{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:HHVYB4GXUICX4CCWX5SQ5N7W7B","short_pith_number":"pith:HHVYB4GX","canonical_record":{"source":{"id":"2601.06487","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-01-10T08:43:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d6aa2bb227654e1a0e44975d81acb81947f0f679ce7da21e697bed83366263d0","abstract_canon_sha256":"765674fc992fd60405e509a627b7aaf75946366da684a2351f52c19961124f86"},"schema_version":"1.0"},"canonical_sha256":"39eb80f0d7a2057e0856bf650eb7f6f84e86cbcb1c0040837582ac4c20107ae4","source":{"kind":"arxiv","id":"2601.06487","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.06487","created_at":"2026-07-23T01:24:20Z"},{"alias_kind":"arxiv_version","alias_value":"2601.06487v3","created_at":"2026-07-23T01:24:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.06487","created_at":"2026-07-23T01:24:20Z"},{"alias_kind":"pith_short_12","alias_value":"HHVYB4GXUICX","created_at":"2026-07-23T01:24:20Z"},{"alias_kind":"pith_short_16","alias_value":"HHVYB4GXUICX4CCW","created_at":"2026-07-23T01:24:20Z"},{"alias_kind":"pith_short_8","alias_value":"HHVYB4GX","created_at":"2026-07-23T01:24:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:HHVYB4GXUICX4CCWX5SQ5N7W7B","target":"record","payload":{"canonical_record":{"source":{"id":"2601.06487","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-01-10T08:43:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d6aa2bb227654e1a0e44975d81acb81947f0f679ce7da21e697bed83366263d0","abstract_canon_sha256":"765674fc992fd60405e509a627b7aaf75946366da684a2351f52c19961124f86"},"schema_version":"1.0"},"canonical_sha256":"39eb80f0d7a2057e0856bf650eb7f6f84e86cbcb1c0040837582ac4c20107ae4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-23T01:24:20.043184Z","signature_b64":"i/iZPLtfQPHsVcbiRO7tSUy0vBqMSj/ccVcQQFdDvHTjTMCKbd/d1xhG8XF4KLLzvEm0EcNmzWG1P12H4iy6AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39eb80f0d7a2057e0856bf650eb7f6f84e86cbcb1c0040837582ac4c20107ae4","last_reissued_at":"2026-07-23T01:24:20.042274Z","signature_status":"signed_v1","first_computed_at":"2026-07-23T01:24:20.042274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2601.06487","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-23T01:24:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dpaVHdI+l1X7UopT5zLALb33AvQiR9H1ky1ErTt0TzkyJmOj3+D3wbyp5CAIVuXZqh8LiWRxvGquAP+xBfLJBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T11:58:37.289662Z"},"content_sha256":"ed5f471d2148b9136d9973ae6de7adb707c37ea466beb9f6c993c93dc8d8d931","schema_version":"1.0","event_id":"sha256:ed5f471d2148b9136d9973ae6de7adb707c37ea466beb9f6c993c93dc8d8d931"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:HHVYB4GXUICX4CCWX5SQ5N7W7B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ailin Ren, Boli Chen, Fanrui Zhang, Haonan Zhang, Jiawei Liu, Jingren Zhou, Ning Guo, Pengjun Xie, Pengyong Wang, Qiang Zhang, Qiuchen Wang, Rongxiang Zhu, Ruixue Ding, Shihang Wang, Xin Li, Yinfeng Huang, Zheng-Jun Zha","submitted_at":"2026-01-10T08:43:07Z","abstract_excerpt":"Reinforcement learning has substantially improved the performance of LLM agents on tasks with verifiable outcomes, but it still struggles on open-ended agent tasks with vast solution spaces (e.g., complex travel planning). Due to the absence of objective ground-truth for these tasks, current RL algorithms largely rely on reward models that assign scalar scores to individual responses. We contend that such pointwise scoring suffers from an inherent discrimination collapse: the reward model struggles to distinguish subtle advantages among different trajectories, resulting in scores within a grou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.06487","kind":"arxiv","version":3},"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/2601.06487/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":"2026-07-23T01:24:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E0mtiXYsWxNoXOr0xb/6Xmyjvg9y2+4Qdi6p9lyXaNbTLYwc/tfuHB55WM9EE5q/fZ3ygJQGb0TVzCc5Xzn2DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T11:58:37.290580Z"},"content_sha256":"d796214405bd5ec706cef3b1dd8e1f26d559a241fd2bf032eba14867e138c3af","schema_version":"1.0","event_id":"sha256:d796214405bd5ec706cef3b1dd8e1f26d559a241fd2bf032eba14867e138c3af"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HHVYB4GXUICX4CCWX5SQ5N7W7B/bundle.json","state_url":"https://pith.science/pith/HHVYB4GXUICX4CCWX5SQ5N7W7B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HHVYB4GXUICX4CCWX5SQ5N7W7B/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":"2026-08-18T11:58:37Z","links":{"resolver":"https://pith.science/pith/HHVYB4GXUICX4CCWX5SQ5N7W7B","bundle":"https://pith.science/pith/HHVYB4GXUICX4CCWX5SQ5N7W7B/bundle.json","state":"https://pith.science/pith/HHVYB4GXUICX4CCWX5SQ5N7W7B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HHVYB4GXUICX4CCWX5SQ5N7W7B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HHVYB4GXUICX4CCWX5SQ5N7W7B","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":"765674fc992fd60405e509a627b7aaf75946366da684a2351f52c19961124f86","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-01-10T08:43:07Z","title_canon_sha256":"d6aa2bb227654e1a0e44975d81acb81947f0f679ce7da21e697bed83366263d0"},"schema_version":"1.0","source":{"id":"2601.06487","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.06487","created_at":"2026-07-23T01:24:20Z"},{"alias_kind":"arxiv_version","alias_value":"2601.06487v3","created_at":"2026-07-23T01:24:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.06487","created_at":"2026-07-23T01:24:20Z"},{"alias_kind":"pith_short_12","alias_value":"HHVYB4GXUICX","created_at":"2026-07-23T01:24:20Z"},{"alias_kind":"pith_short_16","alias_value":"HHVYB4GXUICX4CCW","created_at":"2026-07-23T01:24:20Z"},{"alias_kind":"pith_short_8","alias_value":"HHVYB4GX","created_at":"2026-07-23T01:24:20Z"}],"graph_snapshots":[{"event_id":"sha256:d796214405bd5ec706cef3b1dd8e1f26d559a241fd2bf032eba14867e138c3af","target":"graph","created_at":"2026-07-23T01:24:20Z","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/2601.06487/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning has substantially improved the performance of LLM agents on tasks with verifiable outcomes, but it still struggles on open-ended agent tasks with vast solution spaces (e.g., complex travel planning). Due to the absence of objective ground-truth for these tasks, current RL algorithms largely rely on reward models that assign scalar scores to individual responses. We contend that such pointwise scoring suffers from an inherent discrimination collapse: the reward model struggles to distinguish subtle advantages among different trajectories, resulting in scores within a grou","authors_text":"Ailin Ren, Boli Chen, Fanrui Zhang, Haonan Zhang, Jiawei Liu, Jingren Zhou, Ning Guo, Pengjun Xie, Pengyong Wang, Qiang Zhang, Qiuchen Wang, Rongxiang Zhu, Ruixue Ding, Shihang Wang, Xin Li, Yinfeng Huang, Zheng-Jun Zha","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-01-10T08:43:07Z","title":"ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.06487","kind":"arxiv","version":3},"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:ed5f471d2148b9136d9973ae6de7adb707c37ea466beb9f6c993c93dc8d8d931","target":"record","created_at":"2026-07-23T01:24:20Z","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":"765674fc992fd60405e509a627b7aaf75946366da684a2351f52c19961124f86","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-01-10T08:43:07Z","title_canon_sha256":"d6aa2bb227654e1a0e44975d81acb81947f0f679ce7da21e697bed83366263d0"},"schema_version":"1.0","source":{"id":"2601.06487","kind":"arxiv","version":3}},"canonical_sha256":"39eb80f0d7a2057e0856bf650eb7f6f84e86cbcb1c0040837582ac4c20107ae4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"39eb80f0d7a2057e0856bf650eb7f6f84e86cbcb1c0040837582ac4c20107ae4","first_computed_at":"2026-07-23T01:24:20.042274Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-23T01:24:20.042274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i/iZPLtfQPHsVcbiRO7tSUy0vBqMSj/ccVcQQFdDvHTjTMCKbd/d1xhG8XF4KLLzvEm0EcNmzWG1P12H4iy6AA==","signature_status":"signed_v1","signed_at":"2026-07-23T01:24:20.043184Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.06487","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed5f471d2148b9136d9973ae6de7adb707c37ea466beb9f6c993c93dc8d8d931","sha256:d796214405bd5ec706cef3b1dd8e1f26d559a241fd2bf032eba14867e138c3af"],"state_sha256":"8f0d750226a52c52a9476604daf8d766fa61c428b1ca2576e9712fea473b8bb1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ng5Cd2V18d8m0zwBfeHiib13TnolHxztDq2krxkqekJVnFjjgEzIcoiJA9wZPCr/0FpBAUnIijCO7uN0ZDqoAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T11:58:37.298011Z","bundle_sha256":"ab3d8f25de147f1b58014ddc3a83aa93e170059f068d15e672c2e3e88ed267f1"}}