{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Q7NDP3WM2W3ZSBGN2WTX5SGYDN","short_pith_number":"pith:Q7NDP3WM","schema_version":"1.0","canonical_sha256":"87da37eeccd5b79904cdd5a77ec8d81b569900340752adfd87f1e3c911181ebe","source":{"kind":"arxiv","id":"2406.02844","version":2},"attestation_state":"computed","paper":{"title":"Item-Language Model for Conversational Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Anushya Subbiah, Hardik Patel, Judith Yue Li, Li Yang, Qifan Wang, Reza Mirghaderi, Vikram Aggarwal, Yanwei Song","submitted_at":"2024-06-05T01:35:50Z","abstract_excerpt":"Large-language Models (LLMs) have been extremely successful at tasks like complex dialogue understanding, reasoning and coding due to their emergent abilities. These emergent abilities have been extended with multi-modality to include image, audio, and video capabilities. Recommender systems, on the other hand, have been critical for information seeking and item discovery needs. Recently, there have been attempts to apply LLMs for recommendations. One difficulty of current attempts is that the underlying LLM is usually not trained on the recommender system data, which largely contains user int"},"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":"2406.02844","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-06-05T01:35:50Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"157bd2c43ec80e31332273bf115dd09e7fa0475f63bcb5079c93a705f4a8e744","abstract_canon_sha256":"a1f05ec750a7af2ddc0d8a2001ef1a7632b5f56e239c3cd521a2a184e76b75a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:50.276468Z","signature_b64":"3lqApz5/BRXbOB9keECKKU8u97I8nrEneRxnHHzOSLE1iTLiBiO69+6he6AX0HE9LvpVGeMGmXIIg5JT8G7iBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87da37eeccd5b79904cdd5a77ec8d81b569900340752adfd87f1e3c911181ebe","last_reissued_at":"2026-07-05T11:03:50.275988Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:50.275988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Item-Language Model for Conversational Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Anushya Subbiah, Hardik Patel, Judith Yue Li, Li Yang, Qifan Wang, Reza Mirghaderi, Vikram Aggarwal, Yanwei Song","submitted_at":"2024-06-05T01:35:50Z","abstract_excerpt":"Large-language Models (LLMs) have been extremely successful at tasks like complex dialogue understanding, reasoning and coding due to their emergent abilities. These emergent abilities have been extended with multi-modality to include image, audio, and video capabilities. Recommender systems, on the other hand, have been critical for information seeking and item discovery needs. Recently, there have been attempts to apply LLMs for recommendations. One difficulty of current attempts is that the underlying LLM is usually not trained on the recommender system data, which largely contains user int"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02844","kind":"arxiv","version":2},"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/2406.02844/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":"2406.02844","created_at":"2026-07-05T11:03:50.276047+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.02844v2","created_at":"2026-07-05T11:03:50.276047+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02844","created_at":"2026-07-05T11:03:50.276047+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q7NDP3WM2W3Z","created_at":"2026-07-05T11:03:50.276047+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q7NDP3WM2W3ZSBGN","created_at":"2026-07-05T11:03:50.276047+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q7NDP3WM","created_at":"2026-07-05T11:03:50.276047+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.27157","citing_title":"A Survey on Generative Recommendation: Data, Model, and Tasks","ref_index":205,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07677","citing_title":"TRACE: Tourism Recommendation with Accountable Citation Evidence","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q7NDP3WM2W3ZSBGN2WTX5SGYDN","json":"https://pith.science/pith/Q7NDP3WM2W3ZSBGN2WTX5SGYDN.json","graph_json":"https://pith.science/api/pith-number/Q7NDP3WM2W3ZSBGN2WTX5SGYDN/graph.json","events_json":"https://pith.science/api/pith-number/Q7NDP3WM2W3ZSBGN2WTX5SGYDN/events.json","paper":"https://pith.science/paper/Q7NDP3WM"},"agent_actions":{"view_html":"https://pith.science/pith/Q7NDP3WM2W3ZSBGN2WTX5SGYDN","download_json":"https://pith.science/pith/Q7NDP3WM2W3ZSBGN2WTX5SGYDN.json","view_paper":"https://pith.science/paper/Q7NDP3WM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.02844&json=true","fetch_graph":"https://pith.science/api/pith-number/Q7NDP3WM2W3ZSBGN2WTX5SGYDN/graph.json","fetch_events":"https://pith.science/api/pith-number/Q7NDP3WM2W3ZSBGN2WTX5SGYDN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q7NDP3WM2W3ZSBGN2WTX5SGYDN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q7NDP3WM2W3ZSBGN2WTX5SGYDN/action/storage_attestation","attest_author":"https://pith.science/pith/Q7NDP3WM2W3ZSBGN2WTX5SGYDN/action/author_attestation","sign_citation":"https://pith.science/pith/Q7NDP3WM2W3ZSBGN2WTX5SGYDN/action/citation_signature","submit_replication":"https://pith.science/pith/Q7NDP3WM2W3ZSBGN2WTX5SGYDN/action/replication_record"}},"created_at":"2026-07-05T11:03:50.276047+00:00","updated_at":"2026-07-05T11:03:50.276047+00:00"}