{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:AKBDHCY5DDY6U2R2OGJ3BZR75S","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"df576354bbdf2577f7d323b29933f7c3e46e2d11e0a80fef855d9f377a882df9","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-21T20:48:15Z","title_canon_sha256":"8a5c9a30b1d469bb2833c76f272ed25f3cdec87299430776983df4f9a87d84f0"},"schema_version":"1.0","source":{"id":"2312.14292","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.14292","created_at":"2026-07-05T09:11:23Z"},{"alias_kind":"arxiv_version","alias_value":"2312.14292v2","created_at":"2026-07-05T09:11:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.14292","created_at":"2026-07-05T09:11:23Z"},{"alias_kind":"pith_short_12","alias_value":"AKBDHCY5DDY6","created_at":"2026-07-05T09:11:23Z"},{"alias_kind":"pith_short_16","alias_value":"AKBDHCY5DDY6U2R2","created_at":"2026-07-05T09:11:23Z"},{"alias_kind":"pith_short_8","alias_value":"AKBDHCY5","created_at":"2026-07-05T09:11:23Z"}],"graph_snapshots":[{"event_id":"sha256:68082f7711a69164c1a0a7b81aacd118a5a7aaafe16a26a962f48947821632cf","target":"graph","created_at":"2026-07-05T09:11:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2312.14292/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Anil Murthy, Mudit Verma, Siddhant Bhambri, Subbarao Kambhampati, Upasana Biswas","cross_cats":["cs.LG","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-21T20:48:15Z","title":"Incorporating Human Flexibility through Reward Preferences in Human-AI Teaming"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.14292","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:275a19923a45fbf9f362d4c7df2ad2de9db1b14dc5ac9300a6b7091718b5436b","target":"record","created_at":"2026-07-05T09:11:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"df576354bbdf2577f7d323b29933f7c3e46e2d11e0a80fef855d9f377a882df9","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-21T20:48:15Z","title_canon_sha256":"8a5c9a30b1d469bb2833c76f272ed25f3cdec87299430776983df4f9a87d84f0"},"schema_version":"1.0","source":{"id":"2312.14292","kind":"arxiv","version":2}},"canonical_sha256":"0282338b1d18f1ea6a3a7193b0e63fecac4acfdb8d00737743f890733d037d15","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0282338b1d18f1ea6a3a7193b0e63fecac4acfdb8d00737743f890733d037d15","first_computed_at":"2026-07-05T09:11:23.343091Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:11:23.343091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5W2C/+1vLis1/eIHQN707Ph8UOj5MnBBl1bImA7I91PrYj6fDfa+5Eue9AGX1fM+HhPNE1m/80WQQETXRQjcAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:11:23.343543Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.14292","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:275a19923a45fbf9f362d4c7df2ad2de9db1b14dc5ac9300a6b7091718b5436b","sha256:68082f7711a69164c1a0a7b81aacd118a5a7aaafe16a26a962f48947821632cf"],"state_sha256":"b1e294093eed1dd6b8f2810cff8f3abeb3a72b4966fb9abf9e4f1b04c2a3c99b"}