{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LG2L23P3XOWXRVGDJJ2REKYQXQ","short_pith_number":"pith:LG2L23P3","schema_version":"1.0","canonical_sha256":"59b4bd6dfbbbad78d4c34a75122b10bc27a80fcabb8b6fe17de8349c70870b0e","source":{"kind":"arxiv","id":"2203.15508","version":1},"attestation_state":"computed","paper":{"title":"Improving Contrastive Learning with Model Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.LG","authors_text":"Caiming Xiong, Jia Li, Man Luo, Philip S. Yu, Yongjun Chen, Zhiwei Liu","submitted_at":"2022-03-25T06:12:58Z","abstract_excerpt":"The sequential recommendation aims at predicting the next items in user behaviors, which can be solved by characterizing item relationships in sequences. Due to the data sparsity and noise issues in sequences, a new self-supervised learning (SSL) paradigm is proposed to improve the performance, which employs contrastive learning between positive and negative views of sequences.\n  However, existing methods all construct views by adopting augmentation from data perspectives, while we argue that 1) optimal data augmentation methods are hard to devise, 2) data augmentation methods destroy sequenti"},"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":"2203.15508","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-25T06:12:58Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"cfc02e2d4d25ac423325a4c299f9782da8cb0be686a0dec7792b2fd07f9a753b","abstract_canon_sha256":"4e61a43fdc3376f343a987798c85007c74eb58e20a5e7b10e3b4a25ab63bf76f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:09:26.333249Z","signature_b64":"vot0GevKTyCX+xYSTuv4f2SAyDHtafyVltQs9d3uFck2+LVQifp3QJvkafN9hdizsuZeBAekpNQPo15z0kh4CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59b4bd6dfbbbad78d4c34a75122b10bc27a80fcabb8b6fe17de8349c70870b0e","last_reissued_at":"2026-07-05T04:09:26.332759Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:09:26.332759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Contrastive Learning with Model Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.LG","authors_text":"Caiming Xiong, Jia Li, Man Luo, Philip S. Yu, Yongjun Chen, Zhiwei Liu","submitted_at":"2022-03-25T06:12:58Z","abstract_excerpt":"The sequential recommendation aims at predicting the next items in user behaviors, which can be solved by characterizing item relationships in sequences. Due to the data sparsity and noise issues in sequences, a new self-supervised learning (SSL) paradigm is proposed to improve the performance, which employs contrastive learning between positive and negative views of sequences.\n  However, existing methods all construct views by adopting augmentation from data perspectives, while we argue that 1) optimal data augmentation methods are hard to devise, 2) data augmentation methods destroy sequenti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.15508","kind":"arxiv","version":1},"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/2203.15508/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":"2203.15508","created_at":"2026-07-05T04:09:26.332820+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.15508v1","created_at":"2026-07-05T04:09:26.332820+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.15508","created_at":"2026-07-05T04:09:26.332820+00:00"},{"alias_kind":"pith_short_12","alias_value":"LG2L23P3XOWX","created_at":"2026-07-05T04:09:26.332820+00:00"},{"alias_kind":"pith_short_16","alias_value":"LG2L23P3XOWXRVGD","created_at":"2026-07-05T04:09:26.332820+00:00"},{"alias_kind":"pith_short_8","alias_value":"LG2L23P3","created_at":"2026-07-05T04:09:26.332820+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.14114","citing_title":"ID and Graph View Contrastive Learning with Multi-View Attention Fusion for Sequential Recommendation","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LG2L23P3XOWXRVGDJJ2REKYQXQ","json":"https://pith.science/pith/LG2L23P3XOWXRVGDJJ2REKYQXQ.json","graph_json":"https://pith.science/api/pith-number/LG2L23P3XOWXRVGDJJ2REKYQXQ/graph.json","events_json":"https://pith.science/api/pith-number/LG2L23P3XOWXRVGDJJ2REKYQXQ/events.json","paper":"https://pith.science/paper/LG2L23P3"},"agent_actions":{"view_html":"https://pith.science/pith/LG2L23P3XOWXRVGDJJ2REKYQXQ","download_json":"https://pith.science/pith/LG2L23P3XOWXRVGDJJ2REKYQXQ.json","view_paper":"https://pith.science/paper/LG2L23P3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.15508&json=true","fetch_graph":"https://pith.science/api/pith-number/LG2L23P3XOWXRVGDJJ2REKYQXQ/graph.json","fetch_events":"https://pith.science/api/pith-number/LG2L23P3XOWXRVGDJJ2REKYQXQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LG2L23P3XOWXRVGDJJ2REKYQXQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LG2L23P3XOWXRVGDJJ2REKYQXQ/action/storage_attestation","attest_author":"https://pith.science/pith/LG2L23P3XOWXRVGDJJ2REKYQXQ/action/author_attestation","sign_citation":"https://pith.science/pith/LG2L23P3XOWXRVGDJJ2REKYQXQ/action/citation_signature","submit_replication":"https://pith.science/pith/LG2L23P3XOWXRVGDJJ2REKYQXQ/action/replication_record"}},"created_at":"2026-07-05T04:09:26.332820+00:00","updated_at":"2026-07-05T04:09:26.332820+00:00"}