{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5OPU4SWS22EEWGEBF3TGLN3ZIS","short_pith_number":"pith:5OPU4SWS","schema_version":"1.0","canonical_sha256":"eb9f4e4ad2d6884b18812ee665b7794499500196d5ca93ab8eea35e8283158f5","source":{"kind":"arxiv","id":"2412.11998","version":1},"attestation_state":"computed","paper":{"title":"SAMIC: Segment Anything with In-Context Spatial Prompt Engineering","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaopeng Shen, Daniel Kifer, Kashif Rashid, Savinay Nagendra","submitted_at":"2024-12-16T17:26:06Z","abstract_excerpt":"Few-shot segmentation is the problem of learning to identify specific types of objects (e.g., airplanes) in images from a small set of labeled reference images. The current state of the art is driven by resource-intensive construction of models for every new domain-specific application. Such models must be trained on enormous labeled datasets of unrelated objects (e.g., cars, trains, animals) so that their ``knowledge'' can be transferred to new types of objects. In this paper, we show how to leverage existing vision foundation models (VFMs) to reduce the incremental cost of creating few-shot "},"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":"2412.11998","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-16T17:26:06Z","cross_cats_sorted":[],"title_canon_sha256":"dc7b1933819b46e52784a09a5f485d929f14e789d32f7aaf1113cc9436c44003","abstract_canon_sha256":"3403762b9fdb9fc48c3530b57122dfbb81447a80a8771937c87238c667ea39a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:55.278451Z","signature_b64":"RBsWiRQ6N/gzVlx1OO9p7bvGEtvz6m5Pg0GTlVMUBpazId02tZI10okHZeELq36wWFO1v9NuPHKfcaSnYgHWAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb9f4e4ad2d6884b18812ee665b7794499500196d5ca93ab8eea35e8283158f5","last_reissued_at":"2026-07-05T09:49:55.277917Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:55.277917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAMIC: Segment Anything with In-Context Spatial Prompt Engineering","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaopeng Shen, Daniel Kifer, Kashif Rashid, Savinay Nagendra","submitted_at":"2024-12-16T17:26:06Z","abstract_excerpt":"Few-shot segmentation is the problem of learning to identify specific types of objects (e.g., airplanes) in images from a small set of labeled reference images. The current state of the art is driven by resource-intensive construction of models for every new domain-specific application. Such models must be trained on enormous labeled datasets of unrelated objects (e.g., cars, trains, animals) so that their ``knowledge'' can be transferred to new types of objects. In this paper, we show how to leverage existing vision foundation models (VFMs) to reduce the incremental cost of creating few-shot "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11998","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/2412.11998/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":"2412.11998","created_at":"2026-07-05T09:49:55.277996+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.11998v1","created_at":"2026-07-05T09:49:55.277996+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11998","created_at":"2026-07-05T09:49:55.277996+00:00"},{"alias_kind":"pith_short_12","alias_value":"5OPU4SWS22EE","created_at":"2026-07-05T09:49:55.277996+00:00"},{"alias_kind":"pith_short_16","alias_value":"5OPU4SWS22EEWGEB","created_at":"2026-07-05T09:49:55.277996+00:00"},{"alias_kind":"pith_short_8","alias_value":"5OPU4SWS","created_at":"2026-07-05T09:49:55.277996+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09562","citing_title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","ref_index":50,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5OPU4SWS22EEWGEBF3TGLN3ZIS","json":"https://pith.science/pith/5OPU4SWS22EEWGEBF3TGLN3ZIS.json","graph_json":"https://pith.science/api/pith-number/5OPU4SWS22EEWGEBF3TGLN3ZIS/graph.json","events_json":"https://pith.science/api/pith-number/5OPU4SWS22EEWGEBF3TGLN3ZIS/events.json","paper":"https://pith.science/paper/5OPU4SWS"},"agent_actions":{"view_html":"https://pith.science/pith/5OPU4SWS22EEWGEBF3TGLN3ZIS","download_json":"https://pith.science/pith/5OPU4SWS22EEWGEBF3TGLN3ZIS.json","view_paper":"https://pith.science/paper/5OPU4SWS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.11998&json=true","fetch_graph":"https://pith.science/api/pith-number/5OPU4SWS22EEWGEBF3TGLN3ZIS/graph.json","fetch_events":"https://pith.science/api/pith-number/5OPU4SWS22EEWGEBF3TGLN3ZIS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5OPU4SWS22EEWGEBF3TGLN3ZIS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5OPU4SWS22EEWGEBF3TGLN3ZIS/action/storage_attestation","attest_author":"https://pith.science/pith/5OPU4SWS22EEWGEBF3TGLN3ZIS/action/author_attestation","sign_citation":"https://pith.science/pith/5OPU4SWS22EEWGEBF3TGLN3ZIS/action/citation_signature","submit_replication":"https://pith.science/pith/5OPU4SWS22EEWGEBF3TGLN3ZIS/action/replication_record"}},"created_at":"2026-07-05T09:49:55.277996+00:00","updated_at":"2026-07-05T09:49:55.277996+00:00"}