{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UMGYXDTQXM6Z7EH5WCBSHBAX4V","short_pith_number":"pith:UMGYXDTQ","schema_version":"1.0","canonical_sha256":"a30d8b8e70bb3d9f90fdb083238417e57072a4de6b4bac0de1f682d3ea936234","source":{"kind":"arxiv","id":"2409.12255","version":1},"attestation_state":"computed","paper":{"title":"Efficient Data Subset Selection to Generalize Training Across Models: Transductive and Inductive Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Abir De, Ashish Tendulkar, Eeshaan Jain, Gaurav Aggarwal, Rishabh Iyer, Tushar Nandy","submitted_at":"2024-09-18T18:32:12Z","abstract_excerpt":"Existing subset selection methods for efficient learning predominantly employ discrete combinatorial and model-specific approaches which lack generalizability. For an unseen architecture, one cannot use the subset chosen for a different model. To tackle this problem, we propose $\\texttt{SubSelNet}$, a trainable subset selection framework, that generalizes across architectures. Here, we first introduce an attention-based neural gadget that leverages the graph structure of architectures and acts as a surrogate to trained deep neural networks for quick model prediction. Then, we use these predict"},"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":"2409.12255","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-18T18:32:12Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2cd66bb0f973124806938e6c3e2cac867650c70b5f5969c5a2231d85b2d6dfa4","abstract_canon_sha256":"9976abeb3af359f1c7226374b1cdf8c1bb59be2e81f72779eb3aa99a6ab03b20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:08:50.774082Z","signature_b64":"1iDXJ7cdUmzRbE8BU60E/Xsd86Dkj/LVys1qJomNnoBX5+rHxe0dL4sLuYTpTWZYeMD3MwbFrUpkHOJPihhmBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a30d8b8e70bb3d9f90fdb083238417e57072a4de6b4bac0de1f682d3ea936234","last_reissued_at":"2026-07-05T09:08:50.773546Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:08:50.773546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Data Subset Selection to Generalize Training Across Models: Transductive and Inductive Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Abir De, Ashish Tendulkar, Eeshaan Jain, Gaurav Aggarwal, Rishabh Iyer, Tushar Nandy","submitted_at":"2024-09-18T18:32:12Z","abstract_excerpt":"Existing subset selection methods for efficient learning predominantly employ discrete combinatorial and model-specific approaches which lack generalizability. For an unseen architecture, one cannot use the subset chosen for a different model. To tackle this problem, we propose $\\texttt{SubSelNet}$, a trainable subset selection framework, that generalizes across architectures. Here, we first introduce an attention-based neural gadget that leverages the graph structure of architectures and acts as a surrogate to trained deep neural networks for quick model prediction. Then, we use these predict"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.12255","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/2409.12255/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":"2409.12255","created_at":"2026-07-05T09:08:50.773605+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.12255v1","created_at":"2026-07-05T09:08:50.773605+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.12255","created_at":"2026-07-05T09:08:50.773605+00:00"},{"alias_kind":"pith_short_12","alias_value":"UMGYXDTQXM6Z","created_at":"2026-07-05T09:08:50.773605+00:00"},{"alias_kind":"pith_short_16","alias_value":"UMGYXDTQXM6Z7EH5","created_at":"2026-07-05T09:08:50.773605+00:00"},{"alias_kind":"pith_short_8","alias_value":"UMGYXDTQ","created_at":"2026-07-05T09:08:50.773605+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.21003","citing_title":"InSQuAD: In-Context Learning for Efficient Retrieval via Submodular Mutual Information to Enforce Quality and Diversity","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UMGYXDTQXM6Z7EH5WCBSHBAX4V","json":"https://pith.science/pith/UMGYXDTQXM6Z7EH5WCBSHBAX4V.json","graph_json":"https://pith.science/api/pith-number/UMGYXDTQXM6Z7EH5WCBSHBAX4V/graph.json","events_json":"https://pith.science/api/pith-number/UMGYXDTQXM6Z7EH5WCBSHBAX4V/events.json","paper":"https://pith.science/paper/UMGYXDTQ"},"agent_actions":{"view_html":"https://pith.science/pith/UMGYXDTQXM6Z7EH5WCBSHBAX4V","download_json":"https://pith.science/pith/UMGYXDTQXM6Z7EH5WCBSHBAX4V.json","view_paper":"https://pith.science/paper/UMGYXDTQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.12255&json=true","fetch_graph":"https://pith.science/api/pith-number/UMGYXDTQXM6Z7EH5WCBSHBAX4V/graph.json","fetch_events":"https://pith.science/api/pith-number/UMGYXDTQXM6Z7EH5WCBSHBAX4V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UMGYXDTQXM6Z7EH5WCBSHBAX4V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UMGYXDTQXM6Z7EH5WCBSHBAX4V/action/storage_attestation","attest_author":"https://pith.science/pith/UMGYXDTQXM6Z7EH5WCBSHBAX4V/action/author_attestation","sign_citation":"https://pith.science/pith/UMGYXDTQXM6Z7EH5WCBSHBAX4V/action/citation_signature","submit_replication":"https://pith.science/pith/UMGYXDTQXM6Z7EH5WCBSHBAX4V/action/replication_record"}},"created_at":"2026-07-05T09:08:50.773605+00:00","updated_at":"2026-07-05T09:08:50.773605+00:00"}