{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NU7J5HPFFQ2SDM5YKSZQ2QQD5E","short_pith_number":"pith:NU7J5HPF","schema_version":"1.0","canonical_sha256":"6d3e9e9de52c3521b3b854b30d4203e92ce54e4f8f3cf191f6115c023f137283","source":{"kind":"arxiv","id":"2606.01844","version":1},"attestation_state":"computed","paper":{"title":"Decoupled Residual Quantization for Robust Semantic IDs in Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Guanxing Zhang, Junjie Wang, Weijie Bian, Xuesi Wang, Ziliang Wang","submitted_at":"2026-06-01T07:55:21Z","abstract_excerpt":"Semantic IDs represent items as shared discrete token sequences and have become a practical tool for recommendation and retrieval. Yet it remains difficult to tell why a tokenizer fails: poor quality may come from codebook underutilization, unstable decision boundaries, or geometric distortion of the embedding space. This paper develops a quantitative framework for diagnosing these failures through expected codeword overlap and effective codebook capacity. The former measures expected codeword confusion under retrieval-time perturbation, while the latter converts that confusion into an effecti"},"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":"2606.01844","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-06-01T07:55:21Z","cross_cats_sorted":[],"title_canon_sha256":"6c3565d0d2cbe109c8a5e2451506baa934dbb0df15cc27f25163ba18e9a4080c","abstract_canon_sha256":"5cdd650857132d9b65bf838a07294322e63e4fcc89e8580ebeb064775f085bb2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:58.344190Z","signature_b64":"OlbgNdsdFUYiblk1mLUK3BveAKKGt5+BXfpw8QSXYKT4tgDzsBwNCbfQkbzoPu1b2GLNiOxBhg11avsx/EN0CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d3e9e9de52c3521b3b854b30d4203e92ce54e4f8f3cf191f6115c023f137283","last_reissued_at":"2026-06-02T02:04:58.343773Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:58.343773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decoupled Residual Quantization for Robust Semantic IDs in Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Guanxing Zhang, Junjie Wang, Weijie Bian, Xuesi Wang, Ziliang Wang","submitted_at":"2026-06-01T07:55:21Z","abstract_excerpt":"Semantic IDs represent items as shared discrete token sequences and have become a practical tool for recommendation and retrieval. Yet it remains difficult to tell why a tokenizer fails: poor quality may come from codebook underutilization, unstable decision boundaries, or geometric distortion of the embedding space. This paper develops a quantitative framework for diagnosing these failures through expected codeword overlap and effective codebook capacity. The former measures expected codeword confusion under retrieval-time perturbation, while the latter converts that confusion into an effecti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01844","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/2606.01844/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":"2606.01844","created_at":"2026-06-02T02:04:58.343841+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01844v1","created_at":"2026-06-02T02:04:58.343841+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01844","created_at":"2026-06-02T02:04:58.343841+00:00"},{"alias_kind":"pith_short_12","alias_value":"NU7J5HPFFQ2S","created_at":"2026-06-02T02:04:58.343841+00:00"},{"alias_kind":"pith_short_16","alias_value":"NU7J5HPFFQ2SDM5Y","created_at":"2026-06-02T02:04:58.343841+00:00"},{"alias_kind":"pith_short_8","alias_value":"NU7J5HPF","created_at":"2026-06-02T02:04:58.343841+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NU7J5HPFFQ2SDM5YKSZQ2QQD5E","json":"https://pith.science/pith/NU7J5HPFFQ2SDM5YKSZQ2QQD5E.json","graph_json":"https://pith.science/api/pith-number/NU7J5HPFFQ2SDM5YKSZQ2QQD5E/graph.json","events_json":"https://pith.science/api/pith-number/NU7J5HPFFQ2SDM5YKSZQ2QQD5E/events.json","paper":"https://pith.science/paper/NU7J5HPF"},"agent_actions":{"view_html":"https://pith.science/pith/NU7J5HPFFQ2SDM5YKSZQ2QQD5E","download_json":"https://pith.science/pith/NU7J5HPFFQ2SDM5YKSZQ2QQD5E.json","view_paper":"https://pith.science/paper/NU7J5HPF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01844&json=true","fetch_graph":"https://pith.science/api/pith-number/NU7J5HPFFQ2SDM5YKSZQ2QQD5E/graph.json","fetch_events":"https://pith.science/api/pith-number/NU7J5HPFFQ2SDM5YKSZQ2QQD5E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NU7J5HPFFQ2SDM5YKSZQ2QQD5E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NU7J5HPFFQ2SDM5YKSZQ2QQD5E/action/storage_attestation","attest_author":"https://pith.science/pith/NU7J5HPFFQ2SDM5YKSZQ2QQD5E/action/author_attestation","sign_citation":"https://pith.science/pith/NU7J5HPFFQ2SDM5YKSZQ2QQD5E/action/citation_signature","submit_replication":"https://pith.science/pith/NU7J5HPFFQ2SDM5YKSZQ2QQD5E/action/replication_record"}},"created_at":"2026-06-02T02:04:58.343841+00:00","updated_at":"2026-06-02T02:04:58.343841+00:00"}