{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JK7ZZERLA6G3KLPBFWYRLLBZYX","short_pith_number":"pith:JK7ZZERL","schema_version":"1.0","canonical_sha256":"4abf9c922b078db52de12db115ac39c5c9eeaf6cd961a0a8bb17da8564eb58e1","source":{"kind":"arxiv","id":"2608.10240","version":1},"attestation_state":"computed","paper":{"title":"Sequential Modality Dropout for Robust Multi-Modal Sequential Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MM"],"primary_cat":"cs.IR","authors_text":"Guanqun Yang, Wenlong Zhang","submitted_at":"2026-08-10T21:18:25Z","abstract_excerpt":"Multi-modal sequential recommenders assume every item carries every modality, but real product catalogs often miss images or text, and a model trained on complete data loses much of its recommendation accuracy when a modality is unavailable at serving time. We propose Sequential Modality Dropout (SMD): during training, each modality stream (image and text) is independently erased with probability p for an entire user interaction history, so the model learns to predict the next item without relying on any single modality. We measure robustness by retention, the fraction of a model's full-modali"},"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":"2608.10240","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-08-10T21:18:25Z","cross_cats_sorted":["cs.LG","cs.MM"],"title_canon_sha256":"b8b96130ba7b1a1f30bc7f500296ffbeeafd5b46022a26d449e82ce0816da415","abstract_canon_sha256":"61ac2dd06445f19e74b3405e8800ce96b9e756b626ca0d0e70e26e778f23775f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-12T00:23:09.641112Z","signature_b64":"YAw8MSOGNybz8oweoRuVi/jpqMyKZh4BA6ClXjH64gYhr3z38WB0HEJdi3DOQ9E1Lyb0WC8Rn139wCcyiGotAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4abf9c922b078db52de12db115ac39c5c9eeaf6cd961a0a8bb17da8564eb58e1","last_reissued_at":"2026-08-12T00:23:09.639472Z","signature_status":"signed_v1","first_computed_at":"2026-08-12T00:23:09.639472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sequential Modality Dropout for Robust Multi-Modal Sequential Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MM"],"primary_cat":"cs.IR","authors_text":"Guanqun Yang, Wenlong Zhang","submitted_at":"2026-08-10T21:18:25Z","abstract_excerpt":"Multi-modal sequential recommenders assume every item carries every modality, but real product catalogs often miss images or text, and a model trained on complete data loses much of its recommendation accuracy when a modality is unavailable at serving time. We propose Sequential Modality Dropout (SMD): during training, each modality stream (image and text) is independently erased with probability p for an entire user interaction history, so the model learns to predict the next item without relying on any single modality. We measure robustness by retention, the fraction of a model's full-modali"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.10240","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/2608.10240/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":"2608.10240","created_at":"2026-08-12T00:23:09.642234+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.10240v1","created_at":"2026-08-12T00:23:09.642234+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.10240","created_at":"2026-08-12T00:23:09.642234+00:00"},{"alias_kind":"pith_short_12","alias_value":"JK7ZZERLA6G3","created_at":"2026-08-12T00:23:09.642234+00:00"},{"alias_kind":"pith_short_16","alias_value":"JK7ZZERLA6G3KLPB","created_at":"2026-08-12T00:23:09.642234+00:00"},{"alias_kind":"pith_short_8","alias_value":"JK7ZZERL","created_at":"2026-08-12T00:23:09.642234+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/JK7ZZERLA6G3KLPBFWYRLLBZYX","json":"https://pith.science/pith/JK7ZZERLA6G3KLPBFWYRLLBZYX.json","graph_json":"https://pith.science/api/pith-number/JK7ZZERLA6G3KLPBFWYRLLBZYX/graph.json","events_json":"https://pith.science/api/pith-number/JK7ZZERLA6G3KLPBFWYRLLBZYX/events.json","paper":"https://pith.science/paper/JK7ZZERL"},"agent_actions":{"view_html":"https://pith.science/pith/JK7ZZERLA6G3KLPBFWYRLLBZYX","download_json":"https://pith.science/pith/JK7ZZERLA6G3KLPBFWYRLLBZYX.json","view_paper":"https://pith.science/paper/JK7ZZERL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.10240&json=true","fetch_graph":"https://pith.science/api/pith-number/JK7ZZERLA6G3KLPBFWYRLLBZYX/graph.json","fetch_events":"https://pith.science/api/pith-number/JK7ZZERLA6G3KLPBFWYRLLBZYX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JK7ZZERLA6G3KLPBFWYRLLBZYX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JK7ZZERLA6G3KLPBFWYRLLBZYX/action/storage_attestation","attest_author":"https://pith.science/pith/JK7ZZERLA6G3KLPBFWYRLLBZYX/action/author_attestation","sign_citation":"https://pith.science/pith/JK7ZZERLA6G3KLPBFWYRLLBZYX/action/citation_signature","submit_replication":"https://pith.science/pith/JK7ZZERLA6G3KLPBFWYRLLBZYX/action/replication_record"}},"created_at":"2026-08-12T00:23:09.642234+00:00","updated_at":"2026-08-12T00:23:09.642234+00:00"}