{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HPVOKD7MMYM4JAP32BE5MDHOHT","short_pith_number":"pith:HPVOKD7M","schema_version":"1.0","canonical_sha256":"3beae50fec6619c481fbd049d60cee3cd145b627f01a53493a534ed7e2621c20","source":{"kind":"arxiv","id":"2602.15513","version":2},"attestation_state":"computed","paper":{"title":"HIMM: Human-Inspired Long-Term Memory Modeling for Embodied Exploration and Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Bo Wang, Ji Li, Jing Xia, Mingyi Li, Shiyan Hu","submitted_at":"2026-02-17T11:41:28Z","abstract_excerpt":"Deploying Multimodal Large Language Models as the brain of embodied agents remains challenging, particularly under long-horizon observations and limited context budgets. Existing memory assisted methods often rely on textual summaries, which discard rich visual and spatial details and remain brittle in non-stationary environments. In this work, we propose a non-parametric memory framework that explicitly disentangles episodic and semantic memory for embodied exploration and question answering. Our retrieval-first, reasoning-assisted paradigm recalls episodic experiences via semantic similarity"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2602.15513","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-02-17T11:41:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"85f025fb2425ec3561124a131dd4d5353a93dcaf573377cff2b0483c7e8b9558","abstract_canon_sha256":"493a9ca63c11c1696df691c0f97733e6b6c5e31f38c72e247436efab3227c253"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:20.906723Z","signature_b64":"i6Imn6WHpcL06rUFH4HIblwteNhS3FBVEAH3G+LD0aGiwLWKp1t0qiPPS9DUqatgisSOiHTIYfYBztTX2lQMCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3beae50fec6619c481fbd049d60cee3cd145b627f01a53493a534ed7e2621c20","last_reissued_at":"2026-06-19T16:11:20.906261Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:20.906261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HIMM: Human-Inspired Long-Term Memory Modeling for Embodied Exploration and Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Bo Wang, Ji Li, Jing Xia, Mingyi Li, Shiyan Hu","submitted_at":"2026-02-17T11:41:28Z","abstract_excerpt":"Deploying Multimodal Large Language Models as the brain of embodied agents remains challenging, particularly under long-horizon observations and limited context budgets. Existing memory assisted methods often rely on textual summaries, which discard rich visual and spatial details and remain brittle in non-stationary environments. In this work, we propose a non-parametric memory framework that explicitly disentangles episodic and semantic memory for embodied exploration and question answering. Our retrieval-first, reasoning-assisted paradigm recalls episodic experiences via semantic similarity"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.15513","kind":"arxiv","version":2},"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/2602.15513/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2602.15513","created_at":"2026-06-19T16:11:20.906327+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.15513v2","created_at":"2026-06-19T16:11:20.906327+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.15513","created_at":"2026-06-19T16:11:20.906327+00:00"},{"alias_kind":"pith_short_12","alias_value":"HPVOKD7MMYM4","created_at":"2026-06-19T16:11:20.906327+00:00"},{"alias_kind":"pith_short_16","alias_value":"HPVOKD7MMYM4JAP3","created_at":"2026-06-19T16:11:20.906327+00:00"},{"alias_kind":"pith_short_8","alias_value":"HPVOKD7M","created_at":"2026-06-19T16:11:20.906327+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.10921","citing_title":"RoboMemArena: A Comprehensive and Challenging Robotic Memory Benchmark","ref_index":65,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HPVOKD7MMYM4JAP32BE5MDHOHT","json":"https://pith.science/pith/HPVOKD7MMYM4JAP32BE5MDHOHT.json","graph_json":"https://pith.science/api/pith-number/HPVOKD7MMYM4JAP32BE5MDHOHT/graph.json","events_json":"https://pith.science/api/pith-number/HPVOKD7MMYM4JAP32BE5MDHOHT/events.json","paper":"https://pith.science/paper/HPVOKD7M"},"agent_actions":{"view_html":"https://pith.science/pith/HPVOKD7MMYM4JAP32BE5MDHOHT","download_json":"https://pith.science/pith/HPVOKD7MMYM4JAP32BE5MDHOHT.json","view_paper":"https://pith.science/paper/HPVOKD7M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.15513&json=true","fetch_graph":"https://pith.science/api/pith-number/HPVOKD7MMYM4JAP32BE5MDHOHT/graph.json","fetch_events":"https://pith.science/api/pith-number/HPVOKD7MMYM4JAP32BE5MDHOHT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HPVOKD7MMYM4JAP32BE5MDHOHT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HPVOKD7MMYM4JAP32BE5MDHOHT/action/storage_attestation","attest_author":"https://pith.science/pith/HPVOKD7MMYM4JAP32BE5MDHOHT/action/author_attestation","sign_citation":"https://pith.science/pith/HPVOKD7MMYM4JAP32BE5MDHOHT/action/citation_signature","submit_replication":"https://pith.science/pith/HPVOKD7MMYM4JAP32BE5MDHOHT/action/replication_record"}},"created_at":"2026-06-19T16:11:20.906327+00:00","updated_at":"2026-06-19T16:11:20.906327+00:00"}