{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3BLLHQS6YXB7JWL7AOZ6FLW3IL","short_pith_number":"pith:3BLLHQS6","canonical_record":{"source":{"id":"2403.08206","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-03-13T03:03:15Z","cross_cats_sorted":[],"title_canon_sha256":"21529573c09173ccb8b8ea78b5663fea034fe224d2a632ef93dc67917f5bfba1","abstract_canon_sha256":"85243f9f2859367958e927e37079e7d5f25413b267b6877e9426c0a6ebf5cf7c"},"schema_version":"1.0"},"canonical_sha256":"d856b3c25ec5c3f4d97f03b3e2aedb42c3dec005ab0f7ec823cf67d073d8cffe","source":{"kind":"arxiv","id":"2403.08206","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.08206","created_at":"2026-07-05T07:59:05Z"},{"alias_kind":"arxiv_version","alias_value":"2403.08206v2","created_at":"2026-07-05T07:59:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.08206","created_at":"2026-07-05T07:59:05Z"},{"alias_kind":"pith_short_12","alias_value":"3BLLHQS6YXB7","created_at":"2026-07-05T07:59:05Z"},{"alias_kind":"pith_short_16","alias_value":"3BLLHQS6YXB7JWL7","created_at":"2026-07-05T07:59:05Z"},{"alias_kind":"pith_short_8","alias_value":"3BLLHQS6","created_at":"2026-07-05T07:59:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3BLLHQS6YXB7JWL7AOZ6FLW3IL","target":"record","payload":{"canonical_record":{"source":{"id":"2403.08206","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-03-13T03:03:15Z","cross_cats_sorted":[],"title_canon_sha256":"21529573c09173ccb8b8ea78b5663fea034fe224d2a632ef93dc67917f5bfba1","abstract_canon_sha256":"85243f9f2859367958e927e37079e7d5f25413b267b6877e9426c0a6ebf5cf7c"},"schema_version":"1.0"},"canonical_sha256":"d856b3c25ec5c3f4d97f03b3e2aedb42c3dec005ab0f7ec823cf67d073d8cffe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:05.702616Z","signature_b64":"g9aXHDshrTXUCUyYyhyVMQJqsAMt1hDzhjCa6YL5/WCsZ6COHUu19D96M3Ub3rzUJWDTp/PNuvmESvy9FafcCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d856b3c25ec5c3f4d97f03b3e2aedb42c3dec005ab0f7ec823cf67d073d8cffe","last_reissued_at":"2026-07-05T07:59:05.702228Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:05.702228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.08206","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:59:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bSeoSE8Hp6EsSy6qahz0yHDzWF/F3PBgi9NuN1/ExDojSnP7jHMpqazBTqZJbO0CN57CmTeiUKSDP1xalpGpDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:54:57.997201Z"},"content_sha256":"b0f8e6c76e7f3c27d5398342db5f8009e325aad1bc10685213f984fe6e2e7af9","schema_version":"1.0","event_id":"sha256:b0f8e6c76e7f3c27d5398342db5f8009e325aad1bc10685213f984fe6e2e7af9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3BLLHQS6YXB7JWL7AOZ6FLW3IL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Discrete Semantic Tokenization for Deep CTR Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Hengchang Hu, Jiahao Wu, Jieming Zhu, Min-Yen Kan, Qijiong Liu, Xiao-Ming Wu","submitted_at":"2024-03-13T03:03:15Z","abstract_excerpt":"Incorporating item content information into click-through rate (CTR) prediction models remains a challenge, especially with the time and space constraints of industrial scenarios. The content-encoding paradigm, which integrates user and item encoders directly into CTR models, prioritizes space over time. In contrast, the embedding-based paradigm transforms item and user semantics into latent embeddings, subsequently caching them to optimize processing time at the expense of space. In this paper, we introduce a new semantic-token paradigm and propose a discrete semantic tokenization approach, n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.08206","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/2403.08206/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:59:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gALJ21ZOuHmpZEOh6H9ZDACAgt4dA4h0jzc5+bn36T/0w56dUXhRAuMOsw4tQWipV42sxkhUQW0Xdr7GasJRBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:54:57.997724Z"},"content_sha256":"cb32697f2fba4ae33287f49477a58185217b01a04ab3b2bed175d46ad5c5f75e","schema_version":"1.0","event_id":"sha256:cb32697f2fba4ae33287f49477a58185217b01a04ab3b2bed175d46ad5c5f75e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3BLLHQS6YXB7JWL7AOZ6FLW3IL/bundle.json","state_url":"https://pith.science/pith/3BLLHQS6YXB7JWL7AOZ6FLW3IL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3BLLHQS6YXB7JWL7AOZ6FLW3IL/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T07:54:57Z","links":{"resolver":"https://pith.science/pith/3BLLHQS6YXB7JWL7AOZ6FLW3IL","bundle":"https://pith.science/pith/3BLLHQS6YXB7JWL7AOZ6FLW3IL/bundle.json","state":"https://pith.science/pith/3BLLHQS6YXB7JWL7AOZ6FLW3IL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3BLLHQS6YXB7JWL7AOZ6FLW3IL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3BLLHQS6YXB7JWL7AOZ6FLW3IL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"85243f9f2859367958e927e37079e7d5f25413b267b6877e9426c0a6ebf5cf7c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-03-13T03:03:15Z","title_canon_sha256":"21529573c09173ccb8b8ea78b5663fea034fe224d2a632ef93dc67917f5bfba1"},"schema_version":"1.0","source":{"id":"2403.08206","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.08206","created_at":"2026-07-05T07:59:05Z"},{"alias_kind":"arxiv_version","alias_value":"2403.08206v2","created_at":"2026-07-05T07:59:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.08206","created_at":"2026-07-05T07:59:05Z"},{"alias_kind":"pith_short_12","alias_value":"3BLLHQS6YXB7","created_at":"2026-07-05T07:59:05Z"},{"alias_kind":"pith_short_16","alias_value":"3BLLHQS6YXB7JWL7","created_at":"2026-07-05T07:59:05Z"},{"alias_kind":"pith_short_8","alias_value":"3BLLHQS6","created_at":"2026-07-05T07:59:05Z"}],"graph_snapshots":[{"event_id":"sha256:cb32697f2fba4ae33287f49477a58185217b01a04ab3b2bed175d46ad5c5f75e","target":"graph","created_at":"2026-07-05T07:59:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2403.08206/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Incorporating item content information into click-through rate (CTR) prediction models remains a challenge, especially with the time and space constraints of industrial scenarios. The content-encoding paradigm, which integrates user and item encoders directly into CTR models, prioritizes space over time. In contrast, the embedding-based paradigm transforms item and user semantics into latent embeddings, subsequently caching them to optimize processing time at the expense of space. In this paper, we introduce a new semantic-token paradigm and propose a discrete semantic tokenization approach, n","authors_text":"Hengchang Hu, Jiahao Wu, Jieming Zhu, Min-Yen Kan, Qijiong Liu, Xiao-Ming Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-03-13T03:03:15Z","title":"Discrete Semantic Tokenization for Deep CTR Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.08206","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b0f8e6c76e7f3c27d5398342db5f8009e325aad1bc10685213f984fe6e2e7af9","target":"record","created_at":"2026-07-05T07:59:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"85243f9f2859367958e927e37079e7d5f25413b267b6877e9426c0a6ebf5cf7c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-03-13T03:03:15Z","title_canon_sha256":"21529573c09173ccb8b8ea78b5663fea034fe224d2a632ef93dc67917f5bfba1"},"schema_version":"1.0","source":{"id":"2403.08206","kind":"arxiv","version":2}},"canonical_sha256":"d856b3c25ec5c3f4d97f03b3e2aedb42c3dec005ab0f7ec823cf67d073d8cffe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d856b3c25ec5c3f4d97f03b3e2aedb42c3dec005ab0f7ec823cf67d073d8cffe","first_computed_at":"2026-07-05T07:59:05.702228Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:59:05.702228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g9aXHDshrTXUCUyYyhyVMQJqsAMt1hDzhjCa6YL5/WCsZ6COHUu19D96M3Ub3rzUJWDTp/PNuvmESvy9FafcCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:59:05.702616Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.08206","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b0f8e6c76e7f3c27d5398342db5f8009e325aad1bc10685213f984fe6e2e7af9","sha256:cb32697f2fba4ae33287f49477a58185217b01a04ab3b2bed175d46ad5c5f75e"],"state_sha256":"b96a822d4dd6641e7a719da71af4af108360c5799f139357c970a6f7fc5daf22"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MCFfwAvlWQ4ClMZ/jBKnEmDPZY9Lg5J9bZ//evJA2o+mfK/FKTWARZMG/uzxFROJ81sEpDW5E/QWWX+XYXesAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T07:54:58.000984Z","bundle_sha256":"3f7a37e01ba99f13c691c4a8c575f863ec261340e98af00e140ad146df0872a5"}}