{"_canonicalization":{"envelope_id":"axm_ + sha256(envelope minus {signature, axiom_id, anchors})","envelope_signature":"ed25519(envelope minus {signature, axiom_id})","json":"sort_keys=True, separators=(',',':'), ensure_ascii=False, allow_nan=False, utf-8","leaf_hash":"sha256(0x00 || canonical_json(envelope_full))","seal_signature":"ed25519(seal minus {signature, sig_algorithm})"},"axiom_id":"axm_b3c55f8204359f2fb1bac78ec6cebca3f4b03529f838d824e4d35f1e091bbdcc","bitcoin_anchor":{"bitcoin_attestations":[],"calendar_attestations":[],"ots_url":"","stamped_at":"","status":"pending_next_stamp"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_b3c55f8204359f2fb1bac78ec6cebca3f4b03529f838d824e4d35f1e091bbdcc","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"54abcdf7eef996ef2e7f3565e1e93f9f77cbc93100c167540130863b4ce948cb","published":"Mon, 08 Jun 2026 00:00:00 -0400","receipt_hash":"54abcdf7eef996ef2e7f3565e1e93f9f77cbc93100c167540130863b4ce948cb","schema":"spider.news.vendor_press.v1","spider":"vendor_press","spider_record":{"axiom_subtype":"news.vendor_press.v1","category":"news","decision_hint":"POSITIVE","envelope_target":"AX.OBS","fingerprint":"54abcdf7eef996ef2e7f3565e1e93f9f77cbc93100c167540130863b4ce948cb","observed_at":"2026-06-08T04:44:02.392073Z","parent_run_hash":"4b9e67a023632e16a32d228bb97fee209911f388e0a8dbf20b5a4ec02729c20f","published":"Mon, 08 Jun 2026 00:00:00 -0400","runtime_version":"0.1.0","schema":"spider.news.vendor_press.v1","source_status":200,"source_url":"https://export.arxiv.org/rss/cs.AI","spider":"vendor_press","summary_excerpt":"arXiv:2606.07027v1 Announce Type: new \nAbstract: Reinforcement Learning (RL) has become a promising approach for improving GUI Agents in long-horizon, stochastic digital environments, but trajectory-level success feedback is too sparse to provide reliable credit assignment for intermediate exploration steps. To mitigate this issue, recent studies introduce Process Reward Models (PRMs), which provide finer-grained training feedback through global milestone verification or local step-level evaluation. However, these methods still suffer from two level-specific limitations: global milestone decomposition is subjective and singular, making it difficult to accommodate the multiple valid execution paths in real GUI tasks, while fixed local judging windows may miss long-range key evidence or dilute the decision signal with irrelevant frames. Inspired by stain-tracing mechanisms in network flow analysis, we propose StainFlow, an entity-stain-flow process reward model for GUI Agents. To reduce ","title":"StainFlow: Entity-Stain Tracking and Evidence Linking for Process Rewards in GUI Agents","url":"https://arxiv.org/abs/2606.07027","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.07027v1 Announce Type: new \nAbstract: Reinforcement Learning (RL) has become a promising approach for improving GUI Agents in long-horizon, stochastic digital environments, but trajectory-level success feedback is too sparse to provide reliable credit assignment for intermediate exploration steps. To mitigate this issue, recent studies introduce Process Reward Models (PRMs), which provide finer-grained training feedback through global milestone verification or local step-level evaluation. However, these methods still suffer from two level-specific limitations: global milestone decomposition is subjective and singular, making it difficult to accommodate the multiple valid execution paths in real GUI tasks, while fixed local judging windows may miss long-range key evidence or dilute the decision signal with irrelevant frames. Inspired by stain-tracing mechanisms in network flow analysis, we propose StainFlow, an entity-stain-flow process reward model for GUI Agents. To reduce ","title":"StainFlow: Entity-Stain Tracking and Evidence Linking for Process Rewards in GUI Agents","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-08T04:44:02Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.07027"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:00d1f7458d53bec9e049fd2acd1f8e9ce8d44bd21e59342bd8938d17f531eb44811d78920ccc36e4a8d4f69d4484df9dfb0739cbe31d5e942da5da08e7f77406","signer":"crovia.substrate","subject":{"observed_at":"2026-06-08T04:44:02Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.07027"},"tsa":{"authority":"crovia.substrate.bootstrap","rfc3161_token":"{\"kind\":\"crovia.bootstrap.tsa\",\"source_jsonl\":\"/opt/crovia/spider/data/news/vendor_press_v1.jsonl\",\"source_seal_merkle_root\":\"spider_vendor_press_v1\",\"upgrade_path\":\"Sessione H \\u2014 OpenTimestamps weekly anchor\"}"},"zk_mode":"clear","zk_proof":null},"ledger":{"leaf_hash":"2902365e0513d47113c064acc8b36cf3b58181f88873259ff855fa7b79fb427e","leaf_index":223659,"ledger_path":"/opt/crovia/substrate/axiom_ledger.jsonl"},"merkle_proof":{"hash_alg":"sha256","leaf_prefix":"0x00","node_prefix":"0x01","odd_leaf_rule":"duplicate_last","path":[{"sibling":"e4096141e4d5a0d50de2a0267ae31328a642ccddb7099634fd1e20cd98afb73a","side":"left"},{"sibling":"d29c789b53148bae59cb737065699fdbfd52afb4e8466e81946a4903c35998c5","side":"left"},{"sibling":"5e93139aa977dc2aa12db4661d747c725073342e552e34416a70c1df8c55c5a6","side":"right"},{"sibling":"1ecd41caa77997c8396799da3fb1e0620a4fab5b78c304cd21aad8f453d49708","side":"left"},{"sibling":"1152166bb1c25fe15c7957929b948ea262e5d1c166f87cce50a34254b61f618c","side":"right"},{"sibling":"05827a4a13c768e2db265e72fad0f6fb7a7fbb7d073c0c14e6439b2d7aa27a42","side":"left"},{"sibling":"60fb6338c1398b60f2495d29f49c8dd6efd167badd0ad0f69e5eaf6aa895db59","side":"right"},{"sibling":"f52e49855e10c1db333480ff9b611c4795fd9e2f84430900141c99330582a520","side":"left"},{"sibling":"5f83c2a81d932eed327e06ff2498f8ed85199cdf7d5f3cd3565fb2a9003a8b8f","side":"left"},{"sibling":"06e9be95ebfd6e5cffbe9db8fc8fd32e8c20d38b7d7f0df3dc7dc5e76bb1848c","side":"right"},{"sibling":"5480e1ea31f4744f9bd7c4261771fe51f2cdb01e705cc17320bfc202d935ca12","side":"right"},{"sibling":"24fdc29d461691aedb6fa920758206b5bb43851f477ef7a04c34aaed84b8971b","side":"left"},{"sibling":"036922da4e1e2c46d948f070454bfad299b7406fb00735ea9d8bd1e687f5f445","side":"right"},{"sibling":"533d82482604463aa4a281b9d8b85917b383b7c5f924b2b494039524c55e8797","side":"left"},{"sibling":"b2590791b920ca2a4ed39de126d2c0b1a10d9e7e62f572f12425f214e767b6e1","side":"left"},{"sibling":"87c6b850dfec08ac35a693d9db3a3315250a68adb1cfab9b1015f212b63b15bd","side":"right"},{"sibling":"c300cf0154c136afc09b1702a0be98f4ba5b6dc5cf57e8cc714ec1eaf4196eff","side":"left"},{"sibling":"d841ad93efda0869e5eb97678f348f03f5caab4353e05ff4bf18f47fb945b822","side":"left"}]},"schema":"crovia.axiom_proof.v1","seal":{"first_collector_run_id":"","first_receipt_hash":"","jsonl_path":"/opt/crovia/substrate/axiom_ledger.jsonl","key_id":"430895f101d38164","last_collector_run_id":"","last_receipt_hash":"","leaf_count":224761,"merkle_root":"e9f7b49b652e869ab97ffba9c5a31356b2d0e3dc5d00bb28944adf737c46b1e7","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260609T103805Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-09T14:15:34Z","sig_algorithm":"ed25519","signature":"8ad8076fb12c8e486ae1d1559a9a7ba8e2ee996a9ad3d8ba7bcdbdbd88ab3a15bcb429707aca6d3e9d8b97e2ba755b3dcc77b1abb6601ccb829842719a6fb30d","signer_version":"1.1.0"},"trust_root":{"key_id":"430895f101d38164","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","signature_algorithm":"ed25519","url":"/registry/canon/TRUST_ROOT.md"},"verifier":{"spec":"/registry/canon/AXIOM_RECEIPT_v1.md","url":"/v/axm_b3c55f8204359f2fb1bac78ec6cebca3f4b03529f838d824e4d35f1e091bbdcc"}}