{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6XJMIR7QFCO3HR6R6IJLSJQCLH","short_pith_number":"pith:6XJMIR7Q","canonical_record":{"source":{"id":"2601.09636","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-01-14T17:12:48Z","cross_cats_sorted":["cs.CV","cs.HC","cs.LG"],"title_canon_sha256":"727806031e13f0e4d72d9f79b386a55a2ff732d15caea0223681d8386018b105","abstract_canon_sha256":"a49193ab6edf6abbdf7bfc1b3c120b124c335870cdd3beda373b2110122397fd"},"schema_version":"1.0"},"canonical_sha256":"f5d2c447f0289db3c7d1f212b9260259ef70cca216990a857909fb723443730a","source":{"kind":"arxiv","id":"2601.09636","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.09636","created_at":"2026-05-18T03:09:24Z"},{"alias_kind":"arxiv_version","alias_value":"2601.09636v2","created_at":"2026-05-18T03:09:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.09636","created_at":"2026-05-18T03:09:24Z"},{"alias_kind":"pith_short_12","alias_value":"6XJMIR7QFCO3","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"6XJMIR7QFCO3HR6R","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"6XJMIR7Q","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6XJMIR7QFCO3HR6R6IJLSJQCLH","target":"record","payload":{"canonical_record":{"source":{"id":"2601.09636","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-01-14T17:12:48Z","cross_cats_sorted":["cs.CV","cs.HC","cs.LG"],"title_canon_sha256":"727806031e13f0e4d72d9f79b386a55a2ff732d15caea0223681d8386018b105","abstract_canon_sha256":"a49193ab6edf6abbdf7bfc1b3c120b124c335870cdd3beda373b2110122397fd"},"schema_version":"1.0"},"canonical_sha256":"f5d2c447f0289db3c7d1f212b9260259ef70cca216990a857909fb723443730a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:24.499085Z","signature_b64":"Cj/Sj9tO0HfMz+P8ygQThzNNpyR0NqbrF/D+Iq7vcrEK6H+PUxruhoCmjGip1ssU7q92YLmWLGGIZrsL+RgYBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5d2c447f0289db3c7d1f212b9260259ef70cca216990a857909fb723443730a","last_reissued_at":"2026-05-18T03:09:24.498273Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:24.498273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2601.09636","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8LkhCL0jsden5+S8DArSwhznLb/+fzVHkXhQMJvLTH6VRZ5NFZzwwsdV56l9DDmZTt8tbjignqoAcBfT76NeDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T14:39:43.021448Z"},"content_sha256":"842ffd64e71ae32f163dc3ecc8fb05ae6248ae992ccaf9546ea58279144678a1","schema_version":"1.0","event_id":"sha256:842ffd64e71ae32f163dc3ecc8fb05ae6248ae992ccaf9546ea58279144678a1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6XJMIR7QFCO3HR6R6IJLSJQCLH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PersonalAlign: Hierarchical Implicit Intent Alignment for Personalized GUI Agent with Long-Term User-Centric Records","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Hierarchical memory from long-term records lets GUI agents resolve vague instructions and anticipate routines.","cross_cats":["cs.CV","cs.HC","cs.LG"],"primary_cat":"cs.AI","authors_text":"Gongwei Chen, Liqiang Nie, Rui Shao, Weili Guan, Yibo Lyu","submitted_at":"2026-01-14T17:12:48Z","abstract_excerpt":"While GUI agents have shown strong performance under explicit and completion instructions, real-world deployment requires aligning with users' more complex implicit intents. In this work, we highlight Hierarchical Implicit Intent Alignment for Personalized GUI Agent (PersonalAlign), a new agent task that requires agents to leverage long-term user records as persistent context to resolve omitted preferences in vague instructions and anticipate latent routines by user state for proactive assistance. To facilitate this study, we introduce AndroidIntent, a benchmark designed to evaluate agents' ab"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"HIM-Agent significantly improves both execution and proactive performance by 15.7% and 7.3% on the AndroidIntent benchmark.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the 20k long-term records contain stable, generalizable user preferences and routines that transfer to new vague instructions without overfitting to the 20 users in the benchmark.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"PersonalAlign introduces a hierarchical memory agent that uses long-term user records to resolve vague GUI instructions and provide proactive assistance, improving execution by 15.7% and proactive performance by 7.3% on the new AndroidIntent benchmark.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Hierarchical memory from long-term records lets GUI agents resolve vague instructions and anticipate routines.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"bfeff95e40675015a848a096ab8edb634897c4bfb28916f3c8ac4c2a2bca5da2"},"source":{"id":"2601.09636","kind":"arxiv","version":2},"verdict":{"id":"d044c2cf-fa1f-4681-8c24-c470b471c708","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T14:29:14.352576Z","strongest_claim":"HIM-Agent significantly improves both execution and proactive performance by 15.7% and 7.3% on the AndroidIntent benchmark.","one_line_summary":"PersonalAlign introduces a hierarchical memory agent that uses long-term user records to resolve vague GUI instructions and provide proactive assistance, improving execution by 15.7% and proactive performance by 7.3% on the new AndroidIntent benchmark.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the 20k long-term records contain stable, generalizable user preferences and routines that transfer to new vague instructions without overfitting to the 20 users in the benchmark.","pith_extraction_headline":"Hierarchical memory from long-term records lets GUI agents resolve vague instructions and anticipate routines."},"references":{"count":14,"sample":[{"doi":"","year":2025,"title":"LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training","work_id":"41c2802e-aff9-482f-b506-10955ff0838d","ref_index":1,"cited_arxiv_id":"2509.23661","is_internal_anchor":true},{"doi":"","year":2025,"title":"Score the steps, not just the goal: Vlm-based subgoal evaluation for robotic manipulation","work_id":"ebb97240-cc8c-40cc-8684-46c3b7df07da","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"InProceedings of the IEEE/CVF conference on com- puter vision and pattern recognition, pages 10023– 10031","work_id":"cdfa2461-8017-4be7-b0a6-ad555737130d","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Advances in Neural Information Processing Systems, 37:52040–52094","work_id":"ba5bc0df-5aa8-497c-9121-7b4ac95aa9bb","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent","work_id":"ac66fe72-b869-4874-8a9d-c110b849da0c","ref_index":5,"cited_arxiv_id":"2507.02259","is_internal_anchor":true}],"resolved_work":14,"snapshot_sha256":"427899431cf6e8c5308e1ad4f6bc09c0a5db2c0b063264f2b2a6d2c9593edd37","internal_anchors":2},"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":"d044c2cf-fa1f-4681-8c24-c470b471c708"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lNvW9mGP28ArDWbAwVdPpXAOMw5V04sMdFsDBwV/JFhMo/o5EqH/VVDIXt2LLLzwPs1jkl74LKC+x11vhtt8Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T14:39:43.022581Z"},"content_sha256":"8ed36bea88039c52b8a849678311a0ccd38c085caa8bbc5d1e005c464164071d","schema_version":"1.0","event_id":"sha256:8ed36bea88039c52b8a849678311a0ccd38c085caa8bbc5d1e005c464164071d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6XJMIR7QFCO3HR6R6IJLSJQCLH/bundle.json","state_url":"https://pith.science/pith/6XJMIR7QFCO3HR6R6IJLSJQCLH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6XJMIR7QFCO3HR6R6IJLSJQCLH/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":"2026-05-26T14:39:43Z","links":{"resolver":"https://pith.science/pith/6XJMIR7QFCO3HR6R6IJLSJQCLH","bundle":"https://pith.science/pith/6XJMIR7QFCO3HR6R6IJLSJQCLH/bundle.json","state":"https://pith.science/pith/6XJMIR7QFCO3HR6R6IJLSJQCLH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6XJMIR7QFCO3HR6R6IJLSJQCLH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6XJMIR7QFCO3HR6R6IJLSJQCLH","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":"a49193ab6edf6abbdf7bfc1b3c120b124c335870cdd3beda373b2110122397fd","cross_cats_sorted":["cs.CV","cs.HC","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-01-14T17:12:48Z","title_canon_sha256":"727806031e13f0e4d72d9f79b386a55a2ff732d15caea0223681d8386018b105"},"schema_version":"1.0","source":{"id":"2601.09636","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.09636","created_at":"2026-05-18T03:09:24Z"},{"alias_kind":"arxiv_version","alias_value":"2601.09636v2","created_at":"2026-05-18T03:09:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.09636","created_at":"2026-05-18T03:09:24Z"},{"alias_kind":"pith_short_12","alias_value":"6XJMIR7QFCO3","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"6XJMIR7QFCO3HR6R","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"6XJMIR7Q","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:8ed36bea88039c52b8a849678311a0ccd38c085caa8bbc5d1e005c464164071d","target":"graph","created_at":"2026-05-18T03:09:24Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"HIM-Agent significantly improves both execution and proactive performance by 15.7% and 7.3% on the AndroidIntent benchmark."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the 20k long-term records contain stable, generalizable user preferences and routines that transfer to new vague instructions without overfitting to the 20 users in the benchmark."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"PersonalAlign introduces a hierarchical memory agent that uses long-term user records to resolve vague GUI instructions and provide proactive assistance, improving execution by 15.7% and proactive performance by 7.3% on the new AndroidIntent benchmark."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Hierarchical memory from long-term records lets GUI agents resolve vague instructions and anticipate routines."}],"snapshot_sha256":"bfeff95e40675015a848a096ab8edb634897c4bfb28916f3c8ac4c2a2bca5da2"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"While GUI agents have shown strong performance under explicit and completion instructions, real-world deployment requires aligning with users' more complex implicit intents. In this work, we highlight Hierarchical Implicit Intent Alignment for Personalized GUI Agent (PersonalAlign), a new agent task that requires agents to leverage long-term user records as persistent context to resolve omitted preferences in vague instructions and anticipate latent routines by user state for proactive assistance. To facilitate this study, we introduce AndroidIntent, a benchmark designed to evaluate agents' ab","authors_text":"Gongwei Chen, Liqiang Nie, Rui Shao, Weili Guan, Yibo Lyu","cross_cats":["cs.CV","cs.HC","cs.LG"],"headline":"Hierarchical memory from long-term records lets GUI agents resolve vague instructions and anticipate routines.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-01-14T17:12:48Z","title":"PersonalAlign: Hierarchical Implicit Intent Alignment for Personalized GUI Agent with Long-Term User-Centric Records"},"references":{"count":14,"internal_anchors":2,"resolved_work":14,"sample":[{"cited_arxiv_id":"2509.23661","doi":"","is_internal_anchor":true,"ref_index":1,"title":"LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training","work_id":"41c2802e-aff9-482f-b506-10955ff0838d","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Score the steps, not just the goal: Vlm-based subgoal evaluation for robotic manipulation","work_id":"ebb97240-cc8c-40cc-8684-46c3b7df07da","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"InProceedings of the IEEE/CVF conference on com- puter vision and pattern recognition, pages 10023– 10031","work_id":"cdfa2461-8017-4be7-b0a6-ad555737130d","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Advances in Neural Information Processing Systems, 37:52040–52094","work_id":"ba5bc0df-5aa8-497c-9121-7b4ac95aa9bb","year":2025},{"cited_arxiv_id":"2507.02259","doi":"","is_internal_anchor":true,"ref_index":5,"title":"MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent","work_id":"ac66fe72-b869-4874-8a9d-c110b849da0c","year":2024}],"snapshot_sha256":"427899431cf6e8c5308e1ad4f6bc09c0a5db2c0b063264f2b2a6d2c9593edd37"},"source":{"id":"2601.09636","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-16T14:29:14.352576Z","id":"d044c2cf-fa1f-4681-8c24-c470b471c708","model_set":{"reader":"grok-4.3"},"one_line_summary":"PersonalAlign introduces a hierarchical memory agent that uses long-term user records to resolve vague GUI instructions and provide proactive assistance, improving execution by 15.7% and proactive performance by 7.3% on the new AndroidIntent benchmark.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Hierarchical memory from long-term records lets GUI agents resolve vague instructions and anticipate routines.","strongest_claim":"HIM-Agent significantly improves both execution and proactive performance by 15.7% and 7.3% on the AndroidIntent benchmark.","weakest_assumption":"That the 20k long-term records contain stable, generalizable user preferences and routines that transfer to new vague instructions without overfitting to the 20 users in the benchmark."}},"verdict_id":"d044c2cf-fa1f-4681-8c24-c470b471c708"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:842ffd64e71ae32f163dc3ecc8fb05ae6248ae992ccaf9546ea58279144678a1","target":"record","created_at":"2026-05-18T03:09:24Z","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":"a49193ab6edf6abbdf7bfc1b3c120b124c335870cdd3beda373b2110122397fd","cross_cats_sorted":["cs.CV","cs.HC","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-01-14T17:12:48Z","title_canon_sha256":"727806031e13f0e4d72d9f79b386a55a2ff732d15caea0223681d8386018b105"},"schema_version":"1.0","source":{"id":"2601.09636","kind":"arxiv","version":2}},"canonical_sha256":"f5d2c447f0289db3c7d1f212b9260259ef70cca216990a857909fb723443730a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5d2c447f0289db3c7d1f212b9260259ef70cca216990a857909fb723443730a","first_computed_at":"2026-05-18T03:09:24.498273Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:24.498273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Cj/Sj9tO0HfMz+P8ygQThzNNpyR0NqbrF/D+Iq7vcrEK6H+PUxruhoCmjGip1ssU7q92YLmWLGGIZrsL+RgYBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:24.499085Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.09636","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:842ffd64e71ae32f163dc3ecc8fb05ae6248ae992ccaf9546ea58279144678a1","sha256:8ed36bea88039c52b8a849678311a0ccd38c085caa8bbc5d1e005c464164071d"],"state_sha256":"c4c2bb975a1f6972814f7b51aa2ebe8d1184f8c607150cfdb3dce32da9d10494"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ig9zOQyfiYae96sL/n27cyf8BBtqlpJzaQ2s6YkAd6f4CBQvYUrwx+yY4bFtezZcaoZPBijpPRLUwSfS/XdeAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T14:39:43.027650Z","bundle_sha256":"01c787f4db652adb8cbbeb12b6f6f82e69d6a8f263cc0f7f60438bade9e9e8af"}}