{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XGBD52ZUTUAMR36Z7CM7EZWKRQ","short_pith_number":"pith:XGBD52ZU","schema_version":"1.0","canonical_sha256":"b9823eeb349d00c8efd9f899f266ca8c180e3b8f42f32b69936f041fdd26ebbe","source":{"kind":"arxiv","id":"2504.04843","version":3},"attestation_state":"computed","paper":{"title":"Data Augmentation as Free Lunch: Exploring the Test-Time Augmentation for Sequential Recommendation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Enneng Yang, Guibing Guo, Jianzhe Zhao, Minhan Huang, Xingwei Wang, Yizhou Dang, Yuting Liu","submitted_at":"2025-04-07T08:56:16Z","abstract_excerpt":"Data augmentation has become a promising method of mitigating data sparsity in sequential recommendation. Existing methods generate new yet effective data during model training to improve performance. However, deploying them requires retraining, architecture modification, or introducing additional learnable parameters. The above steps are time-consuming and costly for well-trained models, especially when the model scale becomes large. In this work, we explore the test-time augmentation (TTA) for sequential recommendation, which augments the inputs during the model inference and then aggregates"},"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":"2504.04843","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-04-07T08:56:16Z","cross_cats_sorted":[],"title_canon_sha256":"a4c6f27608f72651fa531ebf148f1eb9a736238b21660d19cc89a019543ed684","abstract_canon_sha256":"92670a4b6ac567762e1ad308bf2971d123971957e93e4b2c37799a1b58390c01"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:56:16.845908Z","signature_b64":"pcDQqbP35+YmFWHpVcat1UjgpSWAgxn/x3pO3EVosi2AQ8a2DzWROOUf8mpSg6vxY0bWhlx+B7KPNgf027jmBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9823eeb349d00c8efd9f899f266ca8c180e3b8f42f32b69936f041fdd26ebbe","last_reissued_at":"2026-07-05T10:56:16.845441Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:56:16.845441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Augmentation as Free Lunch: Exploring the Test-Time Augmentation for Sequential Recommendation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Enneng Yang, Guibing Guo, Jianzhe Zhao, Minhan Huang, Xingwei Wang, Yizhou Dang, Yuting Liu","submitted_at":"2025-04-07T08:56:16Z","abstract_excerpt":"Data augmentation has become a promising method of mitigating data sparsity in sequential recommendation. Existing methods generate new yet effective data during model training to improve performance. However, deploying them requires retraining, architecture modification, or introducing additional learnable parameters. The above steps are time-consuming and costly for well-trained models, especially when the model scale becomes large. In this work, we explore the test-time augmentation (TTA) for sequential recommendation, which augments the inputs during the model inference and then aggregates"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04843","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/2504.04843/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":"2504.04843","created_at":"2026-07-05T10:56:16.845491+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.04843v3","created_at":"2026-07-05T10:56:16.845491+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04843","created_at":"2026-07-05T10:56:16.845491+00:00"},{"alias_kind":"pith_short_12","alias_value":"XGBD52ZUTUAM","created_at":"2026-07-05T10:56:16.845491+00:00"},{"alias_kind":"pith_short_16","alias_value":"XGBD52ZUTUAMR36Z","created_at":"2026-07-05T10:56:16.845491+00:00"},{"alias_kind":"pith_short_8","alias_value":"XGBD52ZU","created_at":"2026-07-05T10:56:16.845491+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.01184","citing_title":"MARS: Modality-Aligned Retrieval for Sequence Augmented CTR Prediction","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XGBD52ZUTUAMR36Z7CM7EZWKRQ","json":"https://pith.science/pith/XGBD52ZUTUAMR36Z7CM7EZWKRQ.json","graph_json":"https://pith.science/api/pith-number/XGBD52ZUTUAMR36Z7CM7EZWKRQ/graph.json","events_json":"https://pith.science/api/pith-number/XGBD52ZUTUAMR36Z7CM7EZWKRQ/events.json","paper":"https://pith.science/paper/XGBD52ZU"},"agent_actions":{"view_html":"https://pith.science/pith/XGBD52ZUTUAMR36Z7CM7EZWKRQ","download_json":"https://pith.science/pith/XGBD52ZUTUAMR36Z7CM7EZWKRQ.json","view_paper":"https://pith.science/paper/XGBD52ZU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.04843&json=true","fetch_graph":"https://pith.science/api/pith-number/XGBD52ZUTUAMR36Z7CM7EZWKRQ/graph.json","fetch_events":"https://pith.science/api/pith-number/XGBD52ZUTUAMR36Z7CM7EZWKRQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XGBD52ZUTUAMR36Z7CM7EZWKRQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XGBD52ZUTUAMR36Z7CM7EZWKRQ/action/storage_attestation","attest_author":"https://pith.science/pith/XGBD52ZUTUAMR36Z7CM7EZWKRQ/action/author_attestation","sign_citation":"https://pith.science/pith/XGBD52ZUTUAMR36Z7CM7EZWKRQ/action/citation_signature","submit_replication":"https://pith.science/pith/XGBD52ZUTUAMR36Z7CM7EZWKRQ/action/replication_record"}},"created_at":"2026-07-05T10:56:16.845491+00:00","updated_at":"2026-07-05T10:56:16.845491+00:00"}