{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WGVBFZ4JTBA2XEULYLKZVZI7PB","short_pith_number":"pith:WGVBFZ4J","schema_version":"1.0","canonical_sha256":"b1aa12e7899841ab928bc2d59ae51f785a35d5264984e663693cb05c67235620","source":{"kind":"arxiv","id":"2203.13366","version":7},"attestation_state":"computed","paper":{"title":"Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Shijie Geng, Shuchang Liu, Yingqiang Ge, Yongfeng Zhang, Zuohui Fu","submitted_at":"2022-03-24T22:13:23Z","abstract_excerpt":"For a long time, different recommendation tasks typically require designing task-specific architectures and training objectives. As a result, it is hard to transfer the learned knowledge and representations from one task to another, thus restricting the generalization ability of existing recommendation approaches, e.g., a sequential recommendation model can hardly be applied or transferred to a review generation method. To deal with such issues, considering that language can describe almost anything and language grounding is a powerful medium to represent various problems or tasks, we present "},"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":"2203.13366","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-03-24T22:13:23Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"c21df7e17fc9f76883cb4417b915a2060bdb999e2f174f8445554186a67bf4d6","abstract_canon_sha256":"3541bdbeb8c8627ec196b38dc804e7ededc46e5ff066723cc435dd0853439d1c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:29:52.435059Z","signature_b64":"VxLn0Cu/UdE7ZcpPucsj0NQpeYN+qW2U6tipX06ZlOD621o4NkmcolwgizF310sOOK2D05ZdxmEfsu3CxwkjBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1aa12e7899841ab928bc2d59ae51f785a35d5264984e663693cb05c67235620","last_reissued_at":"2026-07-05T05:29:52.434606Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:29:52.434606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Shijie Geng, Shuchang Liu, Yingqiang Ge, Yongfeng Zhang, Zuohui Fu","submitted_at":"2022-03-24T22:13:23Z","abstract_excerpt":"For a long time, different recommendation tasks typically require designing task-specific architectures and training objectives. As a result, it is hard to transfer the learned knowledge and representations from one task to another, thus restricting the generalization ability of existing recommendation approaches, e.g., a sequential recommendation model can hardly be applied or transferred to a review generation method. To deal with such issues, considering that language can describe almost anything and language grounding is a powerful medium to represent various problems or tasks, we present "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.13366","kind":"arxiv","version":7},"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/2203.13366/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":"2203.13366","created_at":"2026-07-05T05:29:52.434664+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.13366v7","created_at":"2026-07-05T05:29:52.434664+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.13366","created_at":"2026-07-05T05:29:52.434664+00:00"},{"alias_kind":"pith_short_12","alias_value":"WGVBFZ4JTBA2","created_at":"2026-07-05T05:29:52.434664+00:00"},{"alias_kind":"pith_short_16","alias_value":"WGVBFZ4JTBA2XEUL","created_at":"2026-07-05T05:29:52.434664+00:00"},{"alias_kind":"pith_short_8","alias_value":"WGVBFZ4J","created_at":"2026-07-05T05:29:52.434664+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12198","citing_title":"LLM-Based User Personas for Recommendations at Scale","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11712","citing_title":"Substrate Asymmetry in User-Side Memory: A Diagnostic Framework","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11553","citing_title":"TwiSTAR:Think Fast, Think Slow, Then Act,Generative Recommendation with Adaptive Reasoning","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WGVBFZ4JTBA2XEULYLKZVZI7PB","json":"https://pith.science/pith/WGVBFZ4JTBA2XEULYLKZVZI7PB.json","graph_json":"https://pith.science/api/pith-number/WGVBFZ4JTBA2XEULYLKZVZI7PB/graph.json","events_json":"https://pith.science/api/pith-number/WGVBFZ4JTBA2XEULYLKZVZI7PB/events.json","paper":"https://pith.science/paper/WGVBFZ4J"},"agent_actions":{"view_html":"https://pith.science/pith/WGVBFZ4JTBA2XEULYLKZVZI7PB","download_json":"https://pith.science/pith/WGVBFZ4JTBA2XEULYLKZVZI7PB.json","view_paper":"https://pith.science/paper/WGVBFZ4J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.13366&json=true","fetch_graph":"https://pith.science/api/pith-number/WGVBFZ4JTBA2XEULYLKZVZI7PB/graph.json","fetch_events":"https://pith.science/api/pith-number/WGVBFZ4JTBA2XEULYLKZVZI7PB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WGVBFZ4JTBA2XEULYLKZVZI7PB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WGVBFZ4JTBA2XEULYLKZVZI7PB/action/storage_attestation","attest_author":"https://pith.science/pith/WGVBFZ4JTBA2XEULYLKZVZI7PB/action/author_attestation","sign_citation":"https://pith.science/pith/WGVBFZ4JTBA2XEULYLKZVZI7PB/action/citation_signature","submit_replication":"https://pith.science/pith/WGVBFZ4JTBA2XEULYLKZVZI7PB/action/replication_record"}},"created_at":"2026-07-05T05:29:52.434664+00:00","updated_at":"2026-07-05T05:29:52.434664+00:00"}