{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RMVLFQI45LIDVJ7ECBQ7ZCYVDB","short_pith_number":"pith:RMVLFQI4","schema_version":"1.0","canonical_sha256":"8b2ab2c11cead03aa7e41061fc8b15186126183ff0021a10f3c3e2d37f9d45c4","source":{"kind":"arxiv","id":"2602.11799","version":2},"attestation_state":"computed","paper":{"title":"Hi-SAM: A Hierarchical Structure-Aware Multi-modal Framework for Large-Scale Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.AI","authors_text":"Chuanjiang Luo, Hongxiang Chen, Peiyao Lu, Pingjun Pan, Tingting Fei, Tingting Zhou","submitted_at":"2026-02-12T10:26:15Z","abstract_excerpt":"Multi-modal recommendation has gained traction as items possess rich attributes like text and images. Semantic ID-based approaches effectively discretize this information into compact tokens. However, two challenges persist: (1) Suboptimal Tokenization: existing methods (e.g., RQ-VAE) lack disentanglement between shared cross-modal semantics and modality-specific details, causing redundancy or collapse; (2) Architecture-Data Mismatch: vanilla Transformers treat semantic IDs as flat streams, ignoring the hierarchy of user interactions, items, and tokens. Expanding items into multiple tokens amp"},"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":"2602.11799","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-12T10:26:15Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"b5008828a3bd5c400e7bb2f98dc7707da1d34a7f848954a8d7ae19484f51132f","abstract_canon_sha256":"0dc9d519691e4a2c375576a57e4afe2ac50f9216e9fce5924bf72e66b18cf1c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:44.525125Z","signature_b64":"1LA0hWnN5DvESOlIbuXuS5MgxR47NLMsJuMff7gEGG/hN4D0+b1r6j81w//c+7STwgODmYHTskiAhErJMgOPBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b2ab2c11cead03aa7e41061fc8b15186126183ff0021a10f3c3e2d37f9d45c4","last_reissued_at":"2026-05-27T01:05:44.524279Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:44.524279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hi-SAM: A Hierarchical Structure-Aware Multi-modal Framework for Large-Scale Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.AI","authors_text":"Chuanjiang Luo, Hongxiang Chen, Peiyao Lu, Pingjun Pan, Tingting Fei, Tingting Zhou","submitted_at":"2026-02-12T10:26:15Z","abstract_excerpt":"Multi-modal recommendation has gained traction as items possess rich attributes like text and images. Semantic ID-based approaches effectively discretize this information into compact tokens. However, two challenges persist: (1) Suboptimal Tokenization: existing methods (e.g., RQ-VAE) lack disentanglement between shared cross-modal semantics and modality-specific details, causing redundancy or collapse; (2) Architecture-Data Mismatch: vanilla Transformers treat semantic IDs as flat streams, ignoring the hierarchy of user interactions, items, and tokens. Expanding items into multiple tokens amp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.11799","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/2602.11799/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":"2602.11799","created_at":"2026-05-27T01:05:44.524404+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.11799v2","created_at":"2026-05-27T01:05:44.524404+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.11799","created_at":"2026-05-27T01:05:44.524404+00:00"},{"alias_kind":"pith_short_12","alias_value":"RMVLFQI45LID","created_at":"2026-05-27T01:05:44.524404+00:00"},{"alias_kind":"pith_short_16","alias_value":"RMVLFQI45LIDVJ7E","created_at":"2026-05-27T01:05:44.524404+00:00"},{"alias_kind":"pith_short_8","alias_value":"RMVLFQI4","created_at":"2026-05-27T01:05:44.524404+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/RMVLFQI45LIDVJ7ECBQ7ZCYVDB","json":"https://pith.science/pith/RMVLFQI45LIDVJ7ECBQ7ZCYVDB.json","graph_json":"https://pith.science/api/pith-number/RMVLFQI45LIDVJ7ECBQ7ZCYVDB/graph.json","events_json":"https://pith.science/api/pith-number/RMVLFQI45LIDVJ7ECBQ7ZCYVDB/events.json","paper":"https://pith.science/paper/RMVLFQI4"},"agent_actions":{"view_html":"https://pith.science/pith/RMVLFQI45LIDVJ7ECBQ7ZCYVDB","download_json":"https://pith.science/pith/RMVLFQI45LIDVJ7ECBQ7ZCYVDB.json","view_paper":"https://pith.science/paper/RMVLFQI4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.11799&json=true","fetch_graph":"https://pith.science/api/pith-number/RMVLFQI45LIDVJ7ECBQ7ZCYVDB/graph.json","fetch_events":"https://pith.science/api/pith-number/RMVLFQI45LIDVJ7ECBQ7ZCYVDB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RMVLFQI45LIDVJ7ECBQ7ZCYVDB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RMVLFQI45LIDVJ7ECBQ7ZCYVDB/action/storage_attestation","attest_author":"https://pith.science/pith/RMVLFQI45LIDVJ7ECBQ7ZCYVDB/action/author_attestation","sign_citation":"https://pith.science/pith/RMVLFQI45LIDVJ7ECBQ7ZCYVDB/action/citation_signature","submit_replication":"https://pith.science/pith/RMVLFQI45LIDVJ7ECBQ7ZCYVDB/action/replication_record"}},"created_at":"2026-05-27T01:05:44.524404+00:00","updated_at":"2026-05-27T01:05:44.524404+00:00"}