{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:KIFOZJWQLEPSTCHVIY4G6WIZIX","short_pith_number":"pith:KIFOZJWQ","schema_version":"1.0","canonical_sha256":"520aeca6d0591f2988f546386f591945cb5248486124059b213f7c6e03db05b1","source":{"kind":"arxiv","id":"1301.3630","version":4},"attestation_state":"computed","paper":{"title":"Behavior Pattern Recognition using A New Representation Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Peter A. Beling, Qifeng Qiao","submitted_at":"2013-01-16T09:01:47Z","abstract_excerpt":"We study the use of inverse reinforcement learning (IRL) as a tool for the recognition of agents' behavior on the basis of observation of their sequential decision behavior interacting with the environment. We model the problem faced by the agents as a Markov decision process (MDP) and model the observed behavior of the agents in terms of forward planning for the MDP. We use IRL to learn reward functions and then use these reward functions as the basis for clustering or classification models. Experimental studies with GridWorld, a navigation problem, and the secretary problem, an optimal stopp"},"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":"1301.3630","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-01-16T09:01:47Z","cross_cats_sorted":[],"title_canon_sha256":"bc361bc65155e7fac6ce7406d08a42aa56e4e7d059933091c0ba0ad9c87f5cb9","abstract_canon_sha256":"fc29a3e9695d0bb7f71858246f0e222fee6ad2a497a5bed76e63b3b4d8071e71"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:30:14.712620Z","signature_b64":"I4fudqCj37zHukCCeU6YilIfIsZ5M5v31poWcDtKgrA/9ZjwKWYYOHHeqT5wp3BZxAdBPTrjOISbOs6+D7WWBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"520aeca6d0591f2988f546386f591945cb5248486124059b213f7c6e03db05b1","last_reissued_at":"2026-05-18T03:30:14.711849Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:30:14.711849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Behavior Pattern Recognition using A New Representation Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Peter A. Beling, Qifeng Qiao","submitted_at":"2013-01-16T09:01:47Z","abstract_excerpt":"We study the use of inverse reinforcement learning (IRL) as a tool for the recognition of agents' behavior on the basis of observation of their sequential decision behavior interacting with the environment. We model the problem faced by the agents as a Markov decision process (MDP) and model the observed behavior of the agents in terms of forward planning for the MDP. We use IRL to learn reward functions and then use these reward functions as the basis for clustering or classification models. Experimental studies with GridWorld, a navigation problem, and the secretary problem, an optimal stopp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.3630","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1301.3630","created_at":"2026-05-18T03:30:14.711992+00:00"},{"alias_kind":"arxiv_version","alias_value":"1301.3630v4","created_at":"2026-05-18T03:30:14.711992+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.3630","created_at":"2026-05-18T03:30:14.711992+00:00"},{"alias_kind":"pith_short_12","alias_value":"KIFOZJWQLEPS","created_at":"2026-05-18T12:27:49.015174+00:00"},{"alias_kind":"pith_short_16","alias_value":"KIFOZJWQLEPSTCHV","created_at":"2026-05-18T12:27:49.015174+00:00"},{"alias_kind":"pith_short_8","alias_value":"KIFOZJWQ","created_at":"2026-05-18T12:27:49.015174+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/KIFOZJWQLEPSTCHVIY4G6WIZIX","json":"https://pith.science/pith/KIFOZJWQLEPSTCHVIY4G6WIZIX.json","graph_json":"https://pith.science/api/pith-number/KIFOZJWQLEPSTCHVIY4G6WIZIX/graph.json","events_json":"https://pith.science/api/pith-number/KIFOZJWQLEPSTCHVIY4G6WIZIX/events.json","paper":"https://pith.science/paper/KIFOZJWQ"},"agent_actions":{"view_html":"https://pith.science/pith/KIFOZJWQLEPSTCHVIY4G6WIZIX","download_json":"https://pith.science/pith/KIFOZJWQLEPSTCHVIY4G6WIZIX.json","view_paper":"https://pith.science/paper/KIFOZJWQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1301.3630&json=true","fetch_graph":"https://pith.science/api/pith-number/KIFOZJWQLEPSTCHVIY4G6WIZIX/graph.json","fetch_events":"https://pith.science/api/pith-number/KIFOZJWQLEPSTCHVIY4G6WIZIX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KIFOZJWQLEPSTCHVIY4G6WIZIX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KIFOZJWQLEPSTCHVIY4G6WIZIX/action/storage_attestation","attest_author":"https://pith.science/pith/KIFOZJWQLEPSTCHVIY4G6WIZIX/action/author_attestation","sign_citation":"https://pith.science/pith/KIFOZJWQLEPSTCHVIY4G6WIZIX/action/citation_signature","submit_replication":"https://pith.science/pith/KIFOZJWQLEPSTCHVIY4G6WIZIX/action/replication_record"}},"created_at":"2026-05-18T03:30:14.711992+00:00","updated_at":"2026-05-18T03:30:14.711992+00:00"}