{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CAOA6WQ43ESJRUDJDAHEZKSNE7","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":"465af5ee5b122d9fef82878eb82202f620d07efde7e1521c3d6bbef77be3bfd6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-24T13:30:47Z","title_canon_sha256":"12486388e370f4361f66fa5e34f57bd3db82da75de7509cdcebd447de8508fbf"},"schema_version":"1.0","source":{"id":"2503.18665","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.18665","created_at":"2026-07-05T11:25:43Z"},{"alias_kind":"arxiv_version","alias_value":"2503.18665v2","created_at":"2026-07-05T11:25:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.18665","created_at":"2026-07-05T11:25:43Z"},{"alias_kind":"pith_short_12","alias_value":"CAOA6WQ43ESJ","created_at":"2026-07-05T11:25:43Z"},{"alias_kind":"pith_short_16","alias_value":"CAOA6WQ43ESJRUDJ","created_at":"2026-07-05T11:25:43Z"},{"alias_kind":"pith_short_8","alias_value":"CAOA6WQ4","created_at":"2026-07-05T11:25:43Z"}],"graph_snapshots":[{"event_id":"sha256:82a2f02601def4822b789ecda39057bdb7018065c4afc771f2e30f20cfeac0e1","target":"graph","created_at":"2026-07-05T11:25:43Z","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/2503.18665/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The development of Generalist Virtual Agents (GVAs) has shown significant promise in autonomous task execution. However, current training paradigms face critical limitations, including reliance on outcome supervision and labor-intensive human annotations. To address these challenges, we propose Similar, a Step-Wise Multi-Dimensional Generalist Reward Model, which offers fine-grained signals for agent training and can choose better action for inference-time scaling. Specifically, we begin by systematically defining five dimensions for evaluating agent actions. Building on this framework, we des","authors_text":"Bingchen Miao, Juncheng Li, Minghe Gao, Qifan Yu, Siliang Tang, Tat-Seng Chua, Wendong Bu, Wenqiao Zhang, Yang Wu, Yunfei Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-24T13:30:47Z","title":"Boosting Virtual Agent Learning and Reasoning: A Step-Wise, Multi-Dimensional, and Generalist Reward Model with Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.18665","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":"sha256:713db40c780b56eb316c73456a195d2e27c7c2d49b6c7ca20b6dd1574deab6e3","target":"record","created_at":"2026-07-05T11:25:43Z","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":"465af5ee5b122d9fef82878eb82202f620d07efde7e1521c3d6bbef77be3bfd6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-24T13:30:47Z","title_canon_sha256":"12486388e370f4361f66fa5e34f57bd3db82da75de7509cdcebd447de8508fbf"},"schema_version":"1.0","source":{"id":"2503.18665","kind":"arxiv","version":2}},"canonical_sha256":"101c0f5a1cd92498d069180e4caa4d27da5613e297d9dfa4f1bd19e1ff85c491","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"101c0f5a1cd92498d069180e4caa4d27da5613e297d9dfa4f1bd19e1ff85c491","first_computed_at":"2026-07-05T11:25:43.071095Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:43.071095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ml5tzHdkQbu0gu2S+CV6bMb/sSnao9YRCILCotfUGzoHcgMR1tgv57ZvmRngWY0Xo+Z6LgMelZD0pk7llY6zCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:43.071581Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.18665","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:713db40c780b56eb316c73456a195d2e27c7c2d49b6c7ca20b6dd1574deab6e3","sha256:82a2f02601def4822b789ecda39057bdb7018065c4afc771f2e30f20cfeac0e1"],"state_sha256":"fd3c67d42ccfb67d36f1b7323bf7ca3f26ad2e6d4fc356722da236b01621be28"}