{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WOHXBW2W3NHDF65BUM3XP7E4OA","short_pith_number":"pith:WOHXBW2W","schema_version":"1.0","canonical_sha256":"b38f70db56db4e32fba1a33777fc9c702cb8301fe9c563bdc33963fe0977d981","source":{"kind":"arxiv","id":"2505.16752","version":3},"attestation_state":"computed","paper":{"title":"Action is All You Need: Dual-Flow Generative Ranking Network for Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Erpeng Xue, Hao Guo, Jinpeng Wang, Lei Huang, Lei Wang, Sheng Chen, Shichao Wang, Xiaolei Wang","submitted_at":"2025-05-22T14:58:53Z","abstract_excerpt":"Deep Learning Recommendation Models (DLRMs) often rely on extensive manual feature engineering to improve accuracy and user experience, which increases system complexity and limits scalability of model performance with respect to computational resources. Recently, Meta introduced a generative ranking paradigm based on HSTU block that enables end-to-end learning from raw user behavior sequences and demonstrates scaling law on large datasets that can be regarded as the state-of-the-art (SOTA). However, splitting user behaviors into interleaved item and action information significantly increases "},"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":"2505.16752","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-05-22T14:58:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b43131332bd271cc07e30288475dbed9e7c4d9b3addad86ed225aa2dcfef8e2d","abstract_canon_sha256":"51aee052173ad0632393a86067d2c40fbe9b8bca0ae7571ab30ab0b8030fd320"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:19.539911Z","signature_b64":"tH2B5X0XzwY5IO81rTYXFGhhNxuMGkL6A2ijpAOH0TtmCeS+YmHxb8dUmoCAZi+3lzMLK025zcPUmn/IF5cyCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b38f70db56db4e32fba1a33777fc9c702cb8301fe9c563bdc33963fe0977d981","last_reissued_at":"2026-07-05T11:55:19.539397Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:19.539397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Action is All You Need: Dual-Flow Generative Ranking Network for Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Erpeng Xue, Hao Guo, Jinpeng Wang, Lei Huang, Lei Wang, Sheng Chen, Shichao Wang, Xiaolei Wang","submitted_at":"2025-05-22T14:58:53Z","abstract_excerpt":"Deep Learning Recommendation Models (DLRMs) often rely on extensive manual feature engineering to improve accuracy and user experience, which increases system complexity and limits scalability of model performance with respect to computational resources. Recently, Meta introduced a generative ranking paradigm based on HSTU block that enables end-to-end learning from raw user behavior sequences and demonstrates scaling law on large datasets that can be regarded as the state-of-the-art (SOTA). However, splitting user behaviors into interleaved item and action information significantly increases "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16752","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/2505.16752/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":"2505.16752","created_at":"2026-07-05T11:55:19.539475+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.16752v3","created_at":"2026-07-05T11:55:19.539475+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16752","created_at":"2026-07-05T11:55:19.539475+00:00"},{"alias_kind":"pith_short_12","alias_value":"WOHXBW2W3NHD","created_at":"2026-07-05T11:55:19.539475+00:00"},{"alias_kind":"pith_short_16","alias_value":"WOHXBW2W3NHDF65B","created_at":"2026-07-05T11:55:19.539475+00:00"},{"alias_kind":"pith_short_8","alias_value":"WOHXBW2W","created_at":"2026-07-05T11:55:19.539475+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.06507","citing_title":"GR-LLMs: Recent Advances in Generative Recommendation Based on Large Language Models","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WOHXBW2W3NHDF65BUM3XP7E4OA","json":"https://pith.science/pith/WOHXBW2W3NHDF65BUM3XP7E4OA.json","graph_json":"https://pith.science/api/pith-number/WOHXBW2W3NHDF65BUM3XP7E4OA/graph.json","events_json":"https://pith.science/api/pith-number/WOHXBW2W3NHDF65BUM3XP7E4OA/events.json","paper":"https://pith.science/paper/WOHXBW2W"},"agent_actions":{"view_html":"https://pith.science/pith/WOHXBW2W3NHDF65BUM3XP7E4OA","download_json":"https://pith.science/pith/WOHXBW2W3NHDF65BUM3XP7E4OA.json","view_paper":"https://pith.science/paper/WOHXBW2W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.16752&json=true","fetch_graph":"https://pith.science/api/pith-number/WOHXBW2W3NHDF65BUM3XP7E4OA/graph.json","fetch_events":"https://pith.science/api/pith-number/WOHXBW2W3NHDF65BUM3XP7E4OA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WOHXBW2W3NHDF65BUM3XP7E4OA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WOHXBW2W3NHDF65BUM3XP7E4OA/action/storage_attestation","attest_author":"https://pith.science/pith/WOHXBW2W3NHDF65BUM3XP7E4OA/action/author_attestation","sign_citation":"https://pith.science/pith/WOHXBW2W3NHDF65BUM3XP7E4OA/action/citation_signature","submit_replication":"https://pith.science/pith/WOHXBW2W3NHDF65BUM3XP7E4OA/action/replication_record"}},"created_at":"2026-07-05T11:55:19.539475+00:00","updated_at":"2026-07-05T11:55:19.539475+00:00"}