{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CLLCC5JYWREU7JERBGUTO2STS3","short_pith_number":"pith:CLLCC5JY","schema_version":"1.0","canonical_sha256":"12d6217538b4494fa49109a9376a5396c4ce836384c353060f59b3323c0c5e0c","source":{"kind":"arxiv","id":"2405.08756","version":1},"attestation_state":"computed","paper":{"title":"Stable Inverse Reinforcement Learning: Policies from Control Lyapunov Landscapes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY"],"primary_cat":"eess.SY","authors_text":"Armin Lederer, Leonhard Sprandl, Samuel Tesfazgi, Sandra Hirche","submitted_at":"2024-05-14T16:40:45Z","abstract_excerpt":"Learning from expert demonstrations to flexibly program an autonomous system with complex behaviors or to predict an agent's behavior is a powerful tool, especially in collaborative control settings. A common method to solve this problem is inverse reinforcement learning (IRL), where the observed agent, e.g., a human demonstrator, is assumed to behave according to the optimization of an intrinsic cost function that reflects its intent and informs its control actions. While the framework is expressive, it is also computationally demanding and generally lacks convergence guarantees. We therefore"},"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":"2405.08756","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2024-05-14T16:40:45Z","cross_cats_sorted":["cs.LG","cs.SY"],"title_canon_sha256":"02cb98e2faf63b8d7fc166633990ae58c9077dce577c77086fb05a89c8a149e6","abstract_canon_sha256":"4451f71294cfbf07c15f6d20d2fa7c8c9dc8da0add093208ee3db67a6c757f68"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:19:05.060943Z","signature_b64":"pc4qIfitQsv0TxKzLIfhYTEDZGCLgPnSN1u3eA7L41TlCwS+EZlKrDBwZmQ0xEWO8DhGOw8e7+wE8FoZmex8Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12d6217538b4494fa49109a9376a5396c4ce836384c353060f59b3323c0c5e0c","last_reissued_at":"2026-07-05T08:19:05.059939Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:19:05.059939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stable Inverse Reinforcement Learning: Policies from Control Lyapunov Landscapes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY"],"primary_cat":"eess.SY","authors_text":"Armin Lederer, Leonhard Sprandl, Samuel Tesfazgi, Sandra Hirche","submitted_at":"2024-05-14T16:40:45Z","abstract_excerpt":"Learning from expert demonstrations to flexibly program an autonomous system with complex behaviors or to predict an agent's behavior is a powerful tool, especially in collaborative control settings. A common method to solve this problem is inverse reinforcement learning (IRL), where the observed agent, e.g., a human demonstrator, is assumed to behave according to the optimization of an intrinsic cost function that reflects its intent and informs its control actions. While the framework is expressive, it is also computationally demanding and generally lacks convergence guarantees. We therefore"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.08756","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/2405.08756/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":"2405.08756","created_at":"2026-07-05T08:19:05.060402+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.08756v1","created_at":"2026-07-05T08:19:05.060402+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.08756","created_at":"2026-07-05T08:19:05.060402+00:00"},{"alias_kind":"pith_short_12","alias_value":"CLLCC5JYWREU","created_at":"2026-07-05T08:19:05.060402+00:00"},{"alias_kind":"pith_short_16","alias_value":"CLLCC5JYWREU7JER","created_at":"2026-07-05T08:19:05.060402+00:00"},{"alias_kind":"pith_short_8","alias_value":"CLLCC5JY","created_at":"2026-07-05T08:19:05.060402+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.09128","citing_title":"A Review On Safe Reinforcement Learning Using Lyapunov and Barrier Functions","ref_index":74,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CLLCC5JYWREU7JERBGUTO2STS3","json":"https://pith.science/pith/CLLCC5JYWREU7JERBGUTO2STS3.json","graph_json":"https://pith.science/api/pith-number/CLLCC5JYWREU7JERBGUTO2STS3/graph.json","events_json":"https://pith.science/api/pith-number/CLLCC5JYWREU7JERBGUTO2STS3/events.json","paper":"https://pith.science/paper/CLLCC5JY"},"agent_actions":{"view_html":"https://pith.science/pith/CLLCC5JYWREU7JERBGUTO2STS3","download_json":"https://pith.science/pith/CLLCC5JYWREU7JERBGUTO2STS3.json","view_paper":"https://pith.science/paper/CLLCC5JY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.08756&json=true","fetch_graph":"https://pith.science/api/pith-number/CLLCC5JYWREU7JERBGUTO2STS3/graph.json","fetch_events":"https://pith.science/api/pith-number/CLLCC5JYWREU7JERBGUTO2STS3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CLLCC5JYWREU7JERBGUTO2STS3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CLLCC5JYWREU7JERBGUTO2STS3/action/storage_attestation","attest_author":"https://pith.science/pith/CLLCC5JYWREU7JERBGUTO2STS3/action/author_attestation","sign_citation":"https://pith.science/pith/CLLCC5JYWREU7JERBGUTO2STS3/action/citation_signature","submit_replication":"https://pith.science/pith/CLLCC5JYWREU7JERBGUTO2STS3/action/replication_record"}},"created_at":"2026-07-05T08:19:05.060402+00:00","updated_at":"2026-07-05T08:19:05.060402+00:00"}