{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LPPWWKBH2LMSUSKQI3WPYYTMTT","short_pith_number":"pith:LPPWWKBH","schema_version":"1.0","canonical_sha256":"5bdf6b2827d2d92a495046ecfc626c9ce873c62549c9e94b01ea3c6459ea3395","source":{"kind":"arxiv","id":"2501.08504","version":1},"attestation_state":"computed","paper":{"title":"SuperSAM: Crafting a SAM Supernetwork via Structured Pruning and Unstructured Parameter Prioritization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Akash Dutta, Ali Jannesari, Jan Strube, Luanzheng Guo, Nathan R. Tallent, Pablo Munoz, Sadegh Jafari, Sixing Yu, Waqwoya Abebe","submitted_at":"2025-01-15T00:54:12Z","abstract_excerpt":"Neural Architecture Search (NAS) is a powerful approach of automating the design of efficient neural architectures. In contrast to traditional NAS methods, recently proposed one-shot NAS methods prove to be more efficient in performing NAS. One-shot NAS works by generating a singular weight-sharing supernetwork that acts as a search space (container) of subnetworks. Despite its achievements, designing the one-shot search space remains a major challenge. In this work we propose a search space design strategy for Vision Transformer (ViT)-based architectures. In particular, we convert the Segment"},"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":"2501.08504","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-15T00:54:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"26f00d747b2f7ad35b9bba1a229037eec24f7d1ba7b118559817e90a884608e9","abstract_canon_sha256":"1eaa597ae7a1b54182af8972cd3b11b3520b4073036784777ef97dda45d250c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:20.449225Z","signature_b64":"CyKVVDubRzJEZDnAxKPpMRZ/F/UUqtGpvF3b4VlSPfiuIrrUSENTxKvT+eqczzK4l+UiJQjzVwrp2jcE8NpMDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bdf6b2827d2d92a495046ecfc626c9ce873c62549c9e94b01ea3c6459ea3395","last_reissued_at":"2026-07-05T10:01:20.448880Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:20.448880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SuperSAM: Crafting a SAM Supernetwork via Structured Pruning and Unstructured Parameter Prioritization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Akash Dutta, Ali Jannesari, Jan Strube, Luanzheng Guo, Nathan R. Tallent, Pablo Munoz, Sadegh Jafari, Sixing Yu, Waqwoya Abebe","submitted_at":"2025-01-15T00:54:12Z","abstract_excerpt":"Neural Architecture Search (NAS) is a powerful approach of automating the design of efficient neural architectures. In contrast to traditional NAS methods, recently proposed one-shot NAS methods prove to be more efficient in performing NAS. One-shot NAS works by generating a singular weight-sharing supernetwork that acts as a search space (container) of subnetworks. Despite its achievements, designing the one-shot search space remains a major challenge. In this work we propose a search space design strategy for Vision Transformer (ViT)-based architectures. In particular, we convert the Segment"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.08504","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/2501.08504/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":"2501.08504","created_at":"2026-07-05T10:01:20.448934+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.08504v1","created_at":"2026-07-05T10:01:20.448934+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.08504","created_at":"2026-07-05T10:01:20.448934+00:00"},{"alias_kind":"pith_short_12","alias_value":"LPPWWKBH2LMS","created_at":"2026-07-05T10:01:20.448934+00:00"},{"alias_kind":"pith_short_16","alias_value":"LPPWWKBH2LMSUSKQ","created_at":"2026-07-05T10:01:20.448934+00:00"},{"alias_kind":"pith_short_8","alias_value":"LPPWWKBH","created_at":"2026-07-05T10:01:20.448934+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.04960","citing_title":"On Efficient Variants of Segment Anything Model: A Survey","ref_index":153,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LPPWWKBH2LMSUSKQI3WPYYTMTT","json":"https://pith.science/pith/LPPWWKBH2LMSUSKQI3WPYYTMTT.json","graph_json":"https://pith.science/api/pith-number/LPPWWKBH2LMSUSKQI3WPYYTMTT/graph.json","events_json":"https://pith.science/api/pith-number/LPPWWKBH2LMSUSKQI3WPYYTMTT/events.json","paper":"https://pith.science/paper/LPPWWKBH"},"agent_actions":{"view_html":"https://pith.science/pith/LPPWWKBH2LMSUSKQI3WPYYTMTT","download_json":"https://pith.science/pith/LPPWWKBH2LMSUSKQI3WPYYTMTT.json","view_paper":"https://pith.science/paper/LPPWWKBH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.08504&json=true","fetch_graph":"https://pith.science/api/pith-number/LPPWWKBH2LMSUSKQI3WPYYTMTT/graph.json","fetch_events":"https://pith.science/api/pith-number/LPPWWKBH2LMSUSKQI3WPYYTMTT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LPPWWKBH2LMSUSKQI3WPYYTMTT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LPPWWKBH2LMSUSKQI3WPYYTMTT/action/storage_attestation","attest_author":"https://pith.science/pith/LPPWWKBH2LMSUSKQI3WPYYTMTT/action/author_attestation","sign_citation":"https://pith.science/pith/LPPWWKBH2LMSUSKQI3WPYYTMTT/action/citation_signature","submit_replication":"https://pith.science/pith/LPPWWKBH2LMSUSKQI3WPYYTMTT/action/replication_record"}},"created_at":"2026-07-05T10:01:20.448934+00:00","updated_at":"2026-07-05T10:01:20.448934+00:00"}