{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:QEOHCHJEASIKNX5P65I7EEYDK7","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":"530a2d2eccfdbef4e1a7c2056bf834d1602e1c99e5eff4617920ee93cd2db6bc","cross_cats_sorted":["cs.CL","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-06-14T19:45:59Z","title_canon_sha256":"3f4f0d621745c4ace13685cc70df6dadba91bbdce3da05a51f67c5666c34d2c0"},"schema_version":"1.0","source":{"id":"2106.07728","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.07728","created_at":"2026-07-05T02:49:56Z"},{"alias_kind":"arxiv_version","alias_value":"2106.07728v2","created_at":"2026-07-05T02:49:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.07728","created_at":"2026-07-05T02:49:56Z"},{"alias_kind":"pith_short_12","alias_value":"QEOHCHJEASIK","created_at":"2026-07-05T02:49:56Z"},{"alias_kind":"pith_short_16","alias_value":"QEOHCHJEASIKNX5P","created_at":"2026-07-05T02:49:56Z"},{"alias_kind":"pith_short_8","alias_value":"QEOHCHJE","created_at":"2026-07-05T02:49:56Z"}],"graph_snapshots":[{"event_id":"sha256:baa27bb6c61765ac7e967a5408b5d5f3071f2b6137393a218a189255975331be","target":"graph","created_at":"2026-07-05T02:49:56Z","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/2106.07728/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Successful negotiators must learn how to balance optimizing for self-interest and cooperation. Yet current artificial negotiation agents often heavily depend on the quality of the static datasets they were trained on, limiting their capacity to fashion an adaptive response balancing self-interest and cooperation. For this reason, we find that these agents can achieve either high utility or cooperation, but not both. To address this, we introduce a targeted data acquisition framework where we guide the exploration of a reinforcement learning agent using annotations from an expert oracle. The gu","authors_text":"Dorsa Sadigh, Mariano-Florentino Cuellar, Minae Kwon, Siddharth Karamcheti","cross_cats":["cs.CL","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-06-14T19:45:59Z","title":"Targeted Data Acquisition for Evolving Negotiation Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.07728","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":"sha256:58e7636b03ad0d0d0858a8cea337cd88b5fc18a0064528501e92ed582470af82","target":"record","created_at":"2026-07-05T02:49:56Z","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":"530a2d2eccfdbef4e1a7c2056bf834d1602e1c99e5eff4617920ee93cd2db6bc","cross_cats_sorted":["cs.CL","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2021-06-14T19:45:59Z","title_canon_sha256":"3f4f0d621745c4ace13685cc70df6dadba91bbdce3da05a51f67c5666c34d2c0"},"schema_version":"1.0","source":{"id":"2106.07728","kind":"arxiv","version":2}},"canonical_sha256":"811c711d240490a6dfaff751f2130357d27031e03ad76379561c442fd7d50e38","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"811c711d240490a6dfaff751f2130357d27031e03ad76379561c442fd7d50e38","first_computed_at":"2026-07-05T02:49:56.448921Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:49:56.448921Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r/KpxclEgU5uGJzsO8aZY6SFFT/q0cVU6s/N12HSgKSQynZLQkxfd7p2f5V57ZjPsz+u8o+9L7gqOCSLNpW4Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:49:56.449486Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.07728","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:58e7636b03ad0d0d0858a8cea337cd88b5fc18a0064528501e92ed582470af82","sha256:baa27bb6c61765ac7e967a5408b5d5f3071f2b6137393a218a189255975331be"],"state_sha256":"6d9f49af75a9e3b6cdb9115151fbbd6dd890543a75155a08da1a052f857f0904"}