43:29.565364Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:43:29.565364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uXq72SiQ2l1Bki8qcTesJ3Q31it+9UT7hydxfCb6wnMo4wvhZfvyuUk6PCGD0E3RfXW/wJGJH112kGIhJYavDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:43:29.565819Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.01766","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e205a2f74976284a6019d498f3017faa1361b2762bf43fdd87b5d1bc3c5fde61","sha256:ac2fb8d6947fd363426ef73809a66db0f0e4670db654bfc00a1400dd470cf573"],"state_sha256":"af80ccbe5f3af5d329ee5a42d8eef50c09c6ae5204e2f3d8a84ea4b74c82e405"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6IbS89pp/iK+tPcp2ZjhwzHD/5iQctfncCsnXUhySXFzHBEb0eFa4p8sUPsBKnq4+GKXi+K8/wpnc+NXTD5dCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-02T20:54:00.849850Z","bundle_sha256":"254d254e6844c842ec13d2cc4f9161a9471bd648d8118bda0d128918ebbbc290"}}