{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FET3DHOI3CGPSD6KP5Y6JU4PGS","short_pith_number":"pith:FET3DHOI","schema_version":"1.0","canonical_sha256":"2927b19dc8d88cf90fca7f71e4d38f34a095b35a00cbba40ca4a900ee9597188","source":{"kind":"arxiv","id":"2505.17994","version":1},"attestation_state":"computed","paper":{"title":"Segment Anyword: Mask Prompt Inversion for Open-Set Grounded Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amrutha Saseendran, Chen Jin, Dino Oglic, Fariba Yousefi, Huiyu Zhou, Lei Tong, Nikolay Burlutskiy, Philip Teare, Tom Diethe, Xilin He, Zhihua Liu","submitted_at":"2025-05-23T14:59:44Z","abstract_excerpt":"Open-set image segmentation poses a significant challenge because existing methods often demand extensive training or fine-tuning and generally struggle to segment unified objects consistently across diverse text reference expressions. Motivated by this, we propose Segment Anyword, a novel training-free visual concept prompt learning approach for open-set language grounded segmentation that relies on token-level cross-attention maps from a frozen diffusion model to produce segmentation surrogates or mask prompts, which are then refined into targeted object masks. Initial prompts typically lack"},"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":"2505.17994","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-23T14:59:44Z","cross_cats_sorted":[],"title_canon_sha256":"f938cfb7d6f63d78cfc472bd105c329a7e9fc4d4ea4f504b27e162d8589f3261","abstract_canon_sha256":"026863666ec0867a49b91ef359d2a1306f5a4136dc7f99f836065599e5e43a06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:34.958823Z","signature_b64":"FPGe0Shep4mklA7bvR3tnAwpxPMZ/pSiQdquCHfWBVhp3CUbqwKPBbQjhIPrgcy/hiCodyT5oASGpUtyEeZhBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2927b19dc8d88cf90fca7f71e4d38f34a095b35a00cbba40ca4a900ee9597188","last_reissued_at":"2026-07-05T11:08:34.958336Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:34.958336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Segment Anyword: Mask Prompt Inversion for Open-Set Grounded Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amrutha Saseendran, Chen Jin, Dino Oglic, Fariba Yousefi, Huiyu Zhou, Lei Tong, Nikolay Burlutskiy, Philip Teare, Tom Diethe, Xilin He, Zhihua Liu","submitted_at":"2025-05-23T14:59:44Z","abstract_excerpt":"Open-set image segmentation poses a significant challenge because existing methods often demand extensive training or fine-tuning and generally struggle to segment unified objects consistently across diverse text reference expressions. Motivated by this, we propose Segment Anyword, a novel training-free visual concept prompt learning approach for open-set language grounded segmentation that relies on token-level cross-attention maps from a frozen diffusion model to produce segmentation surrogates or mask prompts, which are then refined into targeted object masks. Initial prompts typically lack"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17994","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/2505.17994/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":"2505.17994","created_at":"2026-07-05T11:08:34.958398+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.17994v1","created_at":"2026-07-05T11:08:34.958398+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17994","created_at":"2026-07-05T11:08:34.958398+00:00"},{"alias_kind":"pith_short_12","alias_value":"FET3DHOI3CGP","created_at":"2026-07-05T11:08:34.958398+00:00"},{"alias_kind":"pith_short_16","alias_value":"FET3DHOI3CGPSD6K","created_at":"2026-07-05T11:08:34.958398+00:00"},{"alias_kind":"pith_short_8","alias_value":"FET3DHOI","created_at":"2026-07-05T11:08:34.958398+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/FET3DHOI3CGPSD6KP5Y6JU4PGS","json":"https://pith.science/pith/FET3DHOI3CGPSD6KP5Y6JU4PGS.json","graph_json":"https://pith.science/api/pith-number/FET3DHOI3CGPSD6KP5Y6JU4PGS/graph.json","events_json":"https://pith.science/api/pith-number/FET3DHOI3CGPSD6KP5Y6JU4PGS/events.json","paper":"https://pith.science/paper/FET3DHOI"},"agent_actions":{"view_html":"https://pith.science/pith/FET3DHOI3CGPSD6KP5Y6JU4PGS","download_json":"https://pith.science/pith/FET3DHOI3CGPSD6KP5Y6JU4PGS.json","view_paper":"https://pith.science/paper/FET3DHOI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.17994&json=true","fetch_graph":"https://pith.science/api/pith-number/FET3DHOI3CGPSD6KP5Y6JU4PGS/graph.json","fetch_events":"https://pith.science/api/pith-number/FET3DHOI3CGPSD6KP5Y6JU4PGS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FET3DHOI3CGPSD6KP5Y6JU4PGS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FET3DHOI3CGPSD6KP5Y6JU4PGS/action/storage_attestation","attest_author":"https://pith.science/pith/FET3DHOI3CGPSD6KP5Y6JU4PGS/action/author_attestation","sign_citation":"https://pith.science/pith/FET3DHOI3CGPSD6KP5Y6JU4PGS/action/citation_signature","submit_replication":"https://pith.science/pith/FET3DHOI3CGPSD6KP5Y6JU4PGS/action/replication_record"}},"created_at":"2026-07-05T11:08:34.958398+00:00","updated_at":"2026-07-05T11:08:34.958398+00:00"}