{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EOFF5EODNXKEW32MBAHWUIWDQJ","short_pith_number":"pith:EOFF5EOD","schema_version":"1.0","canonical_sha256":"238a5e91c36dd44b6f4c080f6a22c38270377e4c5e5b36c1c4853cc259a9512b","source":{"kind":"arxiv","id":"2312.05284","version":4},"attestation_state":"computed","paper":{"title":"SlimSAM: 0.1% Data Makes Segment Anything Slim","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gongfan Fang, Xinchao Wang, Xinyin Ma, Zigeng Chen","submitted_at":"2023-12-08T12:48:53Z","abstract_excerpt":"Current approaches for compressing the Segment Anything Model (SAM) yield commendable results, yet necessitate extensive data to train a new network from scratch. Employing conventional pruning techniques can remarkably reduce data requirements but would suffer from a degradation in performance. To address this challenging trade-off, we introduce SlimSAM, a novel data-efficient SAM compression method that achieves superior performance with extremely less training data. The essence of SlimSAM is encapsulated in the alternate slimming framework which effectively enhances knowledge inheritance un"},"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":"2312.05284","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-08T12:48:53Z","cross_cats_sorted":[],"title_canon_sha256":"7c0241877d18316ec8296af01f99a0c1588b7bb2e2cbb9a6c64b3491495ed898","abstract_canon_sha256":"e62a3fc7a4cf649c4dbb09edb5cd6058cad128b547049607ee891b5e2f6a293a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:12:01.593453Z","signature_b64":"mv1cfGvA2MARNg8N0GuYo38g1n3ezOxkJDh/iMh+AEYjx5evoODUNi2Na02pmFC2vI80+yQuIb8gwwgT1jdgBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"238a5e91c36dd44b6f4c080f6a22c38270377e4c5e5b36c1c4853cc259a9512b","last_reissued_at":"2026-07-05T09:12:01.592946Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:12:01.592946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SlimSAM: 0.1% Data Makes Segment Anything Slim","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gongfan Fang, Xinchao Wang, Xinyin Ma, Zigeng Chen","submitted_at":"2023-12-08T12:48:53Z","abstract_excerpt":"Current approaches for compressing the Segment Anything Model (SAM) yield commendable results, yet necessitate extensive data to train a new network from scratch. Employing conventional pruning techniques can remarkably reduce data requirements but would suffer from a degradation in performance. To address this challenging trade-off, we introduce SlimSAM, a novel data-efficient SAM compression method that achieves superior performance with extremely less training data. The essence of SlimSAM is encapsulated in the alternate slimming framework which effectively enhances knowledge inheritance un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.05284","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/2312.05284/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":"2312.05284","created_at":"2026-07-05T09:12:01.593008+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.05284v4","created_at":"2026-07-05T09:12:01.593008+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.05284","created_at":"2026-07-05T09:12:01.593008+00:00"},{"alias_kind":"pith_short_12","alias_value":"EOFF5EODNXKE","created_at":"2026-07-05T09:12:01.593008+00:00"},{"alias_kind":"pith_short_16","alias_value":"EOFF5EODNXKEW32M","created_at":"2026-07-05T09:12:01.593008+00:00"},{"alias_kind":"pith_short_8","alias_value":"EOFF5EOD","created_at":"2026-07-05T09:12:01.593008+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25324","citing_title":"Efficient Remote Sensing Instance Segmentation with Linear-Time State Space Distilled Visual Foundation Models","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EOFF5EODNXKEW32MBAHWUIWDQJ","json":"https://pith.science/pith/EOFF5EODNXKEW32MBAHWUIWDQJ.json","graph_json":"https://pith.science/api/pith-number/EOFF5EODNXKEW32MBAHWUIWDQJ/graph.json","events_json":"https://pith.science/api/pith-number/EOFF5EODNXKEW32MBAHWUIWDQJ/events.json","paper":"https://pith.science/paper/EOFF5EOD"},"agent_actions":{"view_html":"https://pith.science/pith/EOFF5EODNXKEW32MBAHWUIWDQJ","download_json":"https://pith.science/pith/EOFF5EODNXKEW32MBAHWUIWDQJ.json","view_paper":"https://pith.science/paper/EOFF5EOD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.05284&json=true","fetch_graph":"https://pith.science/api/pith-number/EOFF5EODNXKEW32MBAHWUIWDQJ/graph.json","fetch_events":"https://pith.science/api/pith-number/EOFF5EODNXKEW32MBAHWUIWDQJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EOFF5EODNXKEW32MBAHWUIWDQJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EOFF5EODNXKEW32MBAHWUIWDQJ/action/storage_attestation","attest_author":"https://pith.science/pith/EOFF5EODNXKEW32MBAHWUIWDQJ/action/author_attestation","sign_citation":"https://pith.science/pith/EOFF5EODNXKEW32MBAHWUIWDQJ/action/citation_signature","submit_replication":"https://pith.science/pith/EOFF5EODNXKEW32MBAHWUIWDQJ/action/replication_record"}},"created_at":"2026-07-05T09:12:01.593008+00:00","updated_at":"2026-07-05T09:12:01.593008+00:00"}