{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VQFPYMTY4WGRVXXHEWI3HRQAC2","short_pith_number":"pith:VQFPYMTY","canonical_record":{"source":{"id":"2310.07704","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-11T17:55:15Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e0f7ae8a85a0a0fb3081cee3c416f47a53ccb17e4f03f15ee206de24cb7bc640","abstract_canon_sha256":"419cebae751a0f18a1d1ab104687a18f345ab96416311add427dc504104289dd"},"schema_version":"1.0"},"canonical_sha256":"ac0afc3278e58d1adee72591b3c6001694212189e5f52ccc1f05310c974c13ff","source":{"kind":"arxiv","id":"2310.07704","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.07704","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"arxiv_version","alias_value":"2310.07704v1","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07704","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"pith_short_12","alias_value":"VQFPYMTY4WGR","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"VQFPYMTY4WGRVXXH","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"VQFPYMTY","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VQFPYMTY4WGRVXXHEWI3HRQAC2","target":"record","payload":{"canonical_record":{"source":{"id":"2310.07704","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-11T17:55:15Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e0f7ae8a85a0a0fb3081cee3c416f47a53ccb17e4f03f15ee206de24cb7bc640","abstract_canon_sha256":"419cebae751a0f18a1d1ab104687a18f345ab96416311add427dc504104289dd"},"schema_version":"1.0"},"canonical_sha256":"ac0afc3278e58d1adee72591b3c6001694212189e5f52ccc1f05310c974c13ff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:52.676408Z","signature_b64":"KTAu5voOn/Exa9UjFyZ+wKHJxEuJSEFZh0/jDi4NtUjqvLnt9mZTELxxUxiCiYho85XyLgDpdJkfEon00/gnDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac0afc3278e58d1adee72591b3c6001694212189e5f52ccc1f05310c974c13ff","last_reissued_at":"2026-05-17T23:38:52.675730Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:52.675730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.07704","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"buS198Oy63WajRXUdgNLC/QjQjjaadqhxc3kZnIRzdlaXjq7zXeHwUEKcqSN7m2Iv85GHWr0hLsebwrd6+BIBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T03:05:03.615632Z"},"content_sha256":"1fe411054d166e9a18a048e2291087d37f66b7b6708d400d41c39f55d9f3c809","schema_version":"1.0","event_id":"sha256:1fe411054d166e9a18a048e2291087d37f66b7b6708d400d41c39f55d9f3c809"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VQFPYMTY4WGRVXXHEWI3HRQAC2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ferret: Refer and Ground Anything Anywhere at Any Granularity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Ferret unifies referring and grounding in multimodal LLMs via a hybrid region representation of coordinates and continuous features.","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Bowen Zhang, Haotian Zhang, Haoxuan You, Liangliang Cao, Shih-Fu Chang, Xianzhi Du, Yinfei Yang, Zhe Gan, Zirui Wang","submitted_at":"2023-10-11T17:55:15Z","abstract_excerpt":"We introduce Ferret, a new Multimodal Large Language Model (MLLM) capable of understanding spatial referring of any shape or granularity within an image and accurately grounding open-vocabulary descriptions. To unify referring and grounding in the LLM paradigm, Ferret employs a novel and powerful hybrid region representation that integrates discrete coordinates and continuous features jointly to represent a region in the image. To extract the continuous features of versatile regions, we propose a spatial-aware visual sampler, adept at handling varying sparsity across different shapes. Conseque"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The resulting model not only achieves superior performance in classical referring and grounding tasks, but also greatly outperforms existing MLLMs in region-based and localization-demanded multimodal chatting.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the spatial-aware visual sampler can reliably extract continuous features from regions of arbitrary shape and sparsity without introducing systematic bias or information loss that would affect downstream grounding accuracy.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Ferret introduces a hybrid region representation and the GRIT dataset to let MLLMs refer to and ground arbitrary image regions, outperforming prior models on referring, grounding, and localization-aware chatting while reducing object hallucination.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Ferret unifies referring and grounding in multimodal LLMs via a hybrid region representation of coordinates and continuous features.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"73a4e79f223b2e942c9dc25ab4e1a885e1134543daecb2348e8939682c1a03a5"},"source":{"id":"2310.07704","kind":"arxiv","version":1},"verdict":{"id":"657af406-82d9-4462-a844-036903d1320e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T11:24:46.089802Z","strongest_claim":"The resulting model not only achieves superior performance in classical referring and grounding tasks, but also greatly outperforms existing MLLMs in region-based and localization-demanded multimodal chatting.","one_line_summary":"Ferret introduces a hybrid region representation and the GRIT dataset to let MLLMs refer to and ground arbitrary image regions, outperforming prior models on referring, grounding, and localization-aware chatting while reducing object hallucination.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the spatial-aware visual sampler can reliably extract continuous features from regions of arbitrary shape and sparsity without introducing systematic bias or information loss that would affect downstream grounding accuracy.","pith_extraction_headline":"Ferret unifies referring and grounding in multimodal LLMs via a hybrid region representation of coordinates and continuous features."},"references":{"count":20,"sample":[{"doi":"","year":null,"title":"The length of the output list needs to be exactly equal to the input list","work_id":"5df37ad1-a803-4193-87c3-dab4bc212ed9","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Do not explain the reasons","work_id":"eff2168b-1779-4d8a-a995-c2290e9a4073","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Do not mention the input entities, at least the output name and input name needs to be different","work_id":"a08ad987-d7c3-4b1f-8e9d-7bc6fe9b579a","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Do not mention something abstract, like ¨alien¨","work_id":"c210e3f5-c95a-4540-a7cc-786189f56aac","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"When dealing with quantities, focus solely on increasing the numbers during revision","work_id":"b1ce2dc5-9cf0-4e5d-83d1-16bcf11a63cc","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":20,"snapshot_sha256":"a7ededc6035b60c8027ce87beee2e525dbb4657e9dec9803222aae38e0150bb4","internal_anchors":0},"formal_canon":{"evidence_count":1,"snapshot_sha256":"135267e8810624bb106e0dc58d9ed73e308a9c2616ed8a4aa8c0277ed3d57860"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"657af406-82d9-4462-a844-036903d1320e"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4cpHm25LbpmzoQYk/Qy8oQhQUaHSC2YIGxPMW0fX8HF/6M2ISQa6LenzdgMbnv2/bBgdbPqT4n/Ov4WKjFQ9BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T03:05:03.616186Z"},"content_sha256":"71030a040cc98db9e3425bf6aab1d5634e780e34796da1f7281547b4693089aa","schema_version":"1.0","event_id":"sha256:71030a040cc98db9e3425bf6aab1d5634e780e34796da1f7281547b4693089aa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VQFPYMTY4WGRVXXHEWI3HRQAC2/bundle.json","state_url":"https://pith.science/pith/VQFPYMTY4WGRVXXHEWI3HRQAC2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VQFPYMTY4WGRVXXHEWI3HRQAC2/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":"2026-05-28T03:05:03Z","links":{"resolver":"https://pith.science/pith/VQFPYMTY4WGRVXXHEWI3HRQAC2","bundle":"https://pith.science/pith/VQFPYMTY4WGRVXXHEWI3HRQAC2/bundle.json","state":"https://pith.science/pith/VQFPYMTY4WGRVXXHEWI3HRQAC2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VQFPYMTY4WGRVXXHEWI3HRQAC2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VQFPYMTY4WGRVXXHEWI3HRQAC2","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":"419cebae751a0f18a1d1ab104687a18f345ab96416311add427dc504104289dd","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-11T17:55:15Z","title_canon_sha256":"e0f7ae8a85a0a0fb3081cee3c416f47a53ccb17e4f03f15ee206de24cb7bc640"},"schema_version":"1.0","source":{"id":"2310.07704","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.07704","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"arxiv_version","alias_value":"2310.07704v1","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07704","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"pith_short_12","alias_value":"VQFPYMTY4WGR","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"VQFPYMTY4WGRVXXH","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"VQFPYMTY","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:71030a040cc98db9e3425bf6aab1d5634e780e34796da1f7281547b4693089aa","target":"graph","created_at":"2026-05-17T23:38:52Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"The resulting model not only achieves superior performance in classical referring and grounding tasks, but also greatly outperforms existing MLLMs in region-based and localization-demanded multimodal chatting."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the spatial-aware visual sampler can reliably extract continuous features from regions of arbitrary shape and sparsity without introducing systematic bias or information loss that would affect downstream grounding accuracy."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Ferret introduces a hybrid region representation and the GRIT dataset to let MLLMs refer to and ground arbitrary image regions, outperforming prior models on referring, grounding, and localization-aware chatting while reducing object hallucination."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Ferret unifies referring and grounding in multimodal LLMs via a hybrid region representation of coordinates and continuous features."}],"snapshot_sha256":"73a4e79f223b2e942c9dc25ab4e1a885e1134543daecb2348e8939682c1a03a5"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"135267e8810624bb106e0dc58d9ed73e308a9c2616ed8a4aa8c0277ed3d57860"},"paper":{"abstract_excerpt":"We introduce Ferret, a new Multimodal Large Language Model (MLLM) capable of understanding spatial referring of any shape or granularity within an image and accurately grounding open-vocabulary descriptions. To unify referring and grounding in the LLM paradigm, Ferret employs a novel and powerful hybrid region representation that integrates discrete coordinates and continuous features jointly to represent a region in the image. To extract the continuous features of versatile regions, we propose a spatial-aware visual sampler, adept at handling varying sparsity across different shapes. Conseque","authors_text":"Bowen Zhang, Haotian Zhang, Haoxuan You, Liangliang Cao, Shih-Fu Chang, Xianzhi Du, Yinfei Yang, Zhe Gan, Zirui Wang","cross_cats":["cs.CL"],"headline":"Ferret unifies referring and grounding in multimodal LLMs via a hybrid region representation of coordinates and continuous features.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-11T17:55:15Z","title":"Ferret: Refer and Ground Anything Anywhere at Any Granularity"},"references":{"count":20,"internal_anchors":0,"resolved_work":20,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"The length of the output list needs to be exactly equal to the input list","work_id":"5df37ad1-a803-4193-87c3-dab4bc212ed9","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Do not explain the reasons","work_id":"eff2168b-1779-4d8a-a995-c2290e9a4073","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Do not mention the input entities, at least the output name and input name needs to be different","work_id":"a08ad987-d7c3-4b1f-8e9d-7bc6fe9b579a","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Do not mention something abstract, like ¨alien¨","work_id":"c210e3f5-c95a-4540-a7cc-786189f56aac","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"When dealing with quantities, focus solely on increasing the numbers during revision","work_id":"b1ce2dc5-9cf0-4e5d-83d1-16bcf11a63cc","year":null}],"snapshot_sha256":"a7ededc6035b60c8027ce87beee2e525dbb4657e9dec9803222aae38e0150bb4"},"source":{"id":"2310.07704","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T11:24:46.089802Z","id":"657af406-82d9-4462-a844-036903d1320e","model_set":{"reader":"grok-4.3"},"one_line_summary":"Ferret introduces a hybrid region representation and the GRIT dataset to let MLLMs refer to and ground arbitrary image regions, outperforming prior models on referring, grounding, and localization-aware chatting while reducing object hallucination.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Ferret unifies referring and grounding in multimodal LLMs via a hybrid region representation of coordinates and continuous features.","strongest_claim":"The resulting model not only achieves superior performance in classical referring and grounding tasks, but also greatly outperforms existing MLLMs in region-based and localization-demanded multimodal chatting.","weakest_assumption":"That the spatial-aware visual sampler can reliably extract continuous features from regions of arbitrary shape and sparsity without introducing systematic bias or information loss that would affect downstream grounding accuracy."}},"verdict_id":"657af406-82d9-4462-a844-036903d1320e"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1fe411054d166e9a18a048e2291087d37f66b7b6708d400d41c39f55d9f3c809","target":"record","created_at":"2026-05-17T23:38:52Z","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":"419cebae751a0f18a1d1ab104687a18f345ab96416311add427dc504104289dd","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-11T17:55:15Z","title_canon_sha256":"e0f7ae8a85a0a0fb3081cee3c416f47a53ccb17e4f03f15ee206de24cb7bc640"},"schema_version":"1.0","source":{"id":"2310.07704","kind":"arxiv","version":1}},"canonical_sha256":"ac0afc3278e58d1adee72591b3c6001694212189e5f52ccc1f05310c974c13ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac0afc3278e58d1adee72591b3c6001694212189e5f52ccc1f05310c974c13ff","first_computed_at":"2026-05-17T23:38:52.675730Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:52.675730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KTAu5voOn/Exa9UjFyZ+wKHJxEuJSEFZh0/jDi4NtUjqvLnt9mZTELxxUxiCiYho85XyLgDpdJkfEon00/gnDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:52.676408Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.07704","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1fe411054d166e9a18a048e2291087d37f66b7b6708d400d41c39f55d9f3c809","sha256:71030a040cc98db9e3425bf6aab1d5634e780e34796da1f7281547b4693089aa"],"state_sha256":"d9fbd0b1de2ea4b5ebccb081c0cd17af16704773136df3f8213426feddb888f0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j6yD660IO5s56iqk3dQDkUf3xikHQwfKytVUar4uyA9j2Z7QXV0XnB63Djz5OnQ4fx8XefngCkd5Bk6O/JtsBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T03:05:03.618737Z","bundle_sha256":"6e1c9c0565bc65c0476be074db45b020b640dfc9e3e2f6e47f12508b8440cd94"}}