{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GBZ2HTNYI2EX54F5ACI6IDYD2U","short_pith_number":"pith:GBZ2HTNY","canonical_record":{"source":{"id":"2608.00335","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-31T22:57:16Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"2132cc6d91d24641fc038da029ba44183bb4cc724ec287f91e13851f5f9f0a85","abstract_canon_sha256":"cd0bb9b3c5c22d8199f23ae2c042ceba523d336a7a9134cc5759c4f438f04ab1"},"schema_version":"1.0"},"canonical_sha256":"3073a3cdb846897ef0bd0091e40f03d529ef574c6a958009dc5993dc9d399972","source":{"kind":"arxiv","id":"2608.00335","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GBZ2HTNYI2EX54F5ACI6IDYD2U","target":"record","payload":{"canonical_record":{"source":{"id":"2608.00335","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-31T22:57:16Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"2132cc6d91d24641fc038da029ba44183bb4cc724ec287f91e13851f5f9f0a85","abstract_canon_sha256":"cd0bb9b3c5c22d8199f23ae2c042ceba523d336a7a9134cc5759c4f438f04ab1"},"schema_version":"1.0"},"canonical_sha256":"3073a3cdb846897ef0bd0091e40f03d529ef574c6a958009dc5993dc9d399972","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T00:35:07.192430Z","signature_b64":"pinJ/GZgE5lQScJyGvw+FojTFoJfTXeVKE9K6j5aKRIy8Vz5784p8XszkqDG5lqe1d9h0EvKRFmzRgGKc5O2Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3073a3cdb846897ef0bd0091e40f03d529ef574c6a958009dc5993dc9d399972","last_reissued_at":"2026-08-04T00:35:07.191008Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T00:35:07.191008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.00335","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-04T00:35:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lQKdcrcUN6EZnwyp/4BGsk4WKtpDqrk8mFZWg257nV+XNgFNeCkLIoepniK1ulx7Lbbm4OWPz6cwMzoT4iFaBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T08:48:37.564275Z"},"content_sha256":"110d1320564bacda46649aa4c7d00d225ae7661f4e439123155fb4e9de39cd87","schema_version":"1.0","event_id":"sha256:110d1320564bacda46649aa4c7d00d225ae7661f4e439123155fb4e9de39cd87"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GBZ2HTNYI2EX54F5ACI6IDYD2U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RMSWeb: Reflection, Failure-Mode Mining, and Salvage-DS for Web Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Ao Sun, Chengbo Liu, Guichun Hua, Haojun Huang, Lifang Zhou, Pei Tan, Ruijie Yan, Sining Wei, Yingying He, Yining Chen, Yutao Xie","submitted_at":"2026-07-31T22:57:16Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00335","kind":"arxiv","version":1},"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/2608.00335/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":"2026-08-04T00:35:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xSHaHcPncxRY4e05IY04jsGkP+vzKw51l9YIRkSpYzsd7LGrR0QasfX5UudRTBt6eD8ushb+xH57BQrMBDAuDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T08:48:37.564792Z"},"content_sha256":"c3bd0a28654e1a864070de51d0e3d1e1a2fcd25f81a96423f50d3b1b683649c7","schema_version":"1.0","event_id":"sha256:c3bd0a28654e1a864070de51d0e3d1e1a2fcd25f81a96423f50d3b1b683649c7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GBZ2HTNYI2EX54F5ACI6IDYD2U/bundle.json","state_url":"https://pith.science/pith/GBZ2HTNYI2EX54F5ACI6IDYD2U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GBZ2HTNYI2EX54F5ACI6IDYD2U/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":"2026-08-04T08:48:37Z","links":{"resolver":"https://pith.science/pith/GBZ2HTNYI2EX54F5ACI6IDYD2U","bundle":"https://pith.science/pith/GBZ2HTNYI2EX54F5ACI6IDYD2U/bundle.json","state":"https://pith.science/pith/GBZ2HTNYI2EX54F5ACI6IDYD2U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GBZ2HTNYI2EX54F5ACI6IDYD2U/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e0G9sVtrtiDvfkdl0hoTjClE65oAsztyEYMRSsiVjjaBorh2vpo3uM1LaFy6kIdtDHaZp+Jh8JX1U54vy2D5Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T08:48:37.569726Z","bundle_sha256":"e137b96ee141e28c44f609b651b434aed6b2d66f35e6ad8bf5a17f47da811ebb"}}