{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NQYQRNCIWMA2RDJ2DTV4QNWW5D","short_pith_number":"pith:NQYQRNCI","schema_version":"1.0","canonical_sha256":"6c3108b448b301a88d3a1cebc836d6e8e5e9b9ca0bd6796bcd4323dd4c0aad68","source":{"kind":"arxiv","id":"2306.01567","version":2},"attestation_state":"computed","paper":{"title":"Segment Anything in High Quality","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chi-Keung Tang, Fisher Yu, Lei Ke, Martin Danelljan, Mingqiao Ye, Yifan Liu, Yu-Wing Tai","submitted_at":"2023-06-02T14:23:59Z","abstract_excerpt":"The recent Segment Anything Model (SAM) represents a big leap in scaling up segmentation models, allowing for powerful zero-shot capabilities and flexible prompting. Despite being trained with 1.1 billion masks, SAM's mask prediction quality falls short in many cases, particularly when dealing with objects that have intricate structures. We propose HQ-SAM, equipping SAM with the ability to accurately segment any object, while maintaining SAM's original promptable design, efficiency, and zero-shot generalizability. Our careful design reuses and preserves the pre-trained model weights of SAM, wh"},"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":"2306.01567","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-02T14:23:59Z","cross_cats_sorted":[],"title_canon_sha256":"cc5f5db02b4187d88edc165fdcdffe3bfcab524919e3263a87f6ba4291dcce70","abstract_canon_sha256":"830d930d6256f5a28af731ccfa7fe5886be98099f563ada18102d925213cda8a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:59.595919Z","signature_b64":"a8ZU9uJ+SPgOtVdqVggFpZAe6reor61OTbm3hL4efqu3wXZx2UokIU1Z/2V2dlWoJu9m8coqWIZM8Tp7YsrhAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c3108b448b301a88d3a1cebc836d6e8e5e9b9ca0bd6796bcd4323dd4c0aad68","last_reissued_at":"2026-07-05T07:03:59.595364Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:59.595364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Segment Anything in High Quality","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chi-Keung Tang, Fisher Yu, Lei Ke, Martin Danelljan, Mingqiao Ye, Yifan Liu, Yu-Wing Tai","submitted_at":"2023-06-02T14:23:59Z","abstract_excerpt":"The recent Segment Anything Model (SAM) represents a big leap in scaling up segmentation models, allowing for powerful zero-shot capabilities and flexible prompting. Despite being trained with 1.1 billion masks, SAM's mask prediction quality falls short in many cases, particularly when dealing with objects that have intricate structures. We propose HQ-SAM, equipping SAM with the ability to accurately segment any object, while maintaining SAM's original promptable design, efficiency, and zero-shot generalizability. Our careful design reuses and preserves the pre-trained model weights of SAM, wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.01567","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/2306.01567/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":"2306.01567","created_at":"2026-07-05T07:03:59.595428+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.01567v2","created_at":"2026-07-05T07:03:59.595428+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.01567","created_at":"2026-07-05T07:03:59.595428+00:00"},{"alias_kind":"pith_short_12","alias_value":"NQYQRNCIWMA2","created_at":"2026-07-05T07:03:59.595428+00:00"},{"alias_kind":"pith_short_16","alias_value":"NQYQRNCIWMA2RDJ2","created_at":"2026-07-05T07:03:59.595428+00:00"},{"alias_kind":"pith_short_8","alias_value":"NQYQRNCI","created_at":"2026-07-05T07:03:59.595428+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10136","citing_title":"iSAGE: A Human-in-the-Loop Framework for Remote Sensing Semantic Segmentation via Sparse Point Supervision","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2511.16766","citing_title":"SVG360: Editable Multiview Vector Graphics from a Single SVG","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17633","citing_title":"SparseSAM: Structured Sparsification of Activations in Segment Anything Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2602.00821","citing_title":"Zero-Shot Generative De-identification: Inversion-Free Flow for Privacy-Preserving Skin Image Analysis","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2401.14159","citing_title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NQYQRNCIWMA2RDJ2DTV4QNWW5D","json":"https://pith.science/pith/NQYQRNCIWMA2RDJ2DTV4QNWW5D.json","graph_json":"https://pith.science/api/pith-number/NQYQRNCIWMA2RDJ2DTV4QNWW5D/graph.json","events_json":"https://pith.science/api/pith-number/NQYQRNCIWMA2RDJ2DTV4QNWW5D/events.json","paper":"https://pith.science/paper/NQYQRNCI"},"agent_actions":{"view_html":"https://pith.science/pith/NQYQRNCIWMA2RDJ2DTV4QNWW5D","download_json":"https://pith.science/pith/NQYQRNCIWMA2RDJ2DTV4QNWW5D.json","view_paper":"https://pith.science/paper/NQYQRNCI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.01567&json=true","fetch_graph":"https://pith.science/api/pith-number/NQYQRNCIWMA2RDJ2DTV4QNWW5D/graph.json","fetch_events":"https://pith.science/api/pith-number/NQYQRNCIWMA2RDJ2DTV4QNWW5D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NQYQRNCIWMA2RDJ2DTV4QNWW5D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NQYQRNCIWMA2RDJ2DTV4QNWW5D/action/storage_attestation","attest_author":"https://pith.science/pith/NQYQRNCIWMA2RDJ2DTV4QNWW5D/action/author_attestation","sign_citation":"https://pith.science/pith/NQYQRNCIWMA2RDJ2DTV4QNWW5D/action/citation_signature","submit_replication":"https://pith.science/pith/NQYQRNCIWMA2RDJ2DTV4QNWW5D/action/replication_record"}},"created_at":"2026-07-05T07:03:59.595428+00:00","updated_at":"2026-07-05T07:03:59.595428+00:00"}