{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5A3POPVVLCUH2QNFADNV6AECNL","short_pith_number":"pith:5A3POPVV","schema_version":"1.0","canonical_sha256":"e836f73eb558a87d41a500db5f00826af8d86087debba4386bc443135101d46c","source":{"kind":"arxiv","id":"2509.13648","version":3},"attestation_state":"computed","paper":{"title":"Sequential Data Augmentation for Generative Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.LG","authors_text":"Bhuvesh Kumar, Clark Mingxuan Ju, Geon Lee, Kijung Shin, Liam Collins, Neil Shah, Tong Zhao","submitted_at":"2025-09-17T02:53:25Z","abstract_excerpt":"Generative recommendation plays a crucial role in personalized systems, predicting users' future interactions from their historical behavior sequences. A critical yet underexplored factor in training these models is data augmentation, the process of constructing training data from user interaction histories. By shaping the training distribution, data augmentation directly and often substantially affects model generalization and performance. Nevertheless, in much of the existing work, this process is simplified, applied inconsistently, or treated as a minor design choice, without a systematic a"},"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":"2509.13648","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-17T02:53:25Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"113eb54731721c8b8ae65eec74a20887e7059ae5f2b0e83dee486389ba191920","abstract_canon_sha256":"bedac47be3397ee7e617adf978ef9fbf4b719cd78d186b256921f75c1c358386"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:16.816700Z","signature_b64":"bEi6UpCtPB6mYvqYIF//sGW48hWT5ITaAitLY8H5e70DyK/iWPyglPBJ1pbET/YOqfkI2VNncRT3T5tvW6oVDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e836f73eb558a87d41a500db5f00826af8d86087debba4386bc443135101d46c","last_reissued_at":"2026-05-21T01:04:16.815957Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:16.815957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sequential Data Augmentation for Generative Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.LG","authors_text":"Bhuvesh Kumar, Clark Mingxuan Ju, Geon Lee, Kijung Shin, Liam Collins, Neil Shah, Tong Zhao","submitted_at":"2025-09-17T02:53:25Z","abstract_excerpt":"Generative recommendation plays a crucial role in personalized systems, predicting users' future interactions from their historical behavior sequences. A critical yet underexplored factor in training these models is data augmentation, the process of constructing training data from user interaction histories. By shaping the training distribution, data augmentation directly and often substantially affects model generalization and performance. Nevertheless, in much of the existing work, this process is simplified, applied inconsistently, or treated as a minor design choice, without a systematic a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.13648","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/2509.13648/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":"2509.13648","created_at":"2026-05-21T01:04:16.816051+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.13648v3","created_at":"2026-05-21T01:04:16.816051+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.13648","created_at":"2026-05-21T01:04:16.816051+00:00"},{"alias_kind":"pith_short_12","alias_value":"5A3POPVVLCUH","created_at":"2026-05-21T01:04:16.816051+00:00"},{"alias_kind":"pith_short_16","alias_value":"5A3POPVVLCUH2QNF","created_at":"2026-05-21T01:04:16.816051+00:00"},{"alias_kind":"pith_short_8","alias_value":"5A3POPVV","created_at":"2026-05-21T01:04:16.816051+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.05309","citing_title":"Pay Attention to Sequence Split: Uncovering the Impacts of Sub-Sequence Splitting on Sequential Recommendation Models","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5A3POPVVLCUH2QNFADNV6AECNL","json":"https://pith.science/pith/5A3POPVVLCUH2QNFADNV6AECNL.json","graph_json":"https://pith.science/api/pith-number/5A3POPVVLCUH2QNFADNV6AECNL/graph.json","events_json":"https://pith.science/api/pith-number/5A3POPVVLCUH2QNFADNV6AECNL/events.json","paper":"https://pith.science/paper/5A3POPVV"},"agent_actions":{"view_html":"https://pith.science/pith/5A3POPVVLCUH2QNFADNV6AECNL","download_json":"https://pith.science/pith/5A3POPVVLCUH2QNFADNV6AECNL.json","view_paper":"https://pith.science/paper/5A3POPVV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.13648&json=true","fetch_graph":"https://pith.science/api/pith-number/5A3POPVVLCUH2QNFADNV6AECNL/graph.json","fetch_events":"https://pith.science/api/pith-number/5A3POPVVLCUH2QNFADNV6AECNL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5A3POPVVLCUH2QNFADNV6AECNL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5A3POPVVLCUH2QNFADNV6AECNL/action/storage_attestation","attest_author":"https://pith.science/pith/5A3POPVVLCUH2QNFADNV6AECNL/action/author_attestation","sign_citation":"https://pith.science/pith/5A3POPVVLCUH2QNFADNV6AECNL/action/citation_signature","submit_replication":"https://pith.science/pith/5A3POPVVLCUH2QNFADNV6AECNL/action/replication_record"}},"created_at":"2026-05-21T01:04:16.816051+00:00","updated_at":"2026-05-21T01:04:16.816051+00:00"}