{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:CC3HNXISRAL4UXWT6BYH4VZKXC","short_pith_number":"pith:CC3HNXIS","schema_version":"1.0","canonical_sha256":"10b676dd128817ca5ed3f0707e572ab8a0f498da65fdbbe1695af69333427aaa","source":{"kind":"arxiv","id":"2006.04466","version":2},"attestation_state":"computed","paper":{"title":"Differentiable Neural Input Search for Recommender Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.LG","authors_text":"Linpeng Huang, Weiyu Cheng, Yanyan Shen","submitted_at":"2020-06-08T10:43:59Z","abstract_excerpt":"Latent factor models are the driving forces of the state-of-the-art recommender systems, with an important insight of vectorizing raw input features into dense embeddings. The dimensions of different feature embeddings are often set to a same value empirically, which limits the predictive performance of latent factor models. Existing works have proposed heuristic or reinforcement learning-based methods to search for mixed feature embedding dimensions. For efficiency concern, these methods typically choose embedding dimensions from a restricted set of candidate dimensions. However, this restric"},"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":"2006.04466","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-08T10:43:59Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"03cccb423e125f01376a0ec6b224d0e01a22e441066d5c78813626fb5dde56a8","abstract_canon_sha256":"6e312fb547da9a4d59deadde1163e66d59b590da982242fe316b37322dc36ed2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:34:23.059543Z","signature_b64":"UYyTCSO+S5IJFUWRkKYA5JRHcxwu7yeyfSLmoyPiqPWhheznME3zMgErL+ZrB9NGnyFZ1KG5WnIcKcZR9POSBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10b676dd128817ca5ed3f0707e572ab8a0f498da65fdbbe1695af69333427aaa","last_reissued_at":"2026-07-05T01:34:23.059103Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:34:23.059103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differentiable Neural Input Search for Recommender Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.LG","authors_text":"Linpeng Huang, Weiyu Cheng, Yanyan Shen","submitted_at":"2020-06-08T10:43:59Z","abstract_excerpt":"Latent factor models are the driving forces of the state-of-the-art recommender systems, with an important insight of vectorizing raw input features into dense embeddings. The dimensions of different feature embeddings are often set to a same value empirically, which limits the predictive performance of latent factor models. Existing works have proposed heuristic or reinforcement learning-based methods to search for mixed feature embedding dimensions. For efficiency concern, these methods typically choose embedding dimensions from a restricted set of candidate dimensions. However, this restric"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.04466","kind":"arxiv","version":2},"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/2006.04466/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":"2006.04466","created_at":"2026-07-05T01:34:23.059157+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.04466v2","created_at":"2026-07-05T01:34:23.059157+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.04466","created_at":"2026-07-05T01:34:23.059157+00:00"},{"alias_kind":"pith_short_12","alias_value":"CC3HNXISRAL4","created_at":"2026-07-05T01:34:23.059157+00:00"},{"alias_kind":"pith_short_16","alias_value":"CC3HNXISRAL4UXWT","created_at":"2026-07-05T01:34:23.059157+00:00"},{"alias_kind":"pith_short_8","alias_value":"CC3HNXIS","created_at":"2026-07-05T01:34:23.059157+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.06441","citing_title":"Light-FMP: Lightweight Feature and Model Pruning for Enhanced Deep Recommender Systems","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CC3HNXISRAL4UXWT6BYH4VZKXC","json":"https://pith.science/pith/CC3HNXISRAL4UXWT6BYH4VZKXC.json","graph_json":"https://pith.science/api/pith-number/CC3HNXISRAL4UXWT6BYH4VZKXC/graph.json","events_json":"https://pith.science/api/pith-number/CC3HNXISRAL4UXWT6BYH4VZKXC/events.json","paper":"https://pith.science/paper/CC3HNXIS"},"agent_actions":{"view_html":"https://pith.science/pith/CC3HNXISRAL4UXWT6BYH4VZKXC","download_json":"https://pith.science/pith/CC3HNXISRAL4UXWT6BYH4VZKXC.json","view_paper":"https://pith.science/paper/CC3HNXIS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.04466&json=true","fetch_graph":"https://pith.science/api/pith-number/CC3HNXISRAL4UXWT6BYH4VZKXC/graph.json","fetch_events":"https://pith.science/api/pith-number/CC3HNXISRAL4UXWT6BYH4VZKXC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CC3HNXISRAL4UXWT6BYH4VZKXC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CC3HNXISRAL4UXWT6BYH4VZKXC/action/storage_attestation","attest_author":"https://pith.science/pith/CC3HNXISRAL4UXWT6BYH4VZKXC/action/author_attestation","sign_citation":"https://pith.science/pith/CC3HNXISRAL4UXWT6BYH4VZKXC/action/citation_signature","submit_replication":"https://pith.science/pith/CC3HNXISRAL4UXWT6BYH4VZKXC/action/replication_record"}},"created_at":"2026-07-05T01:34:23.059157+00:00","updated_at":"2026-07-05T01:34:23.059157+00:00"}