{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5Z3PAXMEBFVPTLCY6BEZSEKLSN","short_pith_number":"pith:5Z3PAXME","canonical_record":{"source":{"id":"2411.00119","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2024-10-31T18:17:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d5b9d2ca62ac370fdd98bf488c328e949ccae0d3d44efe1b34d04b3b2777dfb0","abstract_canon_sha256":"1b3b962940be3e1cd1f1c478f159a3333a12bb1ea88179aa1429aaa562d5bf17"},"schema_version":"1.0"},"canonical_sha256":"ee76f05d84096af9ac58f04999114b9354101646e3f81e762c419d661269cbd2","source":{"kind":"arxiv","id":"2411.00119","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.00119","created_at":"2026-07-05T11:28:12Z"},{"alias_kind":"arxiv_version","alias_value":"2411.00119v4","created_at":"2026-07-05T11:28:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00119","created_at":"2026-07-05T11:28:12Z"},{"alias_kind":"pith_short_12","alias_value":"5Z3PAXMEBFVP","created_at":"2026-07-05T11:28:12Z"},{"alias_kind":"pith_short_16","alias_value":"5Z3PAXMEBFVPTLCY","created_at":"2026-07-05T11:28:12Z"},{"alias_kind":"pith_short_8","alias_value":"5Z3PAXME","created_at":"2026-07-05T11:28:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5Z3PAXMEBFVPTLCY6BEZSEKLSN","target":"record","payload":{"canonical_record":{"source":{"id":"2411.00119","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2024-10-31T18:17:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d5b9d2ca62ac370fdd98bf488c328e949ccae0d3d44efe1b34d04b3b2777dfb0","abstract_canon_sha256":"1b3b962940be3e1cd1f1c478f159a3333a12bb1ea88179aa1429aaa562d5bf17"},"schema_version":"1.0"},"canonical_sha256":"ee76f05d84096af9ac58f04999114b9354101646e3f81e762c419d661269cbd2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:12.123828Z","signature_b64":"hLkr9w9DEn2xAhPf7jK9OavyRlyJrUfLIR5TC3e+CJB5W8IxT7qpZJuKaOZCVQX+YRa9N6o2RDM6o0eBt3GGBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee76f05d84096af9ac58f04999114b9354101646e3f81e762c419d661269cbd2","last_reissued_at":"2026-07-05T11:28:12.123297Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:12.123297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.00119","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:28:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HY1qI4pFjfy5cdAVCcMlefYCE++X50wSr3jIpw+7ecEW4qT6M1kBRpeL5r1ONwTyVAtw82t+rVJODpS1+ZjkBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:58:00.420766Z"},"content_sha256":"2b4b9a9f4b84af24d2d6f90a98a338b23ed928e8310314e96baaebf6fd84b96b","schema_version":"1.0","event_id":"sha256:2b4b9a9f4b84af24d2d6f90a98a338b23ed928e8310314e96baaebf6fd84b96b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5Z3PAXMEBFVPTLCY6BEZSEKLSN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Soft Condorcet Optimization for Ranking of General Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.MA","authors_text":"Anna Koop, Doina Precup, Ian Gemp, Kate Larson, Manfred Diaz, Marc Lanctot, Michael Kaisers, Quentin Berthet, Roberto-Rafael Maura-Rivero, Yoram Bachrach","submitted_at":"2024-10-31T18:17:39Z","abstract_excerpt":"Driving progress of AI models and agents requires comparing their performance on standardized benchmarks; for general agents, individual performances must be aggregated across a potentially wide variety of different tasks. In this paper, we describe a novel ranking scheme inspired by social choice frameworks, called Soft Condorcet Optimization (SCO), to compute the optimal ranking of agents: the one that makes the fewest mistakes in predicting the agent comparisons in the evaluation data. This optimal ranking is the maximum likelihood estimate when evaluation data (which we view as votes) are "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00119","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.00119/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:28:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EsHBVn4YybNaKV5COpCVyPUX9Xb045PgbLHA6ZGYCTdMSd+s0ctFHWoR5myht6mSVo1RFfMys/GFJl7Dm2jZDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:58:00.421345Z"},"content_sha256":"0dafdb71566bcaef6fe21251257b7750c489defe8129aabfd95512f358cbd412","schema_version":"1.0","event_id":"sha256:0dafdb71566bcaef6fe21251257b7750c489defe8129aabfd95512f358cbd412"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5Z3PAXMEBFVPTLCY6BEZSEKLSN/bundle.json","state_url":"https://pith.science/pith/5Z3PAXMEBFVPTLCY6BEZSEKLSN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5Z3PAXMEBFVPTLCY6BEZSEKLSN/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T06:58:00Z","links":{"resolver":"https://pith.science/pith/5Z3PAXMEBFVPTLCY6BEZSEKLSN","bundle":"https://pith.science/pith/5Z3PAXMEBFVPTLCY6BEZSEKLSN/bundle.json","state":"https://pith.science/pith/5Z3PAXMEBFVPTLCY6BEZSEKLSN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5Z3PAXMEBFVPTLCY6BEZSEKLSN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5Z3PAXMEBFVPTLCY6BEZSEKLSN","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":"1b3b962940be3e1cd1f1c478f159a3333a12bb1ea88179aa1429aaa562d5bf17","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2024-10-31T18:17:39Z","title_canon_sha256":"d5b9d2ca62ac370fdd98bf488c328e949ccae0d3d44efe1b34d04b3b2777dfb0"},"schema_version":"1.0","source":{"id":"2411.00119","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.00119","created_at":"2026-07-05T11:28:12Z"},{"alias_kind":"arxiv_version","alias_value":"2411.00119v4","created_at":"2026-07-05T11:28:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00119","created_at":"2026-07-05T11:28:12Z"},{"alias_kind":"pith_short_12","alias_value":"5Z3PAXMEBFVP","created_at":"2026-07-05T11:28:12Z"},{"alias_kind":"pith_short_16","alias_value":"5Z3PAXMEBFVPTLCY","created_at":"2026-07-05T11:28:12Z"},{"alias_kind":"pith_short_8","alias_value":"5Z3PAXME","created_at":"2026-07-05T11:28:12Z"}],"graph_snapshots":[{"event_id":"sha256:0dafdb71566bcaef6fe21251257b7750c489defe8129aabfd95512f358cbd412","target":"graph","created_at":"2026-07-05T11:28:12Z","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/2411.00119/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Driving progress of AI models and agents requires comparing their performance on standardized benchmarks; for general agents, individual performances must be aggregated across a potentially wide variety of different tasks. In this paper, we describe a novel ranking scheme inspired by social choice frameworks, called Soft Condorcet Optimization (SCO), to compute the optimal ranking of agents: the one that makes the fewest mistakes in predicting the agent comparisons in the evaluation data. This optimal ranking is the maximum likelihood estimate when evaluation data (which we view as votes) are ","authors_text":"Anna Koop, Doina Precup, Ian Gemp, Kate Larson, Manfred Diaz, Marc Lanctot, Michael Kaisers, Quentin Berthet, Roberto-Rafael Maura-Rivero, Yoram Bachrach","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2024-10-31T18:17:39Z","title":"Soft Condorcet Optimization for Ranking of General Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00119","kind":"arxiv","version":4},"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":"sha256:2b4b9a9f4b84af24d2d6f90a98a338b23ed928e8310314e96baaebf6fd84b96b","target":"record","created_at":"2026-07-05T11:28:12Z","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":"1b3b962940be3e1cd1f1c478f159a3333a12bb1ea88179aa1429aaa562d5bf17","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2024-10-31T18:17:39Z","title_canon_sha256":"d5b9d2ca62ac370fdd98bf488c328e949ccae0d3d44efe1b34d04b3b2777dfb0"},"schema_version":"1.0","source":{"id":"2411.00119","kind":"arxiv","version":4}},"canonical_sha256":"ee76f05d84096af9ac58f04999114b9354101646e3f81e762c419d661269cbd2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ee76f05d84096af9ac58f04999114b9354101646e3f81e762c419d661269cbd2","first_computed_at":"2026-07-05T11:28:12.123297Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:28:12.123297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hLkr9w9DEn2xAhPf7jK9OavyRlyJrUfLIR5TC3e+CJB5W8IxT7qpZJuKaOZCVQX+YRa9N6o2RDM6o0eBt3GGBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:28:12.123828Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.00119","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b4b9a9f4b84af24d2d6f90a98a338b23ed928e8310314e96baaebf6fd84b96b","sha256:0dafdb71566bcaef6fe21251257b7750c489defe8129aabfd95512f358cbd412"],"state_sha256":"f68f6400604dd100ba890823e22151a32011e207d3b0e7138eca5f9121ef47b3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LFrLFtqcQL7J98s9vAPW0p6h3Chbl/xo9YTk0eXfFE/fLbcCJP3TCT9cCCWAdwPkzq5RiY+oC3oIX6H2U+MoBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T06:58:00.425420Z","bundle_sha256":"a39f495e4fcaf301367c983431771f053c1b7832367a11105f7317c90bed401f"}}