{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:K4HYQCHNGMLWQUDH66CU77IHRV","short_pith_number":"pith:K4HYQCHN","schema_version":"1.0","canonical_sha256":"570f8808ed3317685067f7854ffd078d64f7cde8bc3b65843bde634fc985badd","source":{"kind":"arxiv","id":"2504.07942","version":2},"attestation_state":"computed","paper":{"title":"MARS: a Multimodal Alignment and Ranking System for Few-Shot Segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Matteo Matteucci, Nico Catalano, Paolo Pertino, Stefano Samele","submitted_at":"2025-04-10T17:53:23Z","abstract_excerpt":"Few Shot Segmentation aims to segment novel object classes given only a handful of labeled examples, enabling rapid adaptation with minimal supervision. Current literature crucially lacks a selection method that goes beyond visual similarity between the query and example images, leading to suboptimal predictions. We present MARS, a plug-and-play ranking system that leverages multimodal cues to filter and merge mask proposals robustly. Starting from a set of mask predictions for a single query image, we score, filter, and merge them to improve results. Proposals are evaluated using multimodal s"},"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":"2504.07942","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-10T17:53:23Z","cross_cats_sorted":[],"title_canon_sha256":"5ca8bced92fb0895c22cf45bc2cf7eaeb8ffe39e48d9d65761794c581121e362","abstract_canon_sha256":"2514d323f8932c8c4a4a1623b814fc6df43309e2445ffb5cacd1375061c91e01"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:33.899758Z","signature_b64":"MwBykjwDgrEgvBSHp7Yftu0ZicbV9svMrafXhPPn6PKdIcVqN0yaF64ynlRazC/trEsuAiV0oYbLQeEAJCcbAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"570f8808ed3317685067f7854ffd078d64f7cde8bc3b65843bde634fc985badd","last_reissued_at":"2026-07-05T11:40:33.899255Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:33.899255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MARS: a Multimodal Alignment and Ranking System for Few-Shot Segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Matteo Matteucci, Nico Catalano, Paolo Pertino, Stefano Samele","submitted_at":"2025-04-10T17:53:23Z","abstract_excerpt":"Few Shot Segmentation aims to segment novel object classes given only a handful of labeled examples, enabling rapid adaptation with minimal supervision. Current literature crucially lacks a selection method that goes beyond visual similarity between the query and example images, leading to suboptimal predictions. We present MARS, a plug-and-play ranking system that leverages multimodal cues to filter and merge mask proposals robustly. Starting from a set of mask predictions for a single query image, we score, filter, and merge them to improve results. Proposals are evaluated using multimodal s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07942","kind":"arxiv","version":2},"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/2504.07942/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":"2504.07942","created_at":"2026-07-05T11:40:33.899325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.07942v2","created_at":"2026-07-05T11:40:33.899325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07942","created_at":"2026-07-05T11:40:33.899325+00:00"},{"alias_kind":"pith_short_12","alias_value":"K4HYQCHNGMLW","created_at":"2026-07-05T11:40:33.899325+00:00"},{"alias_kind":"pith_short_16","alias_value":"K4HYQCHNGMLWQUDH","created_at":"2026-07-05T11:40:33.899325+00:00"},{"alias_kind":"pith_short_8","alias_value":"K4HYQCHN","created_at":"2026-07-05T11:40:33.899325+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.18831","citing_title":"Enhancing LLMs' Reasoning-Intensive Multimedia Search Capabilities through Fine-Tuning and Reinforcement Learning","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K4HYQCHNGMLWQUDH66CU77IHRV","json":"https://pith.science/pith/K4HYQCHNGMLWQUDH66CU77IHRV.json","graph_json":"https://pith.science/api/pith-number/K4HYQCHNGMLWQUDH66CU77IHRV/graph.json","events_json":"https://pith.science/api/pith-number/K4HYQCHNGMLWQUDH66CU77IHRV/events.json","paper":"https://pith.science/paper/K4HYQCHN"},"agent_actions":{"view_html":"https://pith.science/pith/K4HYQCHNGMLWQUDH66CU77IHRV","download_json":"https://pith.science/pith/K4HYQCHNGMLWQUDH66CU77IHRV.json","view_paper":"https://pith.science/paper/K4HYQCHN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.07942&json=true","fetch_graph":"https://pith.science/api/pith-number/K4HYQCHNGMLWQUDH66CU77IHRV/graph.json","fetch_events":"https://pith.science/api/pith-number/K4HYQCHNGMLWQUDH66CU77IHRV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K4HYQCHNGMLWQUDH66CU77IHRV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K4HYQCHNGMLWQUDH66CU77IHRV/action/storage_attestation","attest_author":"https://pith.science/pith/K4HYQCHNGMLWQUDH66CU77IHRV/action/author_attestation","sign_citation":"https://pith.science/pith/K4HYQCHNGMLWQUDH66CU77IHRV/action/citation_signature","submit_replication":"https://pith.science/pith/K4HYQCHNGMLWQUDH66CU77IHRV/action/replication_record"}},"created_at":"2026-07-05T11:40:33.899325+00:00","updated_at":"2026-07-05T11:40:33.899325+00:00"}