{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5OAHISLRP6P7RPWFOAPFJT5UIE","short_pith_number":"pith:5OAHISLR","schema_version":"1.0","canonical_sha256":"eb807449717f9ff8bec5701e54cfb4411a946770722f4c7c5da73f1b3fd02e16","source":{"kind":"arxiv","id":"2403.00793","version":2},"attestation_state":"computed","paper":{"title":"Ads Recommendation in a Collapsed and Entangled World","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Dapeng Liu, Haibin Yu, Jie Jiang, Junwei Pan, Lei Xiao, Shijie Quan, Wei Xue, Ximei Wang, Xueming Qiu, Xun Liu","submitted_at":"2024-02-22T22:47:08Z","abstract_excerpt":"We present Tencent's ads recommendation system and examine the challenges and practices of learning appropriate recommendation representations. Our study begins by showcasing our approaches to preserving prior knowledge when encoding features of diverse types into embedding representations. We specifically address sequence features, numeric features, and pre-trained embedding features. Subsequently, we delve into two crucial challenges related to feature representation: the dimensional collapse of embeddings and the interest entanglement across different tasks or scenarios. We propose several "},"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":"2403.00793","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-02-22T22:47:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e5e2f5e5e577536527a3a02e856b7528527a8062081c7e5ea17fd1b25ed91e3e","abstract_canon_sha256":"04272001cedaeb19743e203644a3d4285cebd935cf9769c83201b6cae641fbb0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:40:39.504430Z","signature_b64":"EmxZWZa8J2wAUhkTdmO6CF3M8MfZZYv32JUj0JAEAa+1+k2TaKdjUn94jZh1IJIguUTvnyw5osDOW5XrWSM4Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb807449717f9ff8bec5701e54cfb4411a946770722f4c7c5da73f1b3fd02e16","last_reissued_at":"2026-07-05T08:40:39.503930Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:40:39.503930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ads Recommendation in a Collapsed and Entangled World","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Dapeng Liu, Haibin Yu, Jie Jiang, Junwei Pan, Lei Xiao, Shijie Quan, Wei Xue, Ximei Wang, Xueming Qiu, Xun Liu","submitted_at":"2024-02-22T22:47:08Z","abstract_excerpt":"We present Tencent's ads recommendation system and examine the challenges and practices of learning appropriate recommendation representations. Our study begins by showcasing our approaches to preserving prior knowledge when encoding features of diverse types into embedding representations. We specifically address sequence features, numeric features, and pre-trained embedding features. Subsequently, we delve into two crucial challenges related to feature representation: the dimensional collapse of embeddings and the interest entanglement across different tasks or scenarios. We propose several "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00793","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/2403.00793/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":"2403.00793","created_at":"2026-07-05T08:40:39.503990+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.00793v2","created_at":"2026-07-05T08:40:39.503990+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00793","created_at":"2026-07-05T08:40:39.503990+00:00"},{"alias_kind":"pith_short_12","alias_value":"5OAHISLRP6P7","created_at":"2026-07-05T08:40:39.503990+00:00"},{"alias_kind":"pith_short_16","alias_value":"5OAHISLRP6P7RPWF","created_at":"2026-07-05T08:40:39.503990+00:00"},{"alias_kind":"pith_short_8","alias_value":"5OAHISLR","created_at":"2026-07-05T08:40:39.503990+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.12441","citing_title":"Towards Unifying Feature Interaction Models for Click-Through Rate Prediction","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5OAHISLRP6P7RPWFOAPFJT5UIE","json":"https://pith.science/pith/5OAHISLRP6P7RPWFOAPFJT5UIE.json","graph_json":"https://pith.science/api/pith-number/5OAHISLRP6P7RPWFOAPFJT5UIE/graph.json","events_json":"https://pith.science/api/pith-number/5OAHISLRP6P7RPWFOAPFJT5UIE/events.json","paper":"https://pith.science/paper/5OAHISLR"},"agent_actions":{"view_html":"https://pith.science/pith/5OAHISLRP6P7RPWFOAPFJT5UIE","download_json":"https://pith.science/pith/5OAHISLRP6P7RPWFOAPFJT5UIE.json","view_paper":"https://pith.science/paper/5OAHISLR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.00793&json=true","fetch_graph":"https://pith.science/api/pith-number/5OAHISLRP6P7RPWFOAPFJT5UIE/graph.json","fetch_events":"https://pith.science/api/pith-number/5OAHISLRP6P7RPWFOAPFJT5UIE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5OAHISLRP6P7RPWFOAPFJT5UIE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5OAHISLRP6P7RPWFOAPFJT5UIE/action/storage_attestation","attest_author":"https://pith.science/pith/5OAHISLRP6P7RPWFOAPFJT5UIE/action/author_attestation","sign_citation":"https://pith.science/pith/5OAHISLRP6P7RPWFOAPFJT5UIE/action/citation_signature","submit_replication":"https://pith.science/pith/5OAHISLRP6P7RPWFOAPFJT5UIE/action/replication_record"}},"created_at":"2026-07-05T08:40:39.503990+00:00","updated_at":"2026-07-05T08:40:39.503990+00:00"}