{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EKY4TXLABJPHBK5KAEX6EHQV5N","short_pith_number":"pith:EKY4TXLA","schema_version":"1.0","canonical_sha256":"22b1c9dd600a5e70abaa012fe21e15eb542128382cd8fc6931322b8bde6bb24f","source":{"kind":"arxiv","id":"2606.07402","version":1},"attestation_state":"computed","paper":{"title":"M$^3$Exam: Benchmarking Multimodal Memory for Realistic User-Agent Interactions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fangyuan Zhang, Junle Chen, Qintian Guo, Wei Chen, Wenxuan Liu, Xiaofang Zhou, Yuqian Wu, Zhengjun Huang, Zhoujin Tian","submitted_at":"2026-06-05T15:44:18Z","abstract_excerpt":"Language agents are increasingly deployed over accumulating multimodal information, yet existing benchmarks assume a human-human form with sparse visuals and straightforward content, evaluating neither reasoning over authentic multimodal file interaction nor the interpretation of concealed user information. We therefore introduce M$^3$Exam, a query-centric multimodal conversational memory benchmark built on realistic user-agent interaction, with multi-dimensional evaluation spanning cross-modal grounding and implicit information inference. Benchmarking MLLMs and memory systems reveals persiste"},"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":"2606.07402","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-05T15:44:18Z","cross_cats_sorted":[],"title_canon_sha256":"130ee75ae494588d4aea61260fcab35f6efcad881c8e76eade082edf0c499896","abstract_canon_sha256":"4edd6ce4a5874a18eb29102d63e7bc113cf11d6e0cbfcc6dac891d0ffa59d694"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:05:25.070350Z","signature_b64":"9ECZU8QeADt/nvPgUv6ZSivXEYzZMKQSf7FiC/vq9CW/eOXVbhpKTzchUtj9r/RUZ7yz5EBONxIXr1kQXtW8Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22b1c9dd600a5e70abaa012fe21e15eb542128382cd8fc6931322b8bde6bb24f","last_reissued_at":"2026-06-08T01:05:25.069602Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:05:25.069602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"M$^3$Exam: Benchmarking Multimodal Memory for Realistic User-Agent Interactions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fangyuan Zhang, Junle Chen, Qintian Guo, Wei Chen, Wenxuan Liu, Xiaofang Zhou, Yuqian Wu, Zhengjun Huang, Zhoujin Tian","submitted_at":"2026-06-05T15:44:18Z","abstract_excerpt":"Language agents are increasingly deployed over accumulating multimodal information, yet existing benchmarks assume a human-human form with sparse visuals and straightforward content, evaluating neither reasoning over authentic multimodal file interaction nor the interpretation of concealed user information. We therefore introduce M$^3$Exam, a query-centric multimodal conversational memory benchmark built on realistic user-agent interaction, with multi-dimensional evaluation spanning cross-modal grounding and implicit information inference. Benchmarking MLLMs and memory systems reveals persiste"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07402","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/2606.07402/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":"2606.07402","created_at":"2026-06-08T01:05:25.069724+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07402v1","created_at":"2026-06-08T01:05:25.069724+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07402","created_at":"2026-06-08T01:05:25.069724+00:00"},{"alias_kind":"pith_short_12","alias_value":"EKY4TXLABJPH","created_at":"2026-06-08T01:05:25.069724+00:00"},{"alias_kind":"pith_short_16","alias_value":"EKY4TXLABJPHBK5K","created_at":"2026-06-08T01:05:25.069724+00:00"},{"alias_kind":"pith_short_8","alias_value":"EKY4TXLA","created_at":"2026-06-08T01:05:25.069724+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/EKY4TXLABJPHBK5KAEX6EHQV5N","json":"https://pith.science/pith/EKY4TXLABJPHBK5KAEX6EHQV5N.json","graph_json":"https://pith.science/api/pith-number/EKY4TXLABJPHBK5KAEX6EHQV5N/graph.json","events_json":"https://pith.science/api/pith-number/EKY4TXLABJPHBK5KAEX6EHQV5N/events.json","paper":"https://pith.science/paper/EKY4TXLA"},"agent_actions":{"view_html":"https://pith.science/pith/EKY4TXLABJPHBK5KAEX6EHQV5N","download_json":"https://pith.science/pith/EKY4TXLABJPHBK5KAEX6EHQV5N.json","view_paper":"https://pith.science/paper/EKY4TXLA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07402&json=true","fetch_graph":"https://pith.science/api/pith-number/EKY4TXLABJPHBK5KAEX6EHQV5N/graph.json","fetch_events":"https://pith.science/api/pith-number/EKY4TXLABJPHBK5KAEX6EHQV5N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EKY4TXLABJPHBK5KAEX6EHQV5N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EKY4TXLABJPHBK5KAEX6EHQV5N/action/storage_attestation","attest_author":"https://pith.science/pith/EKY4TXLABJPHBK5KAEX6EHQV5N/action/author_attestation","sign_citation":"https://pith.science/pith/EKY4TXLABJPHBK5KAEX6EHQV5N/action/citation_signature","submit_replication":"https://pith.science/pith/EKY4TXLABJPHBK5KAEX6EHQV5N/action/replication_record"}},"created_at":"2026-06-08T01:05:25.069724+00:00","updated_at":"2026-06-08T01:05:25.069724+00:00"}