{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:K2LIXZ47PIQSRKDEVODZNN4V7E","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":"282729d8c4493c74e8fd26864bcf77fa37d0ea176a7432d5ac6fcaadf2d941cc","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-03-22T21:16:08Z","title_canon_sha256":"0a5da02622270d2ecf27020f8286d87df81f5c1305ff6d78db7ff8c442253ad8"},"schema_version":"1.0","source":{"id":"2503.17865","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.17865","created_at":"2026-07-05T10:37:56Z"},{"alias_kind":"arxiv_version","alias_value":"2503.17865v1","created_at":"2026-07-05T10:37:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.17865","created_at":"2026-07-05T10:37:56Z"},{"alias_kind":"pith_short_12","alias_value":"K2LIXZ47PIQS","created_at":"2026-07-05T10:37:56Z"},{"alias_kind":"pith_short_16","alias_value":"K2LIXZ47PIQSRKDE","created_at":"2026-07-05T10:37:56Z"},{"alias_kind":"pith_short_8","alias_value":"K2LIXZ47","created_at":"2026-07-05T10:37:56Z"}],"graph_snapshots":[{"event_id":"sha256:ba92a99c7b28694131e0278ab7ec223fdb7ed49ca85d0fba93935ec4d1da01a7","target":"graph","created_at":"2026-07-05T10:37:56Z","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/2503.17865/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The goal of the Inverse reinforcement learning (IRL) task is to identify the underlying reward function and the corresponding optimal policy from a set of expert demonstrations. While most IRL algorithms' theoretical guarantees rely on a linear reward structure, we aim to extend the theoretical understanding of IRL to scenarios where the reward function is parameterized by neural networks. Meanwhile, conventional IRL algorithms usually adopt a nested structure, leading to computational inefficiency, especially in high-dimensional settings. To address this problem, we propose the first two-time","authors_text":"Alfredo Garcia, Chenliang Li, Mingyi Hong, Ruijia Zhang, Siliang Zeng","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-03-22T21:16:08Z","title":"Understanding Inverse Reinforcement Learning under Overparameterization: Non-Asymptotic Analysis and Global Optimality"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.17865","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:c099dc205985a0672ab63f9abcec2280b6093aba83910f673e117be279cce46c","target":"record","created_at":"2026-07-05T10:37:56Z","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":"282729d8c4493c74e8fd26864bcf77fa37d0ea176a7432d5ac6fcaadf2d941cc","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-03-22T21:16:08Z","title_canon_sha256":"0a5da02622270d2ecf27020f8286d87df81f5c1305ff6d78db7ff8c442253ad8"},"schema_version":"1.0","source":{"id":"2503.17865","kind":"arxiv","version":1}},"canonical_sha256":"56968be79f7a2128a864ab8796b795f91a0f4578a7695e71c21b9059dce316d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"56968be79f7a2128a864ab8796b795f91a0f4578a7695e71c21b9059dce316d7","first_computed_at":"2026-07-05T10:37:56.818851Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:37:56.818851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dW8seMKc7a5pdLuPh6GVH8zopKK6n8w6rgkrkA4GDaWvJVtrDZBdVEfS2/zrSFzHPc4Kg2HoXrIfTcjIG9CXAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:37:56.819464Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.17865","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c099dc205985a0672ab63f9abcec2280b6093aba83910f673e117be279cce46c","sha256:ba92a99c7b28694131e0278ab7ec223fdb7ed49ca85d0fba93935ec4d1da01a7"],"state_sha256":"b55816c8ee0bc6e0b2c48a5cd331d5b2f168bceb06cb524354f995b38ae7b9b0"}