{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:L6V3ZHDZ6WHBLC4LNTUM2T3H4E","short_pith_number":"pith:L6V3ZHDZ","schema_version":"1.0","canonical_sha256":"5fabbc9c79f58e158b8b6ce8cd4f67e10e26f13be9725ee2185b82b195f8da5f","source":{"kind":"arxiv","id":"2403.08199","version":3},"attestation_state":"computed","paper":{"title":"Deep Submodular Peripteral Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Arnav Das, Gantavya Bhatt, Jeff Bilmes","submitted_at":"2024-03-13T02:53:52Z","abstract_excerpt":"Submodular functions, crucial for various applications, often lack practical learning methods for their acquisition. Seemingly unrelated, learning a scaling from oracles offering graded pairwise preferences (GPC) is underexplored, despite a rich history in psychometrics. In this paper, we introduce deep submodular peripteral networks (DSPNs), a novel parametric family of submodular functions, and methods for their training using a GPC-based strategy to connect and then tackle both of the above challenges. We introduce newly devised GPC-style ``peripteral'' loss which leverages numerically grad"},"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":"2403.08199","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-13T02:53:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cf7cac45448c22cef374f7950b9ded32098e16536fc55066e3eda1987fb420bf","abstract_canon_sha256":"af09d766d1de068f1261d1114b04d5ddce0a9ca8185656c349a65939363524d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:26.975444Z","signature_b64":"97ZppomhjXWz63NWrEsxfRPiXlXm2FWn9XeNWadSb2bieBeFZjCwNOnW3FIp+4a5Y6aARX0OOibuxR2aQ5a2Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fabbc9c79f58e158b8b6ce8cd4f67e10e26f13be9725ee2185b82b195f8da5f","last_reissued_at":"2026-07-05T09:29:26.974865Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:26.974865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Submodular Peripteral Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Arnav Das, Gantavya Bhatt, Jeff Bilmes","submitted_at":"2024-03-13T02:53:52Z","abstract_excerpt":"Submodular functions, crucial for various applications, often lack practical learning methods for their acquisition. Seemingly unrelated, learning a scaling from oracles offering graded pairwise preferences (GPC) is underexplored, despite a rich history in psychometrics. In this paper, we introduce deep submodular peripteral networks (DSPNs), a novel parametric family of submodular functions, and methods for their training using a GPC-based strategy to connect and then tackle both of the above challenges. We introduce newly devised GPC-style ``peripteral'' loss which leverages numerically grad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.08199","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/2403.08199/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":"2403.08199","created_at":"2026-07-05T09:29:26.974930+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.08199v3","created_at":"2026-07-05T09:29:26.974930+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.08199","created_at":"2026-07-05T09:29:26.974930+00:00"},{"alias_kind":"pith_short_12","alias_value":"L6V3ZHDZ6WHB","created_at":"2026-07-05T09:29:26.974930+00:00"},{"alias_kind":"pith_short_16","alias_value":"L6V3ZHDZ6WHBLC4L","created_at":"2026-07-05T09:29:26.974930+00:00"},{"alias_kind":"pith_short_8","alias_value":"L6V3ZHDZ","created_at":"2026-07-05T09:29:26.974930+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/L6V3ZHDZ6WHBLC4LNTUM2T3H4E","json":"https://pith.science/pith/L6V3ZHDZ6WHBLC4LNTUM2T3H4E.json","graph_json":"https://pith.science/api/pith-number/L6V3ZHDZ6WHBLC4LNTUM2T3H4E/graph.json","events_json":"https://pith.science/api/pith-number/L6V3ZHDZ6WHBLC4LNTUM2T3H4E/events.json","paper":"https://pith.science/paper/L6V3ZHDZ"},"agent_actions":{"view_html":"https://pith.science/pith/L6V3ZHDZ6WHBLC4LNTUM2T3H4E","download_json":"https://pith.science/pith/L6V3ZHDZ6WHBLC4LNTUM2T3H4E.json","view_paper":"https://pith.science/paper/L6V3ZHDZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.08199&json=true","fetch_graph":"https://pith.science/api/pith-number/L6V3ZHDZ6WHBLC4LNTUM2T3H4E/graph.json","fetch_events":"https://pith.science/api/pith-number/L6V3ZHDZ6WHBLC4LNTUM2T3H4E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L6V3ZHDZ6WHBLC4LNTUM2T3H4E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L6V3ZHDZ6WHBLC4LNTUM2T3H4E/action/storage_attestation","attest_author":"https://pith.science/pith/L6V3ZHDZ6WHBLC4LNTUM2T3H4E/action/author_attestation","sign_citation":"https://pith.science/pith/L6V3ZHDZ6WHBLC4LNTUM2T3H4E/action/citation_signature","submit_replication":"https://pith.science/pith/L6V3ZHDZ6WHBLC4LNTUM2T3H4E/action/replication_record"}},"created_at":"2026-07-05T09:29:26.974930+00:00","updated_at":"2026-07-05T09:29:26.974930+00:00"}