{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5LZTRYZWMQUOZEAA7UQLN5PEET","short_pith_number":"pith:5LZTRYZW","schema_version":"1.0","canonical_sha256":"eaf338e3366428ec9000fd20b6f5e424e6cb1eab485b983b4cc358e34a11d4da","source":{"kind":"arxiv","id":"2503.10596","version":3},"attestation_state":"computed","paper":{"title":"GroundingSuite: Measuring Complex Multi-Granular Pixel Grounding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Heng Liu, Lei Liu, Lianghui Zhu, Longjin Ran, Rui Hu, Tianheng Cheng, Wenyu Liu, Xiaoxin Chen, Xinggang Wang, Yuxuan Zhang","submitted_at":"2025-03-13T17:43:10Z","abstract_excerpt":"Pixel grounding, encompassing tasks such as Referring Expression Segmentation (RES), has garnered considerable attention due to its immense potential for bridging the gap between vision and language modalities. However, advancements in this domain are currently constrained by limitations inherent in existing datasets, including limited object categories, insufficient textual diversity, and a scarcity of high-quality annotations. To mitigate these limitations, we introduce GroundingSuite, which comprises: (1) an automated data annotation framework leveraging multiple Vision-Language Model (VLM)"},"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":"2503.10596","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-13T17:43:10Z","cross_cats_sorted":[],"title_canon_sha256":"6c3aabc7fd75226309af0ba17d1f6f18a7a7edaccd998eda7d22dc8d3f131d26","abstract_canon_sha256":"8b784c171f8c3b109c54b85dbedd453d2170b49e6c4bf5b38f50d4a107683870"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:16.937523Z","signature_b64":"Zq1SY2dIAvnxN6jU4qBExM3C9PbBrSk1bmDnyKfLgbVPvdxp+bMEVXgBKZTesa0bMV1LEfDfR+dDyWppifY8CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eaf338e3366428ec9000fd20b6f5e424e6cb1eab485b983b4cc358e34a11d4da","last_reissued_at":"2026-07-05T11:37:16.936974Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:16.936974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GroundingSuite: Measuring Complex Multi-Granular Pixel Grounding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Heng Liu, Lei Liu, Lianghui Zhu, Longjin Ran, Rui Hu, Tianheng Cheng, Wenyu Liu, Xiaoxin Chen, Xinggang Wang, Yuxuan Zhang","submitted_at":"2025-03-13T17:43:10Z","abstract_excerpt":"Pixel grounding, encompassing tasks such as Referring Expression Segmentation (RES), has garnered considerable attention due to its immense potential for bridging the gap between vision and language modalities. However, advancements in this domain are currently constrained by limitations inherent in existing datasets, including limited object categories, insufficient textual diversity, and a scarcity of high-quality annotations. To mitigate these limitations, we introduce GroundingSuite, which comprises: (1) an automated data annotation framework leveraging multiple Vision-Language Model (VLM)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10596","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/2503.10596/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":"2503.10596","created_at":"2026-07-05T11:37:16.937041+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.10596v3","created_at":"2026-07-05T11:37:16.937041+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10596","created_at":"2026-07-05T11:37:16.937041+00:00"},{"alias_kind":"pith_short_12","alias_value":"5LZTRYZWMQUO","created_at":"2026-07-05T11:37:16.937041+00:00"},{"alias_kind":"pith_short_16","alias_value":"5LZTRYZWMQUOZEAA","created_at":"2026-07-05T11:37:16.937041+00:00"},{"alias_kind":"pith_short_8","alias_value":"5LZTRYZW","created_at":"2026-07-05T11:37:16.937041+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26102","citing_title":"InstructSAM: Segment Any Instance with Any Instructions","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5LZTRYZWMQUOZEAA7UQLN5PEET","json":"https://pith.science/pith/5LZTRYZWMQUOZEAA7UQLN5PEET.json","graph_json":"https://pith.science/api/pith-number/5LZTRYZWMQUOZEAA7UQLN5PEET/graph.json","events_json":"https://pith.science/api/pith-number/5LZTRYZWMQUOZEAA7UQLN5PEET/events.json","paper":"https://pith.science/paper/5LZTRYZW"},"agent_actions":{"view_html":"https://pith.science/pith/5LZTRYZWMQUOZEAA7UQLN5PEET","download_json":"https://pith.science/pith/5LZTRYZWMQUOZEAA7UQLN5PEET.json","view_paper":"https://pith.science/paper/5LZTRYZW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.10596&json=true","fetch_graph":"https://pith.science/api/pith-number/5LZTRYZWMQUOZEAA7UQLN5PEET/graph.json","fetch_events":"https://pith.science/api/pith-number/5LZTRYZWMQUOZEAA7UQLN5PEET/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5LZTRYZWMQUOZEAA7UQLN5PEET/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5LZTRYZWMQUOZEAA7UQLN5PEET/action/storage_attestation","attest_author":"https://pith.science/pith/5LZTRYZWMQUOZEAA7UQLN5PEET/action/author_attestation","sign_citation":"https://pith.science/pith/5LZTRYZWMQUOZEAA7UQLN5PEET/action/citation_signature","submit_replication":"https://pith.science/pith/5LZTRYZWMQUOZEAA7UQLN5PEET/action/replication_record"}},"created_at":"2026-07-05T11:37:16.937041+00:00","updated_at":"2026-07-05T11:37:16.937041+00:00"}