{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZKLDPJ6OUMFSVS2NSN4QAGVY32","short_pith_number":"pith:ZKLDPJ6O","schema_version":"1.0","canonical_sha256":"ca9637a7cea30b2acb4d9379001ab8de95c12259c3f78c2d2cf7bc3a6693306a","source":{"kind":"arxiv","id":"2409.10542","version":3},"attestation_state":"computed","paper":{"title":"SAM4MLLM: Enhance Multi-Modal Large Language Model for Referring Expression Segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Cheng Sun, Chu-Song Chen, Wei-Hua Li, Yi-Chia Chen, Yu-Chiang Frank Wang","submitted_at":"2024-09-01T12:09:33Z","abstract_excerpt":"We introduce SAM4MLLM, an innovative approach which integrates the Segment Anything Model (SAM) with Multi-Modal Large Language Models (MLLMs) for pixel-aware tasks. Our method enables MLLMs to learn pixel-level location information without requiring excessive modifications to the existing model architecture or adding specialized tokens. We introduce an inquiry-based approach that can effectively find prompt points for SAM to perform segmentation based on MLLM. It combines detailed visual information with the powerful expressive capabilities of large language models in a unified language-based"},"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":"2409.10542","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-09-01T12:09:33Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"ec297998fa389e7a855c941917b3ad52a192b53f57f10c924a5d1486beb2b66d","abstract_canon_sha256":"e605fb8b2123a2a20c4d909565b338daa7c1b586c8fba484ffd680b27d01b37c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:10.099851Z","signature_b64":"TGsv00YuTCYaz+T9I9rJGPLZTJ2UEnAIKdz+Vbpc17XZyZV96BA086lSYbJRY+L8vrvyZJw+mIfm6c70l+ucAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca9637a7cea30b2acb4d9379001ab8de95c12259c3f78c2d2cf7bc3a6693306a","last_reissued_at":"2026-07-05T09:49:10.098935Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:10.098935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAM4MLLM: Enhance Multi-Modal Large Language Model for Referring Expression Segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Cheng Sun, Chu-Song Chen, Wei-Hua Li, Yi-Chia Chen, Yu-Chiang Frank Wang","submitted_at":"2024-09-01T12:09:33Z","abstract_excerpt":"We introduce SAM4MLLM, an innovative approach which integrates the Segment Anything Model (SAM) with Multi-Modal Large Language Models (MLLMs) for pixel-aware tasks. Our method enables MLLMs to learn pixel-level location information without requiring excessive modifications to the existing model architecture or adding specialized tokens. We introduce an inquiry-based approach that can effectively find prompt points for SAM to perform segmentation based on MLLM. It combines detailed visual information with the powerful expressive capabilities of large language models in a unified language-based"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.10542","kind":"arxiv","version":3},"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/2409.10542/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":"2409.10542","created_at":"2026-07-05T09:49:10.098995+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.10542v3","created_at":"2026-07-05T09:49:10.098995+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.10542","created_at":"2026-07-05T09:49:10.098995+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZKLDPJ6OUMFS","created_at":"2026-07-05T09:49:10.098995+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZKLDPJ6OUMFSVS2N","created_at":"2026-07-05T09:49:10.098995+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZKLDPJ6O","created_at":"2026-07-05T09:49:10.098995+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22068","citing_title":"COCOTree: A Dataset and Benchmark for Open Tree-Structured Visual Decomposition","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19410","citing_title":"Vision Harnessing Agent for Open Ad-hoc Segmentation","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07916","citing_title":"Tarot-SAM3: Training-free SAM3 for Any Referring Expression Segmentation","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZKLDPJ6OUMFSVS2NSN4QAGVY32","json":"https://pith.science/pith/ZKLDPJ6OUMFSVS2NSN4QAGVY32.json","graph_json":"https://pith.science/api/pith-number/ZKLDPJ6OUMFSVS2NSN4QAGVY32/graph.json","events_json":"https://pith.science/api/pith-number/ZKLDPJ6OUMFSVS2NSN4QAGVY32/events.json","paper":"https://pith.science/paper/ZKLDPJ6O"},"agent_actions":{"view_html":"https://pith.science/pith/ZKLDPJ6OUMFSVS2NSN4QAGVY32","download_json":"https://pith.science/pith/ZKLDPJ6OUMFSVS2NSN4QAGVY32.json","view_paper":"https://pith.science/paper/ZKLDPJ6O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.10542&json=true","fetch_graph":"https://pith.science/api/pith-number/ZKLDPJ6OUMFSVS2NSN4QAGVY32/graph.json","fetch_events":"https://pith.science/api/pith-number/ZKLDPJ6OUMFSVS2NSN4QAGVY32/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZKLDPJ6OUMFSVS2NSN4QAGVY32/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZKLDPJ6OUMFSVS2NSN4QAGVY32/action/storage_attestation","attest_author":"https://pith.science/pith/ZKLDPJ6OUMFSVS2NSN4QAGVY32/action/author_attestation","sign_citation":"https://pith.science/pith/ZKLDPJ6OUMFSVS2NSN4QAGVY32/action/citation_signature","submit_replication":"https://pith.science/pith/ZKLDPJ6OUMFSVS2NSN4QAGVY32/action/replication_record"}},"created_at":"2026-07-05T09:49:10.098995+00:00","updated_at":"2026-07-05T09:49:10.098995+00:00"}