{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VZ523GEWJR7PUTEF72KF5FCUGF","short_pith_number":"pith:VZ523GEW","schema_version":"1.0","canonical_sha256":"ae7bad98964c7efa4c85fe945e9454316b571afe6b18402ea2c84873e40bd4cc","source":{"kind":"arxiv","id":"2407.10385","version":2},"attestation_state":"computed","paper":{"title":"By My Eyes: Grounding Multimodal Large Language Models with Sensor Data via Visual Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Biniyam Aschalew Tolera, Hyungjun Yoon, Kimin Lee, Sung-Ju Lee, Taesik Gong","submitted_at":"2024-07-15T01:33:54Z","abstract_excerpt":"Large language models (LLMs) have demonstrated exceptional abilities across various domains. However, utilizing LLMs for ubiquitous sensing applications remains challenging as existing text-prompt methods show significant performance degradation when handling long sensor data sequences. We propose a visual prompting approach for sensor data using multimodal LLMs (MLLMs). We design a visual prompt that directs MLLMs to utilize visualized sensor data alongside the target sensory task descriptions. Additionally, we introduce a visualization generator that automates the creation of optimal visuali"},"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":"2407.10385","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-15T01:33:54Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"b4f130263e60506c7e8c232d1d9f16c00b957ba37084936c30437f6b092fbe51","abstract_canon_sha256":"99c0a587b547affcefb4aaa7b8be260881b05c2f54e2c84c67e62de8104f5d02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:06.009388Z","signature_b64":"q74DDNJrmCtryiVuEiGI7ntnZ4NMOsrXeLTLsbh8ju1ttbJ4hLJJLeVxZdI70XuL5wQQdVhk3iL9WiBk7sWKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae7bad98964c7efa4c85fe945e9454316b571afe6b18402ea2c84873e40bd4cc","last_reissued_at":"2026-07-05T09:13:06.008909Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:06.008909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"By My Eyes: Grounding Multimodal Large Language Models with Sensor Data via Visual Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Biniyam Aschalew Tolera, Hyungjun Yoon, Kimin Lee, Sung-Ju Lee, Taesik Gong","submitted_at":"2024-07-15T01:33:54Z","abstract_excerpt":"Large language models (LLMs) have demonstrated exceptional abilities across various domains. However, utilizing LLMs for ubiquitous sensing applications remains challenging as existing text-prompt methods show significant performance degradation when handling long sensor data sequences. We propose a visual prompting approach for sensor data using multimodal LLMs (MLLMs). We design a visual prompt that directs MLLMs to utilize visualized sensor data alongside the target sensory task descriptions. Additionally, we introduce a visualization generator that automates the creation of optimal visuali"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10385","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/2407.10385/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":"2407.10385","created_at":"2026-07-05T09:13:06.008960+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.10385v2","created_at":"2026-07-05T09:13:06.008960+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10385","created_at":"2026-07-05T09:13:06.008960+00:00"},{"alias_kind":"pith_short_12","alias_value":"VZ523GEWJR7P","created_at":"2026-07-05T09:13:06.008960+00:00"},{"alias_kind":"pith_short_16","alias_value":"VZ523GEWJR7PUTEF","created_at":"2026-07-05T09:13:06.008960+00:00"},{"alias_kind":"pith_short_8","alias_value":"VZ523GEW","created_at":"2026-07-05T09:13:06.008960+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.23025","citing_title":"LENS: LLM-Enabled Narrative Synthesis for Mental Health by Aligning Multimodal Sensing with Language Models","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VZ523GEWJR7PUTEF72KF5FCUGF","json":"https://pith.science/pith/VZ523GEWJR7PUTEF72KF5FCUGF.json","graph_json":"https://pith.science/api/pith-number/VZ523GEWJR7PUTEF72KF5FCUGF/graph.json","events_json":"https://pith.science/api/pith-number/VZ523GEWJR7PUTEF72KF5FCUGF/events.json","paper":"https://pith.science/paper/VZ523GEW"},"agent_actions":{"view_html":"https://pith.science/pith/VZ523GEWJR7PUTEF72KF5FCUGF","download_json":"https://pith.science/pith/VZ523GEWJR7PUTEF72KF5FCUGF.json","view_paper":"https://pith.science/paper/VZ523GEW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.10385&json=true","fetch_graph":"https://pith.science/api/pith-number/VZ523GEWJR7PUTEF72KF5FCUGF/graph.json","fetch_events":"https://pith.science/api/pith-number/VZ523GEWJR7PUTEF72KF5FCUGF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VZ523GEWJR7PUTEF72KF5FCUGF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VZ523GEWJR7PUTEF72KF5FCUGF/action/storage_attestation","attest_author":"https://pith.science/pith/VZ523GEWJR7PUTEF72KF5FCUGF/action/author_attestation","sign_citation":"https://pith.science/pith/VZ523GEWJR7PUTEF72KF5FCUGF/action/citation_signature","submit_replication":"https://pith.science/pith/VZ523GEWJR7PUTEF72KF5FCUGF/action/replication_record"}},"created_at":"2026-07-05T09:13:06.008960+00:00","updated_at":"2026-07-05T09:13:06.008960+00:00"}