{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LMXLEVX6KTVUCXKN3IRIYI4SM3","short_pith_number":"pith:LMXLEVX6","schema_version":"1.0","canonical_sha256":"5b2eb256fe54eb415d4dda228c239266ed5da93ddf41f985ab9340a0370fb802","source":{"kind":"arxiv","id":"2607.11392","version":1},"attestation_state":"computed","paper":{"title":"Beyond Semantic IDs: Encoding Business-Value Ranking into Document Identifiers for Generative Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Bo Zheng, Dan Ou, Gui Ling, Haihong Tang, Kaixuan Zhang, Kunhai Lin, Tong Xiong, Yu Li, Yuliang Yan, Zhihong Chen","submitted_at":"2026-07-13T10:57:20Z","abstract_excerpt":"Generative Retrieval (GR) formulates retrieval as a sequence-to-sequence generation task, assigning each document a document identifier (DocID) and retrieving it through autoregressive decoding, making DocID design a critical factor in retrieval quality. However, existing schemes based on discrete representation learning suffer from inherent collision issues and create a mismatch between the DocID's encoding objective and the system's business optimization target. To address these limitations, we propose Cluster-Ranked Identifier (CRID), which decouples DocID into semantic clustering and busin"},"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":"2607.11392","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-07-13T10:57:20Z","cross_cats_sorted":[],"title_canon_sha256":"3c0a4b6539f7a65d804512727f686cf171210660639a0b9b7e127e687785a413","abstract_canon_sha256":"ba24c831ff71ee2ee4ff112f2ff49fa6a979634d78793fa4011a545c08bcf7e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T02:21:59.617144Z","signature_b64":"XS/KwTXSGdrXTsNAM31Q9856/eAC1a6tMjaSkAti6gC3mE0we/UOAxzi0ZgBkL8jfC7tjdiEJWDe5zlEHFy3Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b2eb256fe54eb415d4dda228c239266ed5da93ddf41f985ab9340a0370fb802","last_reissued_at":"2026-07-14T02:21:59.616145Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T02:21:59.616145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Semantic IDs: Encoding Business-Value Ranking into Document Identifiers for Generative Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Bo Zheng, Dan Ou, Gui Ling, Haihong Tang, Kaixuan Zhang, Kunhai Lin, Tong Xiong, Yu Li, Yuliang Yan, Zhihong Chen","submitted_at":"2026-07-13T10:57:20Z","abstract_excerpt":"Generative Retrieval (GR) formulates retrieval as a sequence-to-sequence generation task, assigning each document a document identifier (DocID) and retrieving it through autoregressive decoding, making DocID design a critical factor in retrieval quality. However, existing schemes based on discrete representation learning suffer from inherent collision issues and create a mismatch between the DocID's encoding objective and the system's business optimization target. To address these limitations, we propose Cluster-Ranked Identifier (CRID), which decouples DocID into semantic clustering and busin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.11392","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/2607.11392/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":"2607.11392","created_at":"2026-07-14T02:21:59.616627+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.11392v1","created_at":"2026-07-14T02:21:59.616627+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.11392","created_at":"2026-07-14T02:21:59.616627+00:00"},{"alias_kind":"pith_short_12","alias_value":"LMXLEVX6KTVU","created_at":"2026-07-14T02:21:59.616627+00:00"},{"alias_kind":"pith_short_16","alias_value":"LMXLEVX6KTVUCXKN","created_at":"2026-07-14T02:21:59.616627+00:00"},{"alias_kind":"pith_short_8","alias_value":"LMXLEVX6","created_at":"2026-07-14T02:21:59.616627+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/LMXLEVX6KTVUCXKN3IRIYI4SM3","json":"https://pith.science/pith/LMXLEVX6KTVUCXKN3IRIYI4SM3.json","graph_json":"https://pith.science/api/pith-number/LMXLEVX6KTVUCXKN3IRIYI4SM3/graph.json","events_json":"https://pith.science/api/pith-number/LMXLEVX6KTVUCXKN3IRIYI4SM3/events.json","paper":"https://pith.science/paper/LMXLEVX6"},"agent_actions":{"view_html":"https://pith.science/pith/LMXLEVX6KTVUCXKN3IRIYI4SM3","download_json":"https://pith.science/pith/LMXLEVX6KTVUCXKN3IRIYI4SM3.json","view_paper":"https://pith.science/paper/LMXLEVX6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.11392&json=true","fetch_graph":"https://pith.science/api/pith-number/LMXLEVX6KTVUCXKN3IRIYI4SM3/graph.json","fetch_events":"https://pith.science/api/pith-number/LMXLEVX6KTVUCXKN3IRIYI4SM3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LMXLEVX6KTVUCXKN3IRIYI4SM3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LMXLEVX6KTVUCXKN3IRIYI4SM3/action/storage_attestation","attest_author":"https://pith.science/pith/LMXLEVX6KTVUCXKN3IRIYI4SM3/action/author_attestation","sign_citation":"https://pith.science/pith/LMXLEVX6KTVUCXKN3IRIYI4SM3/action/citation_signature","submit_replication":"https://pith.science/pith/LMXLEVX6KTVUCXKN3IRIYI4SM3/action/replication_record"}},"created_at":"2026-07-14T02:21:59.616627+00:00","updated_at":"2026-07-14T02:21:59.616627+00:00"}