{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZKLDPJ6OUMFSVS2NSN4QAGVY32","short_pith_number":"pith:ZKLDPJ6O","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"},"canonical_sha256":"ca9637a7cea30b2acb4d9379001ab8de95c12259c3f78c2d2cf7bc3a6693306a","source":{"kind":"arxiv","id":"2409.10542","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.10542","created_at":"2026-07-05T09:49:10Z"},{"alias_kind":"arxiv_version","alias_value":"2409.10542v3","created_at":"2026-07-05T09:49:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.10542","created_at":"2026-07-05T09:49:10Z"},{"alias_kind":"pith_short_12","alias_value":"ZKLDPJ6OUMFS","created_at":"2026-07-05T09:49:10Z"},{"alias_kind":"pith_short_16","alias_value":"ZKLDPJ6OUMFSVS2N","created_at":"2026-07-05T09:49:10Z"},{"alias_kind":"pith_short_8","alias_value":"ZKLDPJ6O","created_at":"2026-07-05T09:49:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZKLDPJ6OUMFSVS2NSN4QAGVY32","target":"record","payload":{"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"},"canonical_sha256":"ca9637a7cea30b2acb4d9379001ab8de95c12259c3f78c2d2cf7bc3a6693306a","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"},"source_kind":"arxiv","source_id":"2409.10542","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:49:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o09PTqDxECva07ynIxEmMBm0K6ZS7zoH6MxLgjyECfFhTYLn7eQNvGKV8ZNFrtOCW+V1KExp/V3S4PaMDhBzDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T14:45:47.230364Z"},"content_sha256":"05faefffb4c03d594607de77e2b55994e59d660b6721ea8d08425f8a4e6888b9","schema_version":"1.0","event_id":"sha256:05faefffb4c03d594607de77e2b55994e59d660b6721ea8d08425f8a4e6888b9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZKLDPJ6OUMFSVS2NSN4QAGVY32","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:49:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E+yCQDM6tuHaptlP2lq3YP/8dY/PHY4JsCMmyB870ihFfih7uPo5pmFMFVfQK68XrikL1totE7+Na1Wtc29EBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T14:45:47.231129Z"},"content_sha256":"4a1bb37f15e535d8269ce3e6fffe1b121489fe2247d6a5eb5efb8ea20f060923","schema_version":"1.0","event_id":"sha256:4a1bb37f15e535d8269ce3e6fffe1b121489fe2247d6a5eb5efb8ea20f060923"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZKLDPJ6OUMFSVS2NSN4QAGVY32/bundle.json","state_url":"https://pith.science/pith/ZKLDPJ6OUMFSVS2NSN4QAGVY32/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZKLDPJ6OUMFSVS2NSN4QAGVY32/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-21T14:45:47Z","links":{"resolver":"https://pith.science/pith/ZKLDPJ6OUMFSVS2NSN4QAGVY32","bundle":"https://pith.science/pith/ZKLDPJ6OUMFSVS2NSN4QAGVY32/bundle.json","state":"https://pith.science/pith/ZKLDPJ6OUMFSVS2NSN4QAGVY32/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZKLDPJ6OUMFSVS2NSN4QAGVY32/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZKLDPJ6OUMFSVS2NSN4QAGVY32","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e605fb8b2123a2a20c4d909565b338daa7c1b586c8fba484ffd680b27d01b37c","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-09-01T12:09:33Z","title_canon_sha256":"ec297998fa389e7a855c941917b3ad52a192b53f57f10c924a5d1486beb2b66d"},"schema_version":"1.0","source":{"id":"2409.10542","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.10542","created_at":"2026-07-05T09:49:10Z"},{"alias_kind":"arxiv_version","alias_value":"2409.10542v3","created_at":"2026-07-05T09:49:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.10542","created_at":"2026-07-05T09:49:10Z"},{"alias_kind":"pith_short_12","alias_value":"ZKLDPJ6OUMFS","created_at":"2026-07-05T09:49:10Z"},{"alias_kind":"pith_short_16","alias_value":"ZKLDPJ6OUMFSVS2N","created_at":"2026-07-05T09:49:10Z"},{"alias_kind":"pith_short_8","alias_value":"ZKLDPJ6O","created_at":"2026-07-05T09:49:10Z"}],"graph_snapshots":[{"event_id":"sha256:4a1bb37f15e535d8269ce3e6fffe1b121489fe2247d6a5eb5efb8ea20f060923","target":"graph","created_at":"2026-07-05T09:49:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2409.10542/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Cheng Sun, Chu-Song Chen, Wei-Hua Li, Yi-Chia Chen, Yu-Chiang Frank Wang","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-09-01T12:09:33Z","title":"SAM4MLLM: Enhance Multi-Modal Large Language Model for Referring Expression Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.10542","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:05faefffb4c03d594607de77e2b55994e59d660b6721ea8d08425f8a4e6888b9","target":"record","created_at":"2026-07-05T09:49:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e605fb8b2123a2a20c4d909565b338daa7c1b586c8fba484ffd680b27d01b37c","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-09-01T12:09:33Z","title_canon_sha256":"ec297998fa389e7a855c941917b3ad52a192b53f57f10c924a5d1486beb2b66d"},"schema_version":"1.0","source":{"id":"2409.10542","kind":"arxiv","version":3}},"canonical_sha256":"ca9637a7cea30b2acb4d9379001ab8de95c12259c3f78c2d2cf7bc3a6693306a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca9637a7cea30b2acb4d9379001ab8de95c12259c3f78c2d2cf7bc3a6693306a","first_computed_at":"2026-07-05T09:49:10.098935Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:10.098935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TGsv00YuTCYaz+T9I9rJGPLZTJ2UEnAIKdz+Vbpc17XZyZV96BA086lSYbJRY+L8vrvyZJw+mIfm6c70l+ucAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:10.099851Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.10542","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05faefffb4c03d594607de77e2b55994e59d660b6721ea8d08425f8a4e6888b9","sha256:4a1bb37f15e535d8269ce3e6fffe1b121489fe2247d6a5eb5efb8ea20f060923"],"state_sha256":"c7b331dfe73f28fb0cd95e34fa44c59b834ae90b75a40f9b1d3adb899d2e7099"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E2DJ6kg+aJuitrEoZ87Il2o7DoyrW5xeHNJxfce+BW6aZthF3GX24hFiwkgvlsMzwxFjTUcKdFsHvr+F/zoGDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T14:45:47.238499Z","bundle_sha256":"cda9a415481fd80663ee15f0fb64082285f199ae1c744542b79b8c9e912db0e3"}}