{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XWHXRFHSH56ISCRCOLA34SMOQP","short_pith_number":"pith:XWHXRFHS","schema_version":"1.0","canonical_sha256":"bd8f7894f23f7c890a2272c1be498e83e1156e19008143ebad0cd25bafe22c3f","source":{"kind":"arxiv","id":"2507.04396","version":1},"attestation_state":"computed","paper":{"title":"Inverse Reinforcement Learning using Revealed Preferences and Passive Stochastic Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.SP"],"primary_cat":"cs.LG","authors_text":"Vikram Krishnamurthy","submitted_at":"2025-07-06T13:56:02Z","abstract_excerpt":"This monograph, spanning three chapters, explores Inverse Reinforcement Learning (IRL). The first two chapters view inverse reinforcement learning (IRL) through the lens of revealed preferences from microeconomics while the third chapter studies adaptive IRL via Langevin dynamics stochastic gradient algorithms.\n  Chapter uses classical revealed preference theory (Afriat's theorem and extensions) to identify constrained utility maximizers based on observed agent actions. This allows for the reconstruction of set-valued estimates of an agent's utility. We illustrate this procedure by identifying"},"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":"2507.04396","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-06T13:56:02Z","cross_cats_sorted":["eess.SP"],"title_canon_sha256":"b868462939b8cb7a401b7a7ef2caec94f3a2b3fe795a1c677ac88e7e57b4af9c","abstract_canon_sha256":"298370edb3c2261e38b395d3528c93d15916182f7759ab2ea750cfa16c2e36ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:47.166824Z","signature_b64":"ee9V+WTrkaqgdmtcUtcb7WO80qmlknuWMJUvhe7k3sjB9SxqsVy+NHgLddTqk2KCukIVpbInvL2nwM7m785iAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd8f7894f23f7c890a2272c1be498e83e1156e19008143ebad0cd25bafe22c3f","last_reissued_at":"2026-07-05T11:32:47.166349Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:47.166349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inverse Reinforcement Learning using Revealed Preferences and Passive Stochastic Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.SP"],"primary_cat":"cs.LG","authors_text":"Vikram Krishnamurthy","submitted_at":"2025-07-06T13:56:02Z","abstract_excerpt":"This monograph, spanning three chapters, explores Inverse Reinforcement Learning (IRL). The first two chapters view inverse reinforcement learning (IRL) through the lens of revealed preferences from microeconomics while the third chapter studies adaptive IRL via Langevin dynamics stochastic gradient algorithms.\n  Chapter uses classical revealed preference theory (Afriat's theorem and extensions) to identify constrained utility maximizers based on observed agent actions. This allows for the reconstruction of set-valued estimates of an agent's utility. We illustrate this procedure by identifying"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04396","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/2507.04396/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":"2507.04396","created_at":"2026-07-05T11:32:47.166405+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.04396v1","created_at":"2026-07-05T11:32:47.166405+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04396","created_at":"2026-07-05T11:32:47.166405+00:00"},{"alias_kind":"pith_short_12","alias_value":"XWHXRFHSH56I","created_at":"2026-07-05T11:32:47.166405+00:00"},{"alias_kind":"pith_short_16","alias_value":"XWHXRFHSH56ISCRC","created_at":"2026-07-05T11:32:47.166405+00:00"},{"alias_kind":"pith_short_8","alias_value":"XWHXRFHS","created_at":"2026-07-05T11:32:47.166405+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/XWHXRFHSH56ISCRCOLA34SMOQP","json":"https://pith.science/pith/XWHXRFHSH56ISCRCOLA34SMOQP.json","graph_json":"https://pith.science/api/pith-number/XWHXRFHSH56ISCRCOLA34SMOQP/graph.json","events_json":"https://pith.science/api/pith-number/XWHXRFHSH56ISCRCOLA34SMOQP/events.json","paper":"https://pith.science/paper/XWHXRFHS"},"agent_actions":{"view_html":"https://pith.science/pith/XWHXRFHSH56ISCRCOLA34SMOQP","download_json":"https://pith.science/pith/XWHXRFHSH56ISCRCOLA34SMOQP.json","view_paper":"https://pith.science/paper/XWHXRFHS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.04396&json=true","fetch_graph":"https://pith.science/api/pith-number/XWHXRFHSH56ISCRCOLA34SMOQP/graph.json","fetch_events":"https://pith.science/api/pith-number/XWHXRFHSH56ISCRCOLA34SMOQP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XWHXRFHSH56ISCRCOLA34SMOQP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XWHXRFHSH56ISCRCOLA34SMOQP/action/storage_attestation","attest_author":"https://pith.science/pith/XWHXRFHSH56ISCRCOLA34SMOQP/action/author_attestation","sign_citation":"https://pith.science/pith/XWHXRFHSH56ISCRCOLA34SMOQP/action/citation_signature","submit_replication":"https://pith.science/pith/XWHXRFHSH56ISCRCOLA34SMOQP/action/replication_record"}},"created_at":"2026-07-05T11:32:47.166405+00:00","updated_at":"2026-07-05T11:32:47.166405+00:00"}