{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CWYPIYBOTV64UXP5NRMVIU372F","short_pith_number":"pith:CWYPIYBO","schema_version":"1.0","canonical_sha256":"15b0f4602e9d7dca5dfd6c5954537fd17fa64e571fc3e7120394ab7a4089965e","source":{"kind":"arxiv","id":"2502.00719","version":1},"attestation_state":"computed","paper":{"title":"Vision and Language Reference Prompt into SAM for Few-shot Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kosuke Sakurai, Masayuki Goto, Ryotaro Shimizu","submitted_at":"2025-02-02T08:40:14Z","abstract_excerpt":"Segment Anything Model (SAM) represents a large-scale segmentation model that enables powerful zero-shot capabilities with flexible prompts. While SAM can segment any object in zero-shot, it requires user-provided prompts for each target image and does not attach any label information to masks. Few-shot segmentation models addressed these issues by inputting annotated reference images as prompts to SAM and can segment specific objects in target images without user-provided prompts. Previous SAM-based few-shot segmentation models only use annotated reference images as prompts, resulting in limi"},"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":"2502.00719","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-02T08:40:14Z","cross_cats_sorted":[],"title_canon_sha256":"1328628627c4d57933d8057f8e4bac96044fcab6c89bd45808985bf3092d327c","abstract_canon_sha256":"c8fa8957294894df429e064126ee6c740ea89a0b86b5881cf4c575a593715f26"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:37.662458Z","signature_b64":"tend12hRurLlrOCetjYEgCK4bVv2MUxDIa4Dgg6/vlkOf0OuSNy8mIcOoQIuA/ul2q2SmadBL/O3ibu/sI4+DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15b0f4602e9d7dca5dfd6c5954537fd17fa64e571fc3e7120394ab7a4089965e","last_reissued_at":"2026-07-05T10:08:37.661952Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:37.661952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vision and Language Reference Prompt into SAM for Few-shot Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kosuke Sakurai, Masayuki Goto, Ryotaro Shimizu","submitted_at":"2025-02-02T08:40:14Z","abstract_excerpt":"Segment Anything Model (SAM) represents a large-scale segmentation model that enables powerful zero-shot capabilities with flexible prompts. While SAM can segment any object in zero-shot, it requires user-provided prompts for each target image and does not attach any label information to masks. Few-shot segmentation models addressed these issues by inputting annotated reference images as prompts to SAM and can segment specific objects in target images without user-provided prompts. Previous SAM-based few-shot segmentation models only use annotated reference images as prompts, resulting in limi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00719","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/2502.00719/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":"2502.00719","created_at":"2026-07-05T10:08:37.662011+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.00719v1","created_at":"2026-07-05T10:08:37.662011+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00719","created_at":"2026-07-05T10:08:37.662011+00:00"},{"alias_kind":"pith_short_12","alias_value":"CWYPIYBOTV64","created_at":"2026-07-05T10:08:37.662011+00:00"},{"alias_kind":"pith_short_16","alias_value":"CWYPIYBOTV64UXP5","created_at":"2026-07-05T10:08:37.662011+00:00"},{"alias_kind":"pith_short_8","alias_value":"CWYPIYBO","created_at":"2026-07-05T10:08:37.662011+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28920","citing_title":"ExACT: Exemplar-Driven Calibrated Refinement for Training-Free Visual Grounding in Remote Sensing Images","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2511.20886","citing_title":"V$^{2}$-SAM: Marrying SAM2 with Multi-Prompt Experts for Cross-View Object Correspondence","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CWYPIYBOTV64UXP5NRMVIU372F","json":"https://pith.science/pith/CWYPIYBOTV64UXP5NRMVIU372F.json","graph_json":"https://pith.science/api/pith-number/CWYPIYBOTV64UXP5NRMVIU372F/graph.json","events_json":"https://pith.science/api/pith-number/CWYPIYBOTV64UXP5NRMVIU372F/events.json","paper":"https://pith.science/paper/CWYPIYBO"},"agent_actions":{"view_html":"https://pith.science/pith/CWYPIYBOTV64UXP5NRMVIU372F","download_json":"https://pith.science/pith/CWYPIYBOTV64UXP5NRMVIU372F.json","view_paper":"https://pith.science/paper/CWYPIYBO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.00719&json=true","fetch_graph":"https://pith.science/api/pith-number/CWYPIYBOTV64UXP5NRMVIU372F/graph.json","fetch_events":"https://pith.science/api/pith-number/CWYPIYBOTV64UXP5NRMVIU372F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CWYPIYBOTV64UXP5NRMVIU372F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CWYPIYBOTV64UXP5NRMVIU372F/action/storage_attestation","attest_author":"https://pith.science/pith/CWYPIYBOTV64UXP5NRMVIU372F/action/author_attestation","sign_citation":"https://pith.science/pith/CWYPIYBOTV64UXP5NRMVIU372F/action/citation_signature","submit_replication":"https://pith.science/pith/CWYPIYBOTV64UXP5NRMVIU372F/action/replication_record"}},"created_at":"2026-07-05T10:08:37.662011+00:00","updated_at":"2026-07-05T10:08:37.662011+00:00"}