{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AVDLC3GH2KEQ7KNE7Q6FBQOMQE","short_pith_number":"pith:AVDLC3GH","schema_version":"1.0","canonical_sha256":"0546b16cc7d2890fa9a4fc3c50c1cc81339b2bd553235e64352150a5306ff286","source":{"kind":"arxiv","id":"2605.26102","version":1},"attestation_state":"computed","paper":{"title":"InstructSAM: Segment Any Instance with Any Instructions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Juncheng Li, Jun Xiao, Siliang Tang, Wenqiao Zhang, Wentong Li, Yueting Zhuang, Yuqian Yuan, Yutong Lin, Zhaocheng Li","submitted_at":"2026-05-25T17:58:03Z","abstract_excerpt":"In this paper, we introduce InstructSAM, a unified and streamlined framework designed for multi-instance segmentation under arbitrary instructions. We formulates instruction-driven instance segmentation as a set-structured query prediction problem and propose an explicit reasoning-to-instance query interface that elegantly bridges a vision-language model (VLM) and SAM3. Specifically, a bank of learnable instance queries is injected into the VLM and contextualized with instruction and visual information, enabling each query to serve as an instance-aware slot. A hybrid-attention mechanism furthe"},"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":"2605.26102","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T17:58:03Z","cross_cats_sorted":[],"title_canon_sha256":"801732804fc50c84dc9f06d2eb1f76733d722dbce43d4fd45aceccd4def833ac","abstract_canon_sha256":"6ec9f71c8394e17e54dbfbbc7748586bc35cc3f662fe040547f1b2bc18598e2b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:05:27.553510Z","signature_b64":"qNN2PVq31sQSQjdgE5/rA4h8IK0TktG+WKvTrIJaUT1jzDq3GaNBm8UMbfdEDFhmsCmFJYW7tnA0OrPt1UWgAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0546b16cc7d2890fa9a4fc3c50c1cc81339b2bd553235e64352150a5306ff286","last_reissued_at":"2026-05-26T02:05:27.552779Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:05:27.552779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InstructSAM: Segment Any Instance with Any Instructions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Juncheng Li, Jun Xiao, Siliang Tang, Wenqiao Zhang, Wentong Li, Yueting Zhuang, Yuqian Yuan, Yutong Lin, Zhaocheng Li","submitted_at":"2026-05-25T17:58:03Z","abstract_excerpt":"In this paper, we introduce InstructSAM, a unified and streamlined framework designed for multi-instance segmentation under arbitrary instructions. We formulates instruction-driven instance segmentation as a set-structured query prediction problem and propose an explicit reasoning-to-instance query interface that elegantly bridges a vision-language model (VLM) and SAM3. Specifically, a bank of learnable instance queries is injected into the VLM and contextualized with instruction and visual information, enabling each query to serve as an instance-aware slot. A hybrid-attention mechanism furthe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26102","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/2605.26102/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":"2605.26102","created_at":"2026-05-26T02:05:27.552902+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.26102v1","created_at":"2026-05-26T02:05:27.552902+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26102","created_at":"2026-05-26T02:05:27.552902+00:00"},{"alias_kind":"pith_short_12","alias_value":"AVDLC3GH2KEQ","created_at":"2026-05-26T02:05:27.552902+00:00"},{"alias_kind":"pith_short_16","alias_value":"AVDLC3GH2KEQ7KNE","created_at":"2026-05-26T02:05:27.552902+00:00"},{"alias_kind":"pith_short_8","alias_value":"AVDLC3GH","created_at":"2026-05-26T02:05:27.552902+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AVDLC3GH2KEQ7KNE7Q6FBQOMQE","json":"https://pith.science/pith/AVDLC3GH2KEQ7KNE7Q6FBQOMQE.json","graph_json":"https://pith.science/api/pith-number/AVDLC3GH2KEQ7KNE7Q6FBQOMQE/graph.json","events_json":"https://pith.science/api/pith-number/AVDLC3GH2KEQ7KNE7Q6FBQOMQE/events.json","paper":"https://pith.science/paper/AVDLC3GH"},"agent_actions":{"view_html":"https://pith.science/pith/AVDLC3GH2KEQ7KNE7Q6FBQOMQE","download_json":"https://pith.science/pith/AVDLC3GH2KEQ7KNE7Q6FBQOMQE.json","view_paper":"https://pith.science/paper/AVDLC3GH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.26102&json=true","fetch_graph":"https://pith.science/api/pith-number/AVDLC3GH2KEQ7KNE7Q6FBQOMQE/graph.json","fetch_events":"https://pith.science/api/pith-number/AVDLC3GH2KEQ7KNE7Q6FBQOMQE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AVDLC3GH2KEQ7KNE7Q6FBQOMQE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AVDLC3GH2KEQ7KNE7Q6FBQOMQE/action/storage_attestation","attest_author":"https://pith.science/pith/AVDLC3GH2KEQ7KNE7Q6FBQOMQE/action/author_attestation","sign_citation":"https://pith.science/pith/AVDLC3GH2KEQ7KNE7Q6FBQOMQE/action/citation_signature","submit_replication":"https://pith.science/pith/AVDLC3GH2KEQ7KNE7Q6FBQOMQE/action/replication_record"}},"created_at":"2026-05-26T02:05:27.552902+00:00","updated_at":"2026-05-26T02:05:27.552902+00:00"}