{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MOJO63DB4GDBHQP6G2WTTEIA6I","short_pith_number":"pith:MOJO63DB","schema_version":"1.0","canonical_sha256":"6392ef6c61e18613c1fe36ad399100f227aa2adc5957ba4b349a1119b27dca89","source":{"kind":"arxiv","id":"2505.18291","version":1},"attestation_state":"computed","paper":{"title":"InstructPart: Task-Oriented Part Segmentation with Instruction Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.RO"],"primary_cat":"cs.CV","authors_text":"Ce Zhang, Deva Ramanan, Katia Sycara, Simon Stepputtis, Yaqi Xie, Zhiqiu Lin, Zifu Wan, Zihan Wang","submitted_at":"2025-05-23T18:36:13Z","abstract_excerpt":"Large multimodal foundation models, particularly in the domains of language and vision, have significantly advanced various tasks, including robotics, autonomous driving, information retrieval, and grounding. However, many of these models perceive objects as indivisible, overlooking the components that constitute them. Understanding these components and their associated affordances provides valuable insights into an object's functionality, which is fundamental for performing a wide range of tasks. In this work, we introduce a novel real-world benchmark, InstructPart, comprising hand-labeled pa"},"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":"2505.18291","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-23T18:36:13Z","cross_cats_sorted":["cs.CL","cs.RO"],"title_canon_sha256":"c95c90af8c4989d7c5cca0cee98f65918380516f3687d50142638d24c516b506","abstract_canon_sha256":"1757a5c9df8d363d2dbd1f9e6f0dc3e2e1e22d8a159c78d2aad4d80c41ffd3dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:09.784214Z","signature_b64":"gGsY4YGuwzHcOC/6uHEt6ABlxwKysRO5yGTeOIM5jgYSWyQkaK8QPUmfZuqXclUlVLjVJpK+OHQRUrDxhoIiAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6392ef6c61e18613c1fe36ad399100f227aa2adc5957ba4b349a1119b27dca89","last_reissued_at":"2026-07-05T11:10:09.783730Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:09.783730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InstructPart: Task-Oriented Part Segmentation with Instruction Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.RO"],"primary_cat":"cs.CV","authors_text":"Ce Zhang, Deva Ramanan, Katia Sycara, Simon Stepputtis, Yaqi Xie, Zhiqiu Lin, Zifu Wan, Zihan Wang","submitted_at":"2025-05-23T18:36:13Z","abstract_excerpt":"Large multimodal foundation models, particularly in the domains of language and vision, have significantly advanced various tasks, including robotics, autonomous driving, information retrieval, and grounding. However, many of these models perceive objects as indivisible, overlooking the components that constitute them. Understanding these components and their associated affordances provides valuable insights into an object's functionality, which is fundamental for performing a wide range of tasks. In this work, we introduce a novel real-world benchmark, InstructPart, comprising hand-labeled pa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18291","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/2505.18291/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":"2505.18291","created_at":"2026-07-05T11:10:09.783784+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.18291v1","created_at":"2026-07-05T11:10:09.783784+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18291","created_at":"2026-07-05T11:10:09.783784+00:00"},{"alias_kind":"pith_short_12","alias_value":"MOJO63DB4GDB","created_at":"2026-07-05T11:10:09.783784+00:00"},{"alias_kind":"pith_short_16","alias_value":"MOJO63DB4GDBHQP6","created_at":"2026-07-05T11:10:09.783784+00:00"},{"alias_kind":"pith_short_8","alias_value":"MOJO63DB","created_at":"2026-07-05T11:10:09.783784+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27596","citing_title":"Dismantling Pathological Shortcuts: A Causal Framework for Faithful LVLM Decoding","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00663","citing_title":"Affordance Agent Harness: Verification-Gated Skill Orchestration","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00663","citing_title":"Affordance Agent Harness: Verification-Gated Skill Orchestration","ref_index":66,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MOJO63DB4GDBHQP6G2WTTEIA6I","json":"https://pith.science/pith/MOJO63DB4GDBHQP6G2WTTEIA6I.json","graph_json":"https://pith.science/api/pith-number/MOJO63DB4GDBHQP6G2WTTEIA6I/graph.json","events_json":"https://pith.science/api/pith-number/MOJO63DB4GDBHQP6G2WTTEIA6I/events.json","paper":"https://pith.science/paper/MOJO63DB"},"agent_actions":{"view_html":"https://pith.science/pith/MOJO63DB4GDBHQP6G2WTTEIA6I","download_json":"https://pith.science/pith/MOJO63DB4GDBHQP6G2WTTEIA6I.json","view_paper":"https://pith.science/paper/MOJO63DB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.18291&json=true","fetch_graph":"https://pith.science/api/pith-number/MOJO63DB4GDBHQP6G2WTTEIA6I/graph.json","fetch_events":"https://pith.science/api/pith-number/MOJO63DB4GDBHQP6G2WTTEIA6I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MOJO63DB4GDBHQP6G2WTTEIA6I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MOJO63DB4GDBHQP6G2WTTEIA6I/action/storage_attestation","attest_author":"https://pith.science/pith/MOJO63DB4GDBHQP6G2WTTEIA6I/action/author_attestation","sign_citation":"https://pith.science/pith/MOJO63DB4GDBHQP6G2WTTEIA6I/action/citation_signature","submit_replication":"https://pith.science/pith/MOJO63DB4GDBHQP6G2WTTEIA6I/action/replication_record"}},"created_at":"2026-07-05T11:10:09.783784+00:00","updated_at":"2026-07-05T11:10:09.783784+00:00"}