{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:K2ZMGRBXM7LJXMFYD5KSVH6KP6","short_pith_number":"pith:K2ZMGRBX","schema_version":"1.0","canonical_sha256":"56b2c3443767d69bb0b81f552a9fca7faa99290ebfa2f6379fcf7fb62c71b397","source":{"kind":"arxiv","id":"2312.02420","version":3},"attestation_state":"computed","paper":{"title":"Repurposing SAM for User-Defined Semantics Aware Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amit K. Roy-Chowdhury, Arindam Dutta, Rohit Kundu, Sudipta Paul","submitted_at":"2023-12-05T01:37:18Z","abstract_excerpt":"The Segment Anything Model (SAM) excels at generating precise object masks from input prompts but lacks semantic awareness, failing to associate its generated masks with specific object categories. To address this limitation, we propose U-SAM, a novel framework that imbibes semantic awareness into SAM, enabling it to generate targeted masks for user-specified object categories. Given only object class names as input from the user, U-SAM provides pixel-level semantic annotations for images without requiring any labeled/unlabeled samples from the test data distribution. Our approach leverages sy"},"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":"2312.02420","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-05T01:37:18Z","cross_cats_sorted":[],"title_canon_sha256":"022b1c9c38d169e457a9660c3681120fc0ccf1b37c18790eb34c9409b90cf050","abstract_canon_sha256":"70c327b8f91caf411fb2ec0202fb8dd14f6a25545c501d14c30d62c2ff3465d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:03:42.029223Z","signature_b64":"MjgjAK9hUQCIL3IumOxIpvG1q6En/d+fc7NlJw/AfPDWZSArF872OnD3MLJE1GzROkND0d2mF1h6v8AZ+rg7DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56b2c3443767d69bb0b81f552a9fca7faa99290ebfa2f6379fcf7fb62c71b397","last_reissued_at":"2026-07-05T12:03:42.028690Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:03:42.028690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Repurposing SAM for User-Defined Semantics Aware Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amit K. Roy-Chowdhury, Arindam Dutta, Rohit Kundu, Sudipta Paul","submitted_at":"2023-12-05T01:37:18Z","abstract_excerpt":"The Segment Anything Model (SAM) excels at generating precise object masks from input prompts but lacks semantic awareness, failing to associate its generated masks with specific object categories. To address this limitation, we propose U-SAM, a novel framework that imbibes semantic awareness into SAM, enabling it to generate targeted masks for user-specified object categories. Given only object class names as input from the user, U-SAM provides pixel-level semantic annotations for images without requiring any labeled/unlabeled samples from the test data distribution. Our approach leverages sy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.02420","kind":"arxiv","version":3},"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/2312.02420/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":"2312.02420","created_at":"2026-07-05T12:03:42.028747+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.02420v3","created_at":"2026-07-05T12:03:42.028747+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.02420","created_at":"2026-07-05T12:03:42.028747+00:00"},{"alias_kind":"pith_short_12","alias_value":"K2ZMGRBXM7LJ","created_at":"2026-07-05T12:03:42.028747+00:00"},{"alias_kind":"pith_short_16","alias_value":"K2ZMGRBXM7LJXMFY","created_at":"2026-07-05T12:03:42.028747+00:00"},{"alias_kind":"pith_short_8","alias_value":"K2ZMGRBX","created_at":"2026-07-05T12:03:42.028747+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/K2ZMGRBXM7LJXMFYD5KSVH6KP6","json":"https://pith.science/pith/K2ZMGRBXM7LJXMFYD5KSVH6KP6.json","graph_json":"https://pith.science/api/pith-number/K2ZMGRBXM7LJXMFYD5KSVH6KP6/graph.json","events_json":"https://pith.science/api/pith-number/K2ZMGRBXM7LJXMFYD5KSVH6KP6/events.json","paper":"https://pith.science/paper/K2ZMGRBX"},"agent_actions":{"view_html":"https://pith.science/pith/K2ZMGRBXM7LJXMFYD5KSVH6KP6","download_json":"https://pith.science/pith/K2ZMGRBXM7LJXMFYD5KSVH6KP6.json","view_paper":"https://pith.science/paper/K2ZMGRBX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.02420&json=true","fetch_graph":"https://pith.science/api/pith-number/K2ZMGRBXM7LJXMFYD5KSVH6KP6/graph.json","fetch_events":"https://pith.science/api/pith-number/K2ZMGRBXM7LJXMFYD5KSVH6KP6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K2ZMGRBXM7LJXMFYD5KSVH6KP6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K2ZMGRBXM7LJXMFYD5KSVH6KP6/action/storage_attestation","attest_author":"https://pith.science/pith/K2ZMGRBXM7LJXMFYD5KSVH6KP6/action/author_attestation","sign_citation":"https://pith.science/pith/K2ZMGRBXM7LJXMFYD5KSVH6KP6/action/citation_signature","submit_replication":"https://pith.science/pith/K2ZMGRBXM7LJXMFYD5KSVH6KP6/action/replication_record"}},"created_at":"2026-07-05T12:03:42.028747+00:00","updated_at":"2026-07-05T12:03:42.028747+00:00"}