{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VMIF77K6LYJRK74BMJGIGI27K4","short_pith_number":"pith:VMIF77K6","schema_version":"1.0","canonical_sha256":"ab105ffd5e5e13157f81624c83235f573fc38d98b18ac2387ea4c0784d90b6af","source":{"kind":"arxiv","id":"2412.19917","version":1},"attestation_state":"computed","paper":{"title":"Char-SAM: Turning Segment Anything Model into Scene Text Segmentation Annotator with Character-level Visual Prompts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daiqing Wu, Enze Xie, Huawen Shen, Jiaho Lyu, Yu Zhou","submitted_at":"2024-12-27T20:33:39Z","abstract_excerpt":"The recent emergence of the Segment Anything Model (SAM) enables various domain-specific segmentation tasks to be tackled cost-effectively by using bounding boxes as prompts. However, in scene text segmentation, SAM can not achieve desirable performance. The word-level bounding box as prompts is too coarse for characters, while the character-level bounding box as prompts suffers from over-segmentation and under-segmentation issues. In this paper, we propose an automatic annotation pipeline named Char-SAM, that turns SAM into a low-cost segmentation annotator with a Character-level visual promp"},"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":"2412.19917","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-27T20:33:39Z","cross_cats_sorted":[],"title_canon_sha256":"c344f077c04ea448415488421715e9ba82c9ad25d2a58571b4c744bda0428e80","abstract_canon_sha256":"6d80d9a2f6f14393294041567c12d3a2a27da86fcf00f622d2080844b8f75f3b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:51.767474Z","signature_b64":"+jtKwmE2qL09En9TFQkJwmGBqQaLF1rK9kIGahGBl86pFXYDzyB+fhToQUaXVgDlfjUxzGZl7Ck1HeP8foVzDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab105ffd5e5e13157f81624c83235f573fc38d98b18ac2387ea4c0784d90b6af","last_reissued_at":"2026-07-05T09:54:51.766992Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:51.766992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Char-SAM: Turning Segment Anything Model into Scene Text Segmentation Annotator with Character-level Visual Prompts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daiqing Wu, Enze Xie, Huawen Shen, Jiaho Lyu, Yu Zhou","submitted_at":"2024-12-27T20:33:39Z","abstract_excerpt":"The recent emergence of the Segment Anything Model (SAM) enables various domain-specific segmentation tasks to be tackled cost-effectively by using bounding boxes as prompts. However, in scene text segmentation, SAM can not achieve desirable performance. The word-level bounding box as prompts is too coarse for characters, while the character-level bounding box as prompts suffers from over-segmentation and under-segmentation issues. In this paper, we propose an automatic annotation pipeline named Char-SAM, that turns SAM into a low-cost segmentation annotator with a Character-level visual promp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19917","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/2412.19917/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":"2412.19917","created_at":"2026-07-05T09:54:51.767048+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.19917v1","created_at":"2026-07-05T09:54:51.767048+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19917","created_at":"2026-07-05T09:54:51.767048+00:00"},{"alias_kind":"pith_short_12","alias_value":"VMIF77K6LYJR","created_at":"2026-07-05T09:54:51.767048+00:00"},{"alias_kind":"pith_short_16","alias_value":"VMIF77K6LYJRK74B","created_at":"2026-07-05T09:54:51.767048+00:00"},{"alias_kind":"pith_short_8","alias_value":"VMIF77K6","created_at":"2026-07-05T09:54:51.767048+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":72,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VMIF77K6LYJRK74BMJGIGI27K4","json":"https://pith.science/pith/VMIF77K6LYJRK74BMJGIGI27K4.json","graph_json":"https://pith.science/api/pith-number/VMIF77K6LYJRK74BMJGIGI27K4/graph.json","events_json":"https://pith.science/api/pith-number/VMIF77K6LYJRK74BMJGIGI27K4/events.json","paper":"https://pith.science/paper/VMIF77K6"},"agent_actions":{"view_html":"https://pith.science/pith/VMIF77K6LYJRK74BMJGIGI27K4","download_json":"https://pith.science/pith/VMIF77K6LYJRK74BMJGIGI27K4.json","view_paper":"https://pith.science/paper/VMIF77K6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.19917&json=true","fetch_graph":"https://pith.science/api/pith-number/VMIF77K6LYJRK74BMJGIGI27K4/graph.json","fetch_events":"https://pith.science/api/pith-number/VMIF77K6LYJRK74BMJGIGI27K4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VMIF77K6LYJRK74BMJGIGI27K4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VMIF77K6LYJRK74BMJGIGI27K4/action/storage_attestation","attest_author":"https://pith.science/pith/VMIF77K6LYJRK74BMJGIGI27K4/action/author_attestation","sign_citation":"https://pith.science/pith/VMIF77K6LYJRK74BMJGIGI27K4/action/citation_signature","submit_replication":"https://pith.science/pith/VMIF77K6LYJRK74BMJGIGI27K4/action/replication_record"}},"created_at":"2026-07-05T09:54:51.767048+00:00","updated_at":"2026-07-05T09:54:51.767048+00:00"}