{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:H6KWZFSQQNZWIEOI2FR6HCVEZQ","short_pith_number":"pith:H6KWZFSQ","canonical_record":{"source":{"id":"2605.14504","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T07:47:53Z","cross_cats_sorted":[],"title_canon_sha256":"252a621d8f7b57ae821328d3607fa3fa1e1d377ae7f8fc272c71550255cd8e83","abstract_canon_sha256":"db8c4a3e1eb299b0b1ab53c841f726d0d7d7952d4921139f945592bfb70327db"},"schema_version":"1.0"},"canonical_sha256":"3f956c965083736411c8d163e38aa4cc0ff6e4cd22a55bf56445526cbae39073","source":{"kind":"arxiv","id":"2605.14504","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14504","created_at":"2026-05-17T23:39:06Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14504v1","created_at":"2026-05-17T23:39:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14504","created_at":"2026-05-17T23:39:06Z"},{"alias_kind":"pith_short_12","alias_value":"H6KWZFSQQNZW","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"H6KWZFSQQNZWIEOI","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"H6KWZFSQ","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:H6KWZFSQQNZWIEOI2FR6HCVEZQ","target":"record","payload":{"canonical_record":{"source":{"id":"2605.14504","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T07:47:53Z","cross_cats_sorted":[],"title_canon_sha256":"252a621d8f7b57ae821328d3607fa3fa1e1d377ae7f8fc272c71550255cd8e83","abstract_canon_sha256":"db8c4a3e1eb299b0b1ab53c841f726d0d7d7952d4921139f945592bfb70327db"},"schema_version":"1.0"},"canonical_sha256":"3f956c965083736411c8d163e38aa4cc0ff6e4cd22a55bf56445526cbae39073","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:06.277782Z","signature_b64":"eUqK6tA7zv7EPiBPWZrlKOHpeswBnwmOO4wOtR1jBUOQDgpF5+qVfBvc1+f3+Sq7dp7FT8Xqt2+AbsJStmDCCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f956c965083736411c8d163e38aa4cc0ff6e4cd22a55bf56445526cbae39073","last_reissued_at":"2026-05-17T23:39:06.276874Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:06.276874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.14504","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":"2026-05-17T23:39:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7nvAtDJgTftZdtBHg/bBLZ7Kro4U6fh1v5EJSgBjdcwX9R4L8VDS/vJoTQ2jvft8glefj0B5P5FSi1iMH/rPAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T23:32:24.140891Z"},"content_sha256":"b5058a52f0f9d8df3c17d645f3e95cf60f3250fee448d2ce0e43a6602ac3a9ce","schema_version":"1.0","event_id":"sha256:b5058a52f0f9d8df3c17d645f3e95cf60f3250fee448d2ce0e43a6602ac3a9ce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:H6KWZFSQQNZWIEOI2FR6HCVEZQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When Robots Do the Chores: A Benchmark and Agent for Long-Horizon Household Task Execution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"HoloMind agent with DAG planner and dual memories raises long-horizon household task success while cutting dependence on model size.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bowen Pang, Jing Liu, Longteng Guo, Ruyi Ji, Xingjian He, Yanghong Mei, Zilin Zhu, Zongxun Zhang","submitted_at":"2026-05-14T07:47:53Z","abstract_excerpt":"Long-horizon household tasks demand robust high-level planning and sustained reasoning capabilities, which are largely overlooked by existing embodied AI benchmarks that emphasize short-horizon navigation or manipulation and rely on fixed task categories. We introduce LongAct, a benchmark designed to evaluate planning-level autonomy in long-horizon household tasks specified through free-form instructions. By abstracting away embodiment-specific low-level control, LongAct isolates high-level cognitive capabilities such as instruction understanding, dependency management, memory maintenance, and"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"HoloMind substantially improves long-horizon performance while reducing reliance on model scale. Even top models achieve only 59% goal completion and 16% full-task success.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"Abstracting away embodiment-specific low-level control isolates high-level cognitive capabilities such as instruction understanding, dependency management, memory maintenance, and adaptive planning without losing essential task realism.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"LongAct benchmark reveals top VLMs reach only 59% goal completion and 16% full success on long-horizon household tasks, while HoloMind agent improves results via DAG planner, multimodal spatial memory, episodic memory, and global critic.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"HoloMind agent with DAG planner and dual memories raises long-horizon household task success while cutting dependence on model size.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"ec12b714591e2539c6a20c56a8798200702d62b6d8ea32579e2375c6d12dd29d"},"source":{"id":"2605.14504","kind":"arxiv","version":1},"verdict":{"id":"94bc80ce-e9cf-49aa-b028-9585781dec0f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T01:55:07.807981Z","strongest_claim":"HoloMind substantially improves long-horizon performance while reducing reliance on model scale. Even top models achieve only 59% goal completion and 16% full-task success.","one_line_summary":"LongAct benchmark reveals top VLMs reach only 59% goal completion and 16% full success on long-horizon household tasks, while HoloMind agent improves results via DAG planner, multimodal spatial memory, episodic memory, and global critic.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"Abstracting away embodiment-specific low-level control isolates high-level cognitive capabilities such as instruction understanding, dependency management, memory maintenance, and adaptive planning without losing essential task realism.","pith_extraction_headline":"HoloMind agent with DAG planner and dual memories raises long-horizon household task success while cutting dependence on model size."},"references":{"count":43,"sample":[{"doi":"","year":2025,"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","ref_index":1,"cited_arxiv_id":"2505.09388","is_internal_anchor":true},{"doi":"","year":2023,"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","ref_index":2,"cited_arxiv_id":"2303.08774","is_internal_anchor":true},{"doi":"","year":2023,"title":"H. Liu, C. Li, Q. Wu, and Y . J. Lee. Visual instruction tuning.Advances in Neural Information Processing Systems, 36:1–19, 2023","work_id":"4eec8a8e-8c6e-46ee-8008-9b1dd58415a1","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","work_id":"cbc2bb21-b6bb-46c0-80bf-107e195ffe10","ref_index":4,"cited_arxiv_id":"2308.12966","is_internal_anchor":true},{"doi":"","year":2023,"title":"Gemini: A Family of Highly Capable Multimodal Models","work_id":"83f7c85b-3f11-450f-ac0c-64d9745220b2","ref_index":5,"cited_arxiv_id":"2312.11805","is_internal_anchor":true}],"resolved_work":43,"snapshot_sha256":"21571ef359ea4e79e652bc800ce523debebc34db345e2391734a67fe6616f61d","internal_anchors":12},"formal_canon":{"evidence_count":2,"snapshot_sha256":"d547d575035ac5376155c4db5e45601102cffa2ea632f260cf140bd9dc162946"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"94bc80ce-e9cf-49aa-b028-9585781dec0f"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RjAtwT1lifzCtqFLVzYsCZRS8Dkr4ESabyTZ1jQMFBwwvDdyuZadjjKydpeTnRU+HqJyV859QgbfVLOeiEgvDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T23:32:24.142105Z"},"content_sha256":"8e23c1c73f288bc10884fdd7d4bf4b9e23bcba4ce11003a6ee2bbe40e4623d8c","schema_version":"1.0","event_id":"sha256:8e23c1c73f288bc10884fdd7d4bf4b9e23bcba4ce11003a6ee2bbe40e4623d8c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H6KWZFSQQNZWIEOI2FR6HCVEZQ/bundle.json","state_url":"https://pith.science/pith/H6KWZFSQQNZWIEOI2FR6HCVEZQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H6KWZFSQQNZWIEOI2FR6HCVEZQ/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":"2026-05-25T23:32:24Z","links":{"resolver":"https://pith.science/pith/H6KWZFSQQNZWIEOI2FR6HCVEZQ","bundle":"https://pith.science/pith/H6KWZFSQQNZWIEOI2FR6HCVEZQ/bundle.json","state":"https://pith.science/pith/H6KWZFSQQNZWIEOI2FR6HCVEZQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H6KWZFSQQNZWIEOI2FR6HCVEZQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:H6KWZFSQQNZWIEOI2FR6HCVEZQ","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":"db8c4a3e1eb299b0b1ab53c841f726d0d7d7952d4921139f945592bfb70327db","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T07:47:53Z","title_canon_sha256":"252a621d8f7b57ae821328d3607fa3fa1e1d377ae7f8fc272c71550255cd8e83"},"schema_version":"1.0","source":{"id":"2605.14504","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14504","created_at":"2026-05-17T23:39:06Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14504v1","created_at":"2026-05-17T23:39:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14504","created_at":"2026-05-17T23:39:06Z"},{"alias_kind":"pith_short_12","alias_value":"H6KWZFSQQNZW","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"H6KWZFSQQNZWIEOI","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"H6KWZFSQ","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:8e23c1c73f288bc10884fdd7d4bf4b9e23bcba4ce11003a6ee2bbe40e4623d8c","target":"graph","created_at":"2026-05-17T23:39:06Z","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":"HoloMind substantially improves long-horizon performance while reducing reliance on model scale. Even top models achieve only 59% goal completion and 16% full-task success."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"Abstracting away embodiment-specific low-level control isolates high-level cognitive capabilities such as instruction understanding, dependency management, memory maintenance, and adaptive planning without losing essential task realism."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"LongAct benchmark reveals top VLMs reach only 59% goal completion and 16% full success on long-horizon household tasks, while HoloMind agent improves results via DAG planner, multimodal spatial memory, episodic memory, and global critic."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"HoloMind agent with DAG planner and dual memories raises long-horizon household task success while cutting dependence on model size."}],"snapshot_sha256":"ec12b714591e2539c6a20c56a8798200702d62b6d8ea32579e2375c6d12dd29d"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"d547d575035ac5376155c4db5e45601102cffa2ea632f260cf140bd9dc162946"},"paper":{"abstract_excerpt":"Long-horizon household tasks demand robust high-level planning and sustained reasoning capabilities, which are largely overlooked by existing embodied AI benchmarks that emphasize short-horizon navigation or manipulation and rely on fixed task categories. We introduce LongAct, a benchmark designed to evaluate planning-level autonomy in long-horizon household tasks specified through free-form instructions. By abstracting away embodiment-specific low-level control, LongAct isolates high-level cognitive capabilities such as instruction understanding, dependency management, memory maintenance, and","authors_text":"Bowen Pang, Jing Liu, Longteng Guo, Ruyi Ji, Xingjian He, Yanghong Mei, Zilin Zhu, Zongxun Zhang","cross_cats":[],"headline":"HoloMind agent with DAG planner and dual memories raises long-horizon household task success while cutting dependence on model size.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T07:47:53Z","title":"When Robots Do the Chores: A Benchmark and Agent for Long-Horizon Household Task Execution"},"references":{"count":43,"internal_anchors":12,"resolved_work":43,"sample":[{"cited_arxiv_id":"2505.09388","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","year":2025},{"cited_arxiv_id":"2303.08774","doi":"","is_internal_anchor":true,"ref_index":2,"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"H. Liu, C. Li, Q. Wu, and Y . J. Lee. Visual instruction tuning.Advances in Neural Information Processing Systems, 36:1–19, 2023","work_id":"4eec8a8e-8c6e-46ee-8008-9b1dd58415a1","year":2023},{"cited_arxiv_id":"2308.12966","doi":"","is_internal_anchor":true,"ref_index":4,"title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","work_id":"cbc2bb21-b6bb-46c0-80bf-107e195ffe10","year":2023},{"cited_arxiv_id":"2312.11805","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Gemini: A Family of Highly Capable Multimodal Models","work_id":"83f7c85b-3f11-450f-ac0c-64d9745220b2","year":2023}],"snapshot_sha256":"21571ef359ea4e79e652bc800ce523debebc34db345e2391734a67fe6616f61d"},"source":{"id":"2605.14504","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T01:55:07.807981Z","id":"94bc80ce-e9cf-49aa-b028-9585781dec0f","model_set":{"reader":"grok-4.3"},"one_line_summary":"LongAct benchmark reveals top VLMs reach only 59% goal completion and 16% full success on long-horizon household tasks, while HoloMind agent improves results via DAG planner, multimodal spatial memory, episodic memory, and global critic.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"HoloMind agent with DAG planner and dual memories raises long-horizon household task success while cutting dependence on model size.","strongest_claim":"HoloMind substantially improves long-horizon performance while reducing reliance on model scale. Even top models achieve only 59% goal completion and 16% full-task success.","weakest_assumption":"Abstracting away embodiment-specific low-level control isolates high-level cognitive capabilities such as instruction understanding, dependency management, memory maintenance, and adaptive planning without losing essential task realism."}},"verdict_id":"94bc80ce-e9cf-49aa-b028-9585781dec0f"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b5058a52f0f9d8df3c17d645f3e95cf60f3250fee448d2ce0e43a6602ac3a9ce","target":"record","created_at":"2026-05-17T23:39:06Z","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":"db8c4a3e1eb299b0b1ab53c841f726d0d7d7952d4921139f945592bfb70327db","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T07:47:53Z","title_canon_sha256":"252a621d8f7b57ae821328d3607fa3fa1e1d377ae7f8fc272c71550255cd8e83"},"schema_version":"1.0","source":{"id":"2605.14504","kind":"arxiv","version":1}},"canonical_sha256":"3f956c965083736411c8d163e38aa4cc0ff6e4cd22a55bf56445526cbae39073","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f956c965083736411c8d163e38aa4cc0ff6e4cd22a55bf56445526cbae39073","first_computed_at":"2026-05-17T23:39:06.276874Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:06.276874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eUqK6tA7zv7EPiBPWZrlKOHpeswBnwmOO4wOtR1jBUOQDgpF5+qVfBvc1+f3+Sq7dp7FT8Xqt2+AbsJStmDCCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:06.277782Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14504","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5058a52f0f9d8df3c17d645f3e95cf60f3250fee448d2ce0e43a6602ac3a9ce","sha256:8e23c1c73f288bc10884fdd7d4bf4b9e23bcba4ce11003a6ee2bbe40e4623d8c"],"state_sha256":"ded2732ca4a0924b7c80f2340445c0aff22aee4dc45928ba3e5465ca21e8d046"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gv5CFyMnlXB/OCjR7WM+HaGqLUhFue9a9zNipIykZrMOUotI7bpGfs69FimOzzuWgMJ9gd9Bd6lkjKb9GRO7Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T23:32:24.147236Z","bundle_sha256":"844f6b2dc54ed3cf3fa86d741d50454a4fbfaab080cfd2ef78fad8c72ba1fbce"}}