{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GBZ2HTNYI2EX54F5ACI6IDYD2U","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":"cd0bb9b3c5c22d8199f23ae2c042ceba523d336a7a9134cc5759c4f438f04ab1","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-31T22:57:16Z","title_canon_sha256":"2132cc6d91d24641fc038da029ba44183bb4cc724ec287f91e13851f5f9f0a85"},"schema_version":"1.0","source":{"id":"2608.00335","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.00335","created_at":"2026-08-04T00:35:07Z"},{"alias_kind":"arxiv_version","alias_value":"2608.00335v1","created_at":"2026-08-04T00:35:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00335","created_at":"2026-08-04T00:35:07Z"},{"alias_kind":"pith_short_12","alias_value":"GBZ2HTNYI2EX","created_at":"2026-08-04T00:35:07Z"},{"alias_kind":"pith_short_16","alias_value":"GBZ2HTNYI2EX54F5","created_at":"2026-08-04T00:35:07Z"},{"alias_kind":"pith_short_8","alias_value":"GBZ2HTNY","created_at":"2026-08-04T00:35:07Z"}],"graph_snapshots":[{"event_id":"sha256:c3bd0a28654e1a864070de51d0e3d1e1a2fcd25f81a96423f50d3b1b683649c7","target":"graph","created_at":"2026-08-04T00:35:07Z","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/2608.00335/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Compact web agents can reduce deployment cost, but training them poses challenges in both data collection and post-SFT reinforcement learning (RL). Successful trajectories are expensive to collect and often contain inefficient detours. After supervised fine-tuning (SFT), full trajectory corpora are dominated by routine states; moreover, when group-relative RL is applied to web actions, inadequately designed action-level rewards can yield weak or misleading relative updates, while groups rejected as unsuitable for such updates receive no fallback learning signal. We present RMSWeb, a three-part","authors_text":"Ao Sun, Chengbo Liu, Guichun Hua, Haojun Huang, Lifang Zhou, Pei Tan, Ruijie Yan, Sining Wei, Yingying He, Yining Chen, Yutao Xie","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-31T22:57:16Z","title":"RMSWeb: Reflection, Failure-Mode Mining, and Salvage-DS for Web Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00335","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":"sha256:110d1320564bacda46649aa4c7d00d225ae7661f4e439123155fb4e9de39cd87","target":"record","created_at":"2026-08-04T00:35:07Z","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":"cd0bb9b3c5c22d8199f23ae2c042ceba523d336a7a9134cc5759c4f438f04ab1","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-31T22:57:16Z","title_canon_sha256":"2132cc6d91d24641fc038da029ba44183bb4cc724ec287f91e13851f5f9f0a85"},"schema_version":"1.0","source":{"id":"2608.00335","kind":"arxiv","version":1}},"canonical_sha256":"3073a3cdb846897ef0bd0091e40f03d529ef574c6a958009dc5993dc9d399972","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3073a3cdb846897ef0bd0091e40f03d529ef574c6a958009dc5993dc9d399972","first_computed_at":"2026-08-04T00:35:07.191008Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T00:35:07.191008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pinJ/GZgE5lQScJyGvw+FojTFoJfTXeVKE9K6j5aKRIy8Vz5784p8XszkqDG5lqe1d9h0EvKRFmzRgGKc5O2Bw==","signature_status":"signed_v1","signed_at":"2026-08-04T00:35:07.192430Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.00335","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:110d1320564bacda46649aa4c7d00d225ae7661f4e439123155fb4e9de39cd87","sha256:c3bd0a28654e1a864070de51d0e3d1e1a2fcd25f81a96423f50d3b1b683649c7"],"state_sha256":"b756d935eb4c149e76c1d033552a4951a38b815979af5a98af6efdd18c14edc6"}