{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2MUDLHAUFY3T5J7YY2TK2YB6PY","short_pith_number":"pith:2MUDLHAU","schema_version":"1.0","canonical_sha256":"d328359c142e373ea7f8c6a6ad603e7e0648c0e83bce89c9beb016ba0b8ea8a5","source":{"kind":"arxiv","id":"2608.01543","version":1},"attestation_state":"computed","paper":{"title":"V-Mem: Modality-Routed Retrieval for Long-Term Multimodal Agentic Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.IR"],"primary_cat":"cs.AI","authors_text":"Bingzhe Li, Dingyi Kang, Dongming Jiang, Guanpeng Li, Yi Li","submitted_at":"2026-08-02T23:47:18Z","abstract_excerpt":"Interaction between users and LLM agents is increasingly multimodal: conversations interleave text with images, and a later question may target either. Yet most agent memories are designed around text, and even the few that support multimodal conversations still fail on vision-related questions. We trace this failure to an assumption behind the similarity search they rely on: in the index space, a query lies close to the relevant evidence that answers it. In multimodal settings, two gaps break it. By the modality gap, a query lies closer to memory content of its own modality than to evidence i"},"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":"2608.01543","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-02T23:47:18Z","cross_cats_sorted":["cs.CL","cs.CV","cs.IR"],"title_canon_sha256":"c4108592b4e01e9051ebed6b76ba62a6e58e2f30541a7432ea3d14a722fc1db2","abstract_canon_sha256":"fe2cd517a9a2737262e737eef79bc6ca476b31a1e6bcd37d6e65d9dbbe9c35e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:05:53.934035Z","signature_b64":"kPzZHPAe4O5tb47JNlt8JkBeqwLJ2xl6B+U9Jlsd5VBwXo1v3zb0fqy9v4RlwOQ155psExN0vuNE60Si+SFbBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d328359c142e373ea7f8c6a6ad603e7e0648c0e83bce89c9beb016ba0b8ea8a5","last_reissued_at":"2026-08-04T02:05:53.932534Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:05:53.932534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"V-Mem: Modality-Routed Retrieval for Long-Term Multimodal Agentic Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.IR"],"primary_cat":"cs.AI","authors_text":"Bingzhe Li, Dingyi Kang, Dongming Jiang, Guanpeng Li, Yi Li","submitted_at":"2026-08-02T23:47:18Z","abstract_excerpt":"Interaction between users and LLM agents is increasingly multimodal: conversations interleave text with images, and a later question may target either. Yet most agent memories are designed around text, and even the few that support multimodal conversations still fail on vision-related questions. We trace this failure to an assumption behind the similarity search they rely on: in the index space, a query lies close to the relevant evidence that answers it. In multimodal settings, two gaps break it. By the modality gap, a query lies closer to memory content of its own modality than to evidence i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01543","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/2608.01543/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":"2608.01543","created_at":"2026-08-04T02:05:53.933960+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.01543v1","created_at":"2026-08-04T02:05:53.933960+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01543","created_at":"2026-08-04T02:05:53.933960+00:00"},{"alias_kind":"pith_short_12","alias_value":"2MUDLHAUFY3T","created_at":"2026-08-04T02:05:53.933960+00:00"},{"alias_kind":"pith_short_16","alias_value":"2MUDLHAUFY3T5J7Y","created_at":"2026-08-04T02:05:53.933960+00:00"},{"alias_kind":"pith_short_8","alias_value":"2MUDLHAU","created_at":"2026-08-04T02:05:53.933960+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2MUDLHAUFY3T5J7YY2TK2YB6PY","json":"https://pith.science/pith/2MUDLHAUFY3T5J7YY2TK2YB6PY.json","graph_json":"https://pith.science/api/pith-number/2MUDLHAUFY3T5J7YY2TK2YB6PY/graph.json","events_json":"https://pith.science/api/pith-number/2MUDLHAUFY3T5J7YY2TK2YB6PY/events.json","paper":"https://pith.science/paper/2MUDLHAU"},"agent_actions":{"view_html":"https://pith.science/pith/2MUDLHAUFY3T5J7YY2TK2YB6PY","download_json":"https://pith.science/pith/2MUDLHAUFY3T5J7YY2TK2YB6PY.json","view_paper":"https://pith.science/paper/2MUDLHAU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.01543&json=true","fetch_graph":"https://pith.science/api/pith-number/2MUDLHAUFY3T5J7YY2TK2YB6PY/graph.json","fetch_events":"https://pith.science/api/pith-number/2MUDLHAUFY3T5J7YY2TK2YB6PY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2MUDLHAUFY3T5J7YY2TK2YB6PY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2MUDLHAUFY3T5J7YY2TK2YB6PY/action/storage_attestation","attest_author":"https://pith.science/pith/2MUDLHAUFY3T5J7YY2TK2YB6PY/action/author_attestation","sign_citation":"https://pith.science/pith/2MUDLHAUFY3T5J7YY2TK2YB6PY/action/citation_signature","submit_replication":"https://pith.science/pith/2MUDLHAUFY3T5J7YY2TK2YB6PY/action/replication_record"}},"created_at":"2026-08-04T02:05:53.933960+00:00","updated_at":"2026-08-04T02:05:53.933960+00:00"}