{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:244VCTSEIB7F2LXF35CBEA3QOI","short_pith_number":"pith:244VCTSE","schema_version":"1.0","canonical_sha256":"d739514e44407e5d2ee5df441203707226ab74075feec5c2a5d8054851b46c52","source":{"kind":"arxiv","id":"2306.07713","version":3},"attestation_state":"computed","paper":{"title":"Robustness of SAM: Segment Anything Under Corruptions and Beyond","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaoning Zhang, Chenshuang Zhang, Choong Seon Hong, Donghun Kim, Taegoo Kang, Yu Qiao","submitted_at":"2023-06-13T12:00:49Z","abstract_excerpt":"Segment anything model (SAM), as the name suggests, is claimed to be capable of cutting out any object and demonstrates impressive zero-shot transfer performance with the guidance of prompts. However, there is currently a lack of comprehensive evaluation regarding its robustness under various corruptions. Understanding the robustness of SAM across different corruption scenarios is crucial for its real-world deployment. Prior works show that SAM is biased towards texture (style) rather than shape, motivated by which we start by investigating its robustness against style transfer, which is synth"},"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":"2306.07713","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-13T12:00:49Z","cross_cats_sorted":[],"title_canon_sha256":"46901ec4e018834c49470f28cc98acac3a8a0a22f2ccf1b3b7b2ec7b97556f77","abstract_canon_sha256":"4d9588f1195c2be8e57fea01e92b2cc050b53fac06bd2f25dba04e50b60d1d16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:47:22.791219Z","signature_b64":"sFOFdcvaBRgDvdYu0xTeeH3gaUL0148NiNh+dRNE+LiN/IP1lO844b6Nvg2rEuIgowgs4/xOq4rEI1ACeunSAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d739514e44407e5d2ee5df441203707226ab74075feec5c2a5d8054851b46c52","last_reissued_at":"2026-07-05T06:47:22.790596Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:47:22.790596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robustness of SAM: Segment Anything Under Corruptions and Beyond","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaoning Zhang, Chenshuang Zhang, Choong Seon Hong, Donghun Kim, Taegoo Kang, Yu Qiao","submitted_at":"2023-06-13T12:00:49Z","abstract_excerpt":"Segment anything model (SAM), as the name suggests, is claimed to be capable of cutting out any object and demonstrates impressive zero-shot transfer performance with the guidance of prompts. However, there is currently a lack of comprehensive evaluation regarding its robustness under various corruptions. Understanding the robustness of SAM across different corruption scenarios is crucial for its real-world deployment. Prior works show that SAM is biased towards texture (style) rather than shape, motivated by which we start by investigating its robustness against style transfer, which is synth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07713","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/2306.07713/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":"2306.07713","created_at":"2026-07-05T06:47:22.790680+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.07713v3","created_at":"2026-07-05T06:47:22.790680+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07713","created_at":"2026-07-05T06:47:22.790680+00:00"},{"alias_kind":"pith_short_12","alias_value":"244VCTSEIB7F","created_at":"2026-07-05T06:47:22.790680+00:00"},{"alias_kind":"pith_short_16","alias_value":"244VCTSEIB7F2LXF","created_at":"2026-07-05T06:47:22.790680+00:00"},{"alias_kind":"pith_short_8","alias_value":"244VCTSE","created_at":"2026-07-05T06:47:22.790680+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30477","citing_title":"PGE-SAM: Prompt-Guided Feature Enhancement for Interactive Segmentation under Degradation","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25730","citing_title":"DeCoDrift: Stabilizing Decoder Coupling in Closed-Loop Foundation Segmentation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2503.12507","citing_title":"Segment Any-Quality Images with Generative Latent Space Enhancement","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2505.06907","citing_title":"A Survey on Foundation Models for Personalized Federated Intelligence","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2306.14289","citing_title":"Faster Segment Anything: Towards Lightweight SAM for Mobile Applications","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2601.02018","citing_title":"Towards Any-Quality Image Segmentation via Generative and Adaptive Latent Space Enhancement","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/244VCTSEIB7F2LXF35CBEA3QOI","json":"https://pith.science/pith/244VCTSEIB7F2LXF35CBEA3QOI.json","graph_json":"https://pith.science/api/pith-number/244VCTSEIB7F2LXF35CBEA3QOI/graph.json","events_json":"https://pith.science/api/pith-number/244VCTSEIB7F2LXF35CBEA3QOI/events.json","paper":"https://pith.science/paper/244VCTSE"},"agent_actions":{"view_html":"https://pith.science/pith/244VCTSEIB7F2LXF35CBEA3QOI","download_json":"https://pith.science/pith/244VCTSEIB7F2LXF35CBEA3QOI.json","view_paper":"https://pith.science/paper/244VCTSE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.07713&json=true","fetch_graph":"https://pith.science/api/pith-number/244VCTSEIB7F2LXF35CBEA3QOI/graph.json","fetch_events":"https://pith.science/api/pith-number/244VCTSEIB7F2LXF35CBEA3QOI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/244VCTSEIB7F2LXF35CBEA3QOI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/244VCTSEIB7F2LXF35CBEA3QOI/action/storage_attestation","attest_author":"https://pith.science/pith/244VCTSEIB7F2LXF35CBEA3QOI/action/author_attestation","sign_citation":"https://pith.science/pith/244VCTSEIB7F2LXF35CBEA3QOI/action/citation_signature","submit_replication":"https://pith.science/pith/244VCTSEIB7F2LXF35CBEA3QOI/action/replication_record"}},"created_at":"2026-07-05T06:47:22.790680+00:00","updated_at":"2026-07-05T06:47:22.790680+00:00"}