{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ZLSPF2SXOEFZ5FFICSXKCIBTZX","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":"6eab0d87eaacf8ba8026c7a2d82b9a1abec45e92628744cf8781fde9abbbdea7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MA","submitted_at":"2021-11-23T07:22:05Z","title_canon_sha256":"1969109b9e545e757ea2888846c66fb3dee1ef1cb6c1ffce3965056417aba8cf"},"schema_version":"1.0","source":{"id":"2111.11692","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.11692","created_at":"2026-07-05T03:34:11Z"},{"alias_kind":"arxiv_version","alias_value":"2111.11692v1","created_at":"2026-07-05T03:34:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.11692","created_at":"2026-07-05T03:34:11Z"},{"alias_kind":"pith_short_12","alias_value":"ZLSPF2SXOEFZ","created_at":"2026-07-05T03:34:11Z"},{"alias_kind":"pith_short_16","alias_value":"ZLSPF2SXOEFZ5FFI","created_at":"2026-07-05T03:34:11Z"},{"alias_kind":"pith_short_8","alias_value":"ZLSPF2SX","created_at":"2026-07-05T03:34:11Z"}],"graph_snapshots":[{"event_id":"sha256:3d0bb449ae66c2f2cf40f70190900e0a12ff813345ff50268ee878c1c28fa6dd","target":"graph","created_at":"2026-07-05T03:34:11Z","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/2111.11692/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Individual rationality, which involves maximizing expected individual returns, does not always lead to high-utility individual or group outcomes in multi-agent problems. For instance, in multi-agent social dilemmas, Reinforcement Learning (RL) agents trained to maximize individual rewards converge to a low-utility mutually harmful equilibrium. In contrast, humans evolve useful strategies in such social dilemmas. Inspired by ideas from human psychology that attribute this behavior to the status-quo bias, we present a status-quo loss (SQLoss) and the corresponding policy gradient algorithm that ","authors_text":"Abhishek Sinha, Balaji Krishnamurthy, Jayakumar Subramanian, Mausoom Sarkar, Nikaash Puri, Pinkesh Badjatiya, Siddharth Singh","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MA","submitted_at":"2021-11-23T07:22:05Z","title":"Status-quo policy gradient in Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.11692","kind":"arxiv","version":1},"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":"sha256:5850e6b4c0678a30cac9350671fc535a0d66da9403ceda400d15868b807271ba","target":"record","created_at":"2026-07-05T03:34:11Z","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":"6eab0d87eaacf8ba8026c7a2d82b9a1abec45e92628744cf8781fde9abbbdea7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MA","submitted_at":"2021-11-23T07:22:05Z","title_canon_sha256":"1969109b9e545e757ea2888846c66fb3dee1ef1cb6c1ffce3965056417aba8cf"},"schema_version":"1.0","source":{"id":"2111.11692","kind":"arxiv","version":1}},"canonical_sha256":"cae4f2ea57710b9e94a814aea12033cdf5ee123adad6d084a16ca3a5f200905e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cae4f2ea57710b9e94a814aea12033cdf5ee123adad6d084a16ca3a5f200905e","first_computed_at":"2026-07-05T03:34:11.792756Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:34:11.792756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vRAN49stNJXCbNRJt43jS60OZ+rv4pz1icoPRmAQtKEnnS6bEd28SV/101PYs4KCx09tueDtpCCtsyrFl0VcDw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:34:11.793184Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.11692","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5850e6b4c0678a30cac9350671fc535a0d66da9403ceda400d15868b807271ba","sha256:3d0bb449ae66c2f2cf40f70190900e0a12ff813345ff50268ee878c1c28fa6dd"],"state_sha256":"c6239c1b31e14643d550d599a16005fcbd63e4459d1a76d85f61b8e8c9ebeaca"}