{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BLDETY3LINEGPE6YOSDGYLUC67","short_pith_number":"pith:BLDETY3L","schema_version":"1.0","canonical_sha256":"0ac649e36b43486793d874866c2e82f7c19026d55b2c349199357ef416cc5a13","source":{"kind":"arxiv","id":"2401.04651","version":1},"attestation_state":"computed","paper":{"title":"Learning to Prompt Segment Anything Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eric Xing, Han Qiu, Jiaxing Huang, Jingyi Zhang, Kai Jiang, Lewei Lu, Shijian Lu","submitted_at":"2024-01-09T16:24:25Z","abstract_excerpt":"Segment Anything Models (SAMs) like SEEM and SAM have demonstrated great potential in learning to segment anything. The core design of SAMs lies with Promptable Segmentation, which takes a handcrafted prompt as input and returns the expected segmentation mask. SAMs work with two types of prompts including spatial prompts (e.g., points) and semantic prompts (e.g., texts), which work together to prompt SAMs to segment anything on downstream datasets. Despite the important role of prompts, how to acquire suitable prompts for SAMs is largely under-explored. In this work, we examine the architectur"},"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":"2401.04651","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-09T16:24:25Z","cross_cats_sorted":[],"title_canon_sha256":"1eaecaeec45cb1daef19d85731c9a3654fc0d224a8cf8d61e4ee88809ceaeb4a","abstract_canon_sha256":"e69caba9f4682c5d0b5cf9c138b10644a11e08aa9fe27fe6425d240a76667b86"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:31:48.631384Z","signature_b64":"+jSXyqMzm7LhAsgjyao0VDRMy0IaNxavw3MzPlzZPcKAg9qrdamDTkIfoSuuBvhRxYg929fhtsIVdYdviGIPAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ac649e36b43486793d874866c2e82f7c19026d55b2c349199357ef416cc5a13","last_reissued_at":"2026-07-05T07:31:48.630981Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:31:48.630981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Prompt Segment Anything Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eric Xing, Han Qiu, Jiaxing Huang, Jingyi Zhang, Kai Jiang, Lewei Lu, Shijian Lu","submitted_at":"2024-01-09T16:24:25Z","abstract_excerpt":"Segment Anything Models (SAMs) like SEEM and SAM have demonstrated great potential in learning to segment anything. The core design of SAMs lies with Promptable Segmentation, which takes a handcrafted prompt as input and returns the expected segmentation mask. SAMs work with two types of prompts including spatial prompts (e.g., points) and semantic prompts (e.g., texts), which work together to prompt SAMs to segment anything on downstream datasets. Despite the important role of prompts, how to acquire suitable prompts for SAMs is largely under-explored. In this work, we examine the architectur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.04651","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/2401.04651/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":"2401.04651","created_at":"2026-07-05T07:31:48.631037+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.04651v1","created_at":"2026-07-05T07:31:48.631037+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.04651","created_at":"2026-07-05T07:31:48.631037+00:00"},{"alias_kind":"pith_short_12","alias_value":"BLDETY3LINEG","created_at":"2026-07-05T07:31:48.631037+00:00"},{"alias_kind":"pith_short_16","alias_value":"BLDETY3LINEGPE6Y","created_at":"2026-07-05T07:31:48.631037+00:00"},{"alias_kind":"pith_short_8","alias_value":"BLDETY3L","created_at":"2026-07-05T07:31:48.631037+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04705","citing_title":"Enhancing MedSAM with a Lightweight Box Predictor for Medical Image Segmentation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23314","citing_title":"Learning from Noisy Prompts: Saliency-Guided Prompt Distillation for Robust Segmentation with SAM","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05433","citing_title":"Few-Shot Semantic Segmentation Meets SAM3","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BLDETY3LINEGPE6YOSDGYLUC67","json":"https://pith.science/pith/BLDETY3LINEGPE6YOSDGYLUC67.json","graph_json":"https://pith.science/api/pith-number/BLDETY3LINEGPE6YOSDGYLUC67/graph.json","events_json":"https://pith.science/api/pith-number/BLDETY3LINEGPE6YOSDGYLUC67/events.json","paper":"https://pith.science/paper/BLDETY3L"},"agent_actions":{"view_html":"https://pith.science/pith/BLDETY3LINEGPE6YOSDGYLUC67","download_json":"https://pith.science/pith/BLDETY3LINEGPE6YOSDGYLUC67.json","view_paper":"https://pith.science/paper/BLDETY3L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.04651&json=true","fetch_graph":"https://pith.science/api/pith-number/BLDETY3LINEGPE6YOSDGYLUC67/graph.json","fetch_events":"https://pith.science/api/pith-number/BLDETY3LINEGPE6YOSDGYLUC67/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BLDETY3LINEGPE6YOSDGYLUC67/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BLDETY3LINEGPE6YOSDGYLUC67/action/storage_attestation","attest_author":"https://pith.science/pith/BLDETY3LINEGPE6YOSDGYLUC67/action/author_attestation","sign_citation":"https://pith.science/pith/BLDETY3LINEGPE6YOSDGYLUC67/action/citation_signature","submit_replication":"https://pith.science/pith/BLDETY3LINEGPE6YOSDGYLUC67/action/replication_record"}},"created_at":"2026-07-05T07:31:48.631037+00:00","updated_at":"2026-07-05T07:31:48.631037+00:00"}