{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Q2FZQY4KDL5USCQW6XB5PTTBEG","short_pith_number":"pith:Q2FZQY4K","schema_version":"1.0","canonical_sha256":"868b98638a1afb490a16f5c3d7ce6121b9ec015a31a6ae95ee7bbcb4ede46306","source":{"kind":"arxiv","id":"2408.09085","version":1},"attestation_state":"computed","paper":{"title":"Segment Anything with Multiple Modalities","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aoran Xiao, Heli Qi, Naoto Yokoya, Shijian Lu, Weihao Xuan, Yun Xing","submitted_at":"2024-08-17T03:45:40Z","abstract_excerpt":"Robust and accurate segmentation of scenes has become one core functionality in various visual recognition and navigation tasks. This has inspired the recent development of Segment Anything Model (SAM), a foundation model for general mask segmentation. However, SAM is largely tailored for single-modal RGB images, limiting its applicability to multi-modal data captured with widely-adopted sensor suites, such as LiDAR plus RGB, depth plus RGB, thermal plus RGB, etc. We develop MM-SAM, an extension and expansion of SAM that supports cross-modal and multi-modal processing for robust and enhanced s"},"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":"2408.09085","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-17T03:45:40Z","cross_cats_sorted":[],"title_canon_sha256":"f39ef9532e9cb3f4be1b96c19f62f17c42e13613c7a2f3201b84aacdc4e7a5d2","abstract_canon_sha256":"2227ccf6bf29429af3253977095add9a57220f4480ec8d6035e9f1b2ba23d377"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:27.722805Z","signature_b64":"hUYC0i0d7qMVDPqHKkX0FrAvhb8mzNI71Qk7b7Q+XONuFd+mIP9xGl81tFYJZ8Gr6LsfBfNWC66p0FsUAdxSAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"868b98638a1afb490a16f5c3d7ce6121b9ec015a31a6ae95ee7bbcb4ede46306","last_reissued_at":"2026-07-05T08:56:27.722396Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:27.722396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Segment Anything with Multiple Modalities","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aoran Xiao, Heli Qi, Naoto Yokoya, Shijian Lu, Weihao Xuan, Yun Xing","submitted_at":"2024-08-17T03:45:40Z","abstract_excerpt":"Robust and accurate segmentation of scenes has become one core functionality in various visual recognition and navigation tasks. This has inspired the recent development of Segment Anything Model (SAM), a foundation model for general mask segmentation. However, SAM is largely tailored for single-modal RGB images, limiting its applicability to multi-modal data captured with widely-adopted sensor suites, such as LiDAR plus RGB, depth plus RGB, thermal plus RGB, etc. We develop MM-SAM, an extension and expansion of SAM that supports cross-modal and multi-modal processing for robust and enhanced s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09085","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/2408.09085/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":"2408.09085","created_at":"2026-07-05T08:56:27.722454+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.09085v1","created_at":"2026-07-05T08:56:27.722454+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09085","created_at":"2026-07-05T08:56:27.722454+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q2FZQY4KDL5U","created_at":"2026-07-05T08:56:27.722454+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q2FZQY4KDL5USCQW","created_at":"2026-07-05T08:56:27.722454+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q2FZQY4K","created_at":"2026-07-05T08:56:27.722454+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.04960","citing_title":"On Efficient Variants of Segment Anything Model: A Survey","ref_index":209,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q2FZQY4KDL5USCQW6XB5PTTBEG","json":"https://pith.science/pith/Q2FZQY4KDL5USCQW6XB5PTTBEG.json","graph_json":"https://pith.science/api/pith-number/Q2FZQY4KDL5USCQW6XB5PTTBEG/graph.json","events_json":"https://pith.science/api/pith-number/Q2FZQY4KDL5USCQW6XB5PTTBEG/events.json","paper":"https://pith.science/paper/Q2FZQY4K"},"agent_actions":{"view_html":"https://pith.science/pith/Q2FZQY4KDL5USCQW6XB5PTTBEG","download_json":"https://pith.science/pith/Q2FZQY4KDL5USCQW6XB5PTTBEG.json","view_paper":"https://pith.science/paper/Q2FZQY4K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.09085&json=true","fetch_graph":"https://pith.science/api/pith-number/Q2FZQY4KDL5USCQW6XB5PTTBEG/graph.json","fetch_events":"https://pith.science/api/pith-number/Q2FZQY4KDL5USCQW6XB5PTTBEG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q2FZQY4KDL5USCQW6XB5PTTBEG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q2FZQY4KDL5USCQW6XB5PTTBEG/action/storage_attestation","attest_author":"https://pith.science/pith/Q2FZQY4KDL5USCQW6XB5PTTBEG/action/author_attestation","sign_citation":"https://pith.science/pith/Q2FZQY4KDL5USCQW6XB5PTTBEG/action/citation_signature","submit_replication":"https://pith.science/pith/Q2FZQY4KDL5USCQW6XB5PTTBEG/action/replication_record"}},"created_at":"2026-07-05T08:56:27.722454+00:00","updated_at":"2026-07-05T08:56:27.722454+00:00"}