{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QPZGLIXP2HZPG7BYNZZGXLK6BE","short_pith_number":"pith:QPZGLIXP","schema_version":"1.0","canonical_sha256":"83f265a2efd1f2f37c386e726bad5e0909ce2066e39d168bd811c9d103578bf8","source":{"kind":"arxiv","id":"2401.02317","version":4},"attestation_state":"computed","paper":{"title":"BA-SAM: Scalable Bias-Mode Attention Mask for Segment Anything Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deng-Ping Fan, Lizhuang Ma, Qianyu Zhou, Xiangtai Li, Xuequan Lu, Yiran Song","submitted_at":"2024-01-04T15:34:44Z","abstract_excerpt":"In this paper, we address the challenge of image resolution variation for the Segment Anything Model (SAM). SAM, known for its zero-shot generalizability, exhibits a performance degradation when faced with datasets with varying image sizes. Previous approaches tend to resize the image to a fixed size or adopt structure modifications, hindering the preservation of SAM's rich prior knowledge. Besides, such task-specific tuning necessitates a complete retraining of the model, which is cost-expensive and unacceptable for deployment in the downstream tasks. In this paper, we reformulate this issue "},"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":"2401.02317","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-04T15:34:44Z","cross_cats_sorted":[],"title_canon_sha256":"187502ef9c68a456063909e687b71a51ea198559b1e9bb1dd140303b354c688c","abstract_canon_sha256":"5acc5f45cf2f311f401258360137923667255d7f648c9c07b18a11b810ebfee9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:58:26.175359Z","signature_b64":"D1+895MVAZMKNOYIolHTLGSm8uMumUIcgxs/jv/1NgMOaSUgizjRmqKUv8fN/CU9KcRkTX0JzHw+MYpqcd+lBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83f265a2efd1f2f37c386e726bad5e0909ce2066e39d168bd811c9d103578bf8","last_reissued_at":"2026-07-05T07:58:26.174828Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:58:26.174828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BA-SAM: Scalable Bias-Mode Attention Mask for Segment Anything Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deng-Ping Fan, Lizhuang Ma, Qianyu Zhou, Xiangtai Li, Xuequan Lu, Yiran Song","submitted_at":"2024-01-04T15:34:44Z","abstract_excerpt":"In this paper, we address the challenge of image resolution variation for the Segment Anything Model (SAM). SAM, known for its zero-shot generalizability, exhibits a performance degradation when faced with datasets with varying image sizes. Previous approaches tend to resize the image to a fixed size or adopt structure modifications, hindering the preservation of SAM's rich prior knowledge. Besides, such task-specific tuning necessitates a complete retraining of the model, which is cost-expensive and unacceptable for deployment in the downstream tasks. In this paper, we reformulate this issue "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02317","kind":"arxiv","version":4},"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/2401.02317/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":"2401.02317","created_at":"2026-07-05T07:58:26.174890+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.02317v4","created_at":"2026-07-05T07:58:26.174890+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02317","created_at":"2026-07-05T07:58:26.174890+00:00"},{"alias_kind":"pith_short_12","alias_value":"QPZGLIXP2HZP","created_at":"2026-07-05T07:58:26.174890+00:00"},{"alias_kind":"pith_short_16","alias_value":"QPZGLIXP2HZPG7BY","created_at":"2026-07-05T07:58:26.174890+00:00"},{"alias_kind":"pith_short_8","alias_value":"QPZGLIXP","created_at":"2026-07-05T07:58:26.174890+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/QPZGLIXP2HZPG7BYNZZGXLK6BE","json":"https://pith.science/pith/QPZGLIXP2HZPG7BYNZZGXLK6BE.json","graph_json":"https://pith.science/api/pith-number/QPZGLIXP2HZPG7BYNZZGXLK6BE/graph.json","events_json":"https://pith.science/api/pith-number/QPZGLIXP2HZPG7BYNZZGXLK6BE/events.json","paper":"https://pith.science/paper/QPZGLIXP"},"agent_actions":{"view_html":"https://pith.science/pith/QPZGLIXP2HZPG7BYNZZGXLK6BE","download_json":"https://pith.science/pith/QPZGLIXP2HZPG7BYNZZGXLK6BE.json","view_paper":"https://pith.science/paper/QPZGLIXP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.02317&json=true","fetch_graph":"https://pith.science/api/pith-number/QPZGLIXP2HZPG7BYNZZGXLK6BE/graph.json","fetch_events":"https://pith.science/api/pith-number/QPZGLIXP2HZPG7BYNZZGXLK6BE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QPZGLIXP2HZPG7BYNZZGXLK6BE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QPZGLIXP2HZPG7BYNZZGXLK6BE/action/storage_attestation","attest_author":"https://pith.science/pith/QPZGLIXP2HZPG7BYNZZGXLK6BE/action/author_attestation","sign_citation":"https://pith.science/pith/QPZGLIXP2HZPG7BYNZZGXLK6BE/action/citation_signature","submit_replication":"https://pith.science/pith/QPZGLIXP2HZPG7BYNZZGXLK6BE/action/replication_record"}},"created_at":"2026-07-05T07:58:26.174890+00:00","updated_at":"2026-07-05T07:58:26.174890+00:00"}