{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AKBDHCY5DDY6U2R2OGJ3BZR75S","short_pith_number":"pith:AKBDHCY5","schema_version":"1.0","canonical_sha256":"0282338b1d18f1ea6a3a7193b0e63fecac4acfdb8d00737743f890733d037d15","source":{"kind":"arxiv","id":"2312.14292","version":2},"attestation_state":"computed","paper":{"title":"Incorporating Human Flexibility through Reward Preferences in Human-AI Teaming","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Anil Murthy, Mudit Verma, Siddhant Bhambri, Subbarao Kambhampati, Upasana Biswas","submitted_at":"2023-12-21T20:48:15Z","abstract_excerpt":"Preference-based Reinforcement Learning (PbRL) has made significant strides in single-agent settings, but has not been studied for multi-agent frameworks. On the other hand, modeling cooperation between multiple agents, specifically, Human-AI Teaming settings while ensuring successful task completion is a challenging problem. To this end, we perform the first investigation of multi-agent PbRL by extending single-agent PbRL to the two-agent teaming settings and formulate it as a Human-AI PbRL Cooperation Game, where the RL agent queries the human-in-the-loop to elicit task objective and human's"},"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":"2312.14292","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-21T20:48:15Z","cross_cats_sorted":["cs.LG","cs.MA"],"title_canon_sha256":"8a5c9a30b1d469bb2833c76f272ed25f3cdec87299430776983df4f9a87d84f0","abstract_canon_sha256":"df576354bbdf2577f7d323b29933f7c3e46e2d11e0a80fef855d9f377a882df9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:11:23.343543Z","signature_b64":"5W2C/+1vLis1/eIHQN707Ph8UOj5MnBBl1bImA7I91PrYj6fDfa+5Eue9AGX1fM+HhPNE1m/80WQQETXRQjcAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0282338b1d18f1ea6a3a7193b0e63fecac4acfdb8d00737743f890733d037d15","last_reissued_at":"2026-07-05T09:11:23.343091Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:11:23.343091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Incorporating Human Flexibility through Reward Preferences in Human-AI Teaming","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Anil Murthy, Mudit Verma, Siddhant Bhambri, Subbarao Kambhampati, Upasana Biswas","submitted_at":"2023-12-21T20:48:15Z","abstract_excerpt":"Preference-based Reinforcement Learning (PbRL) has made significant strides in single-agent settings, but has not been studied for multi-agent frameworks. On the other hand, modeling cooperation between multiple agents, specifically, Human-AI Teaming settings while ensuring successful task completion is a challenging problem. To this end, we perform the first investigation of multi-agent PbRL by extending single-agent PbRL to the two-agent teaming settings and formulate it as a Human-AI PbRL Cooperation Game, where the RL agent queries the human-in-the-loop to elicit task objective and human's"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.14292","kind":"arxiv","version":2},"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/2312.14292/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":"2312.14292","created_at":"2026-07-05T09:11:23.343151+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.14292v2","created_at":"2026-07-05T09:11:23.343151+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.14292","created_at":"2026-07-05T09:11:23.343151+00:00"},{"alias_kind":"pith_short_12","alias_value":"AKBDHCY5DDY6","created_at":"2026-07-05T09:11:23.343151+00:00"},{"alias_kind":"pith_short_16","alias_value":"AKBDHCY5DDY6U2R2","created_at":"2026-07-05T09:11:23.343151+00:00"},{"alias_kind":"pith_short_8","alias_value":"AKBDHCY5","created_at":"2026-07-05T09:11:23.343151+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02198","citing_title":"What Types of Human-AI Teams Exist?","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AKBDHCY5DDY6U2R2OGJ3BZR75S","json":"https://pith.science/pith/AKBDHCY5DDY6U2R2OGJ3BZR75S.json","graph_json":"https://pith.science/api/pith-number/AKBDHCY5DDY6U2R2OGJ3BZR75S/graph.json","events_json":"https://pith.science/api/pith-number/AKBDHCY5DDY6U2R2OGJ3BZR75S/events.json","paper":"https://pith.science/paper/AKBDHCY5"},"agent_actions":{"view_html":"https://pith.science/pith/AKBDHCY5DDY6U2R2OGJ3BZR75S","download_json":"https://pith.science/pith/AKBDHCY5DDY6U2R2OGJ3BZR75S.json","view_paper":"https://pith.science/paper/AKBDHCY5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.14292&json=true","fetch_graph":"https://pith.science/api/pith-number/AKBDHCY5DDY6U2R2OGJ3BZR75S/graph.json","fetch_events":"https://pith.science/api/pith-number/AKBDHCY5DDY6U2R2OGJ3BZR75S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AKBDHCY5DDY6U2R2OGJ3BZR75S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AKBDHCY5DDY6U2R2OGJ3BZR75S/action/storage_attestation","attest_author":"https://pith.science/pith/AKBDHCY5DDY6U2R2OGJ3BZR75S/action/author_attestation","sign_citation":"https://pith.science/pith/AKBDHCY5DDY6U2R2OGJ3BZR75S/action/citation_signature","submit_replication":"https://pith.science/pith/AKBDHCY5DDY6U2R2OGJ3BZR75S/action/replication_record"}},"created_at":"2026-07-05T09:11:23.343151+00:00","updated_at":"2026-07-05T09:11:23.343151+00:00"}