{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:554FK673RR5EYF5BDGS6QJCPHB","short_pith_number":"pith:554FK673","schema_version":"1.0","canonical_sha256":"ef78557bfb8c7a4c17a119a5e8244f3878c22bd044ccbef04479c889bf905235","source":{"kind":"arxiv","id":"2502.10833","version":2},"attestation_state":"computed","paper":{"title":"Order-agnostic Identifier for Large Language Model-based Generative Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Fuli Feng, Haihan Shi, Qifan Wang, See-kiong Ng, Tat-Seng Chua, Wenjie Wang, Xinyu Lin","submitted_at":"2025-02-15T15:25:38Z","abstract_excerpt":"Leveraging Large Language Models (LLMs) for generative recommendation has attracted significant research interest, where item tokenization is a critical step. It involves assigning item identifiers for LLMs to encode user history and generate the next item. Existing approaches leverage either token-sequence identifiers, representing items as discrete token sequences, or single-token identifiers, using ID or semantic embeddings. Token-sequence identifiers face issues such as the local optima problem in beam search and low generation efficiency due to step-by-step generation. In contrast, single"},"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":"2502.10833","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-02-15T15:25:38Z","cross_cats_sorted":[],"title_canon_sha256":"96417e06d574658d0051d8d78052fdd2baa7142ad0fbf09c1f3af9b09d8e5375","abstract_canon_sha256":"011ef79dccca83ca0fff7c2b8d2caec982873b31b71c5d12810efd56dbdac2fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:08.397492Z","signature_b64":"OS/zvb7+1nrwyrINfOzmpoUbyqL2Ibm3du+2QZUiQ5NdYlvEmgTkmlHWD6YITzDxvIXPSGxLIQGNxXCuV7F/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef78557bfb8c7a4c17a119a5e8244f3878c22bd044ccbef04479c889bf905235","last_reissued_at":"2026-07-05T11:09:08.397018Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:08.397018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Order-agnostic Identifier for Large Language Model-based Generative Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Fuli Feng, Haihan Shi, Qifan Wang, See-kiong Ng, Tat-Seng Chua, Wenjie Wang, Xinyu Lin","submitted_at":"2025-02-15T15:25:38Z","abstract_excerpt":"Leveraging Large Language Models (LLMs) for generative recommendation has attracted significant research interest, where item tokenization is a critical step. It involves assigning item identifiers for LLMs to encode user history and generate the next item. Existing approaches leverage either token-sequence identifiers, representing items as discrete token sequences, or single-token identifiers, using ID or semantic embeddings. Token-sequence identifiers face issues such as the local optima problem in beam search and low generation efficiency due to step-by-step generation. In contrast, single"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10833","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/2502.10833/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":"2502.10833","created_at":"2026-07-05T11:09:08.397073+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.10833v2","created_at":"2026-07-05T11:09:08.397073+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10833","created_at":"2026-07-05T11:09:08.397073+00:00"},{"alias_kind":"pith_short_12","alias_value":"554FK673RR5E","created_at":"2026-07-05T11:09:08.397073+00:00"},{"alias_kind":"pith_short_16","alias_value":"554FK673RR5EYF5B","created_at":"2026-07-05T11:09:08.397073+00:00"},{"alias_kind":"pith_short_8","alias_value":"554FK673","created_at":"2026-07-05T11:09:08.397073+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.16114","citing_title":"GFlowGR: Fine-tuning Generative Recommendation Frameworks with Generative Flow Networks","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/554FK673RR5EYF5BDGS6QJCPHB","json":"https://pith.science/pith/554FK673RR5EYF5BDGS6QJCPHB.json","graph_json":"https://pith.science/api/pith-number/554FK673RR5EYF5BDGS6QJCPHB/graph.json","events_json":"https://pith.science/api/pith-number/554FK673RR5EYF5BDGS6QJCPHB/events.json","paper":"https://pith.science/paper/554FK673"},"agent_actions":{"view_html":"https://pith.science/pith/554FK673RR5EYF5BDGS6QJCPHB","download_json":"https://pith.science/pith/554FK673RR5EYF5BDGS6QJCPHB.json","view_paper":"https://pith.science/paper/554FK673","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.10833&json=true","fetch_graph":"https://pith.science/api/pith-number/554FK673RR5EYF5BDGS6QJCPHB/graph.json","fetch_events":"https://pith.science/api/pith-number/554FK673RR5EYF5BDGS6QJCPHB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/554FK673RR5EYF5BDGS6QJCPHB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/554FK673RR5EYF5BDGS6QJCPHB/action/storage_attestation","attest_author":"https://pith.science/pith/554FK673RR5EYF5BDGS6QJCPHB/action/author_attestation","sign_citation":"https://pith.science/pith/554FK673RR5EYF5BDGS6QJCPHB/action/citation_signature","submit_replication":"https://pith.science/pith/554FK673RR5EYF5BDGS6QJCPHB/action/replication_record"}},"created_at":"2026-07-05T11:09:08.397073+00:00","updated_at":"2026-07-05T11:09:08.397073+00:00"}