{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:K2LIXZ47PIQSRKDEVODZNN4V7E","short_pith_number":"pith:K2LIXZ47","schema_version":"1.0","canonical_sha256":"56968be79f7a2128a864ab8796b795f91a0f4578a7695e71c21b9059dce316d7","source":{"kind":"arxiv","id":"2503.17865","version":1},"attestation_state":"computed","paper":{"title":"Understanding Inverse Reinforcement Learning under Overparameterization: Non-Asymptotic Analysis and Global Optimality","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alfredo Garcia, Chenliang Li, Mingyi Hong, Ruijia Zhang, Siliang Zeng","submitted_at":"2025-03-22T21:16:08Z","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"},"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":"2503.17865","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-03-22T21:16:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0a5da02622270d2ecf27020f8286d87df81f5c1305ff6d78db7ff8c442253ad8","abstract_canon_sha256":"282729d8c4493c74e8fd26864bcf77fa37d0ea176a7432d5ac6fcaadf2d941cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:37:56.819464Z","signature_b64":"dW8seMKc7a5pdLuPh6GVH8zopKK6n8w6rgkrkA4GDaWvJVtrDZBdVEfS2/zrSFzHPc4Kg2HoXrIfTcjIG9CXAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56968be79f7a2128a864ab8796b795f91a0f4578a7695e71c21b9059dce316d7","last_reissued_at":"2026-07-05T10:37:56.818851Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:37:56.818851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Inverse Reinforcement Learning under Overparameterization: Non-Asymptotic Analysis and Global Optimality","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alfredo Garcia, Chenliang Li, Mingyi Hong, Ruijia Zhang, Siliang Zeng","submitted_at":"2025-03-22T21:16:08Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.17865","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/2503.17865/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":"2503.17865","created_at":"2026-07-05T10:37:56.818927+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.17865v1","created_at":"2026-07-05T10:37:56.818927+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.17865","created_at":"2026-07-05T10:37:56.818927+00:00"},{"alias_kind":"pith_short_12","alias_value":"K2LIXZ47PIQS","created_at":"2026-07-05T10:37:56.818927+00:00"},{"alias_kind":"pith_short_16","alias_value":"K2LIXZ47PIQSRKDE","created_at":"2026-07-05T10:37:56.818927+00:00"},{"alias_kind":"pith_short_8","alias_value":"K2LIXZ47","created_at":"2026-07-05T10:37:56.818927+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/K2LIXZ47PIQSRKDEVODZNN4V7E","json":"https://pith.science/pith/K2LIXZ47PIQSRKDEVODZNN4V7E.json","graph_json":"https://pith.science/api/pith-number/K2LIXZ47PIQSRKDEVODZNN4V7E/graph.json","events_json":"https://pith.science/api/pith-number/K2LIXZ47PIQSRKDEVODZNN4V7E/events.json","paper":"https://pith.science/paper/K2LIXZ47"},"agent_actions":{"view_html":"https://pith.science/pith/K2LIXZ47PIQSRKDEVODZNN4V7E","download_json":"https://pith.science/pith/K2LIXZ47PIQSRKDEVODZNN4V7E.json","view_paper":"https://pith.science/paper/K2LIXZ47","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.17865&json=true","fetch_graph":"https://pith.science/api/pith-number/K2LIXZ47PIQSRKDEVODZNN4V7E/graph.json","fetch_events":"https://pith.science/api/pith-number/K2LIXZ47PIQSRKDEVODZNN4V7E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K2LIXZ47PIQSRKDEVODZNN4V7E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K2LIXZ47PIQSRKDEVODZNN4V7E/action/storage_attestation","attest_author":"https://pith.science/pith/K2LIXZ47PIQSRKDEVODZNN4V7E/action/author_attestation","sign_citation":"https://pith.science/pith/K2LIXZ47PIQSRKDEVODZNN4V7E/action/citation_signature","submit_replication":"https://pith.science/pith/K2LIXZ47PIQSRKDEVODZNN4V7E/action/replication_record"}},"created_at":"2026-07-05T10:37:56.818927+00:00","updated_at":"2026-07-05T10:37:56.818927+00:00"}