{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:XNAUCN672X57TT4DPNSRM2DDCW","short_pith_number":"pith:XNAUCN67","canonical_record":{"source":{"id":"2305.12102","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-20T05:35:40Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"6debfb91e9d9d03d4be377564666c3ed9022541709fc75e6d5e909deb78ae472","abstract_canon_sha256":"ab8ec8b7fcde34253d06b74c3562a397deaa90b9ce5127780d74c6bed3960f95"},"schema_version":"1.0"},"canonical_sha256":"bb414137dfd5fbf9cf837b6516686315b5a85f1564af6a684d3e833c6760bdb9","source":{"kind":"arxiv","id":"2305.12102","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.12102","created_at":"2026-07-05T08:32:59Z"},{"alias_kind":"arxiv_version","alias_value":"2305.12102v3","created_at":"2026-07-05T08:32:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12102","created_at":"2026-07-05T08:32:59Z"},{"alias_kind":"pith_short_12","alias_value":"XNAUCN672X57","created_at":"2026-07-05T08:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"XNAUCN672X57TT4D","created_at":"2026-07-05T08:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"XNAUCN67","created_at":"2026-07-05T08:32:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:XNAUCN672X57TT4DPNSRM2DDCW","target":"record","payload":{"canonical_record":{"source":{"id":"2305.12102","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-20T05:35:40Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"6debfb91e9d9d03d4be377564666c3ed9022541709fc75e6d5e909deb78ae472","abstract_canon_sha256":"ab8ec8b7fcde34253d06b74c3562a397deaa90b9ce5127780d74c6bed3960f95"},"schema_version":"1.0"},"canonical_sha256":"bb414137dfd5fbf9cf837b6516686315b5a85f1564af6a684d3e833c6760bdb9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:59.125186Z","signature_b64":"+bjK1545j+utuzLbLtyNHpKNDNcQe5seZK5lIUdaAcy5FmvVrC8x2VWjSTGQ+WuFdNgavYk7Iek5PSv0joU9BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb414137dfd5fbf9cf837b6516686315b5a85f1564af6a684d3e833c6760bdb9","last_reissued_at":"2026-07-05T08:32:59.124672Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:59.124672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.12102","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:32:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wQcnEfjQ0P/pRNqccSU6SGpXpVrMkK0ouwFsYpwrqdHYomH05aAGD5QPE5ufynBJQY4lwe1snYzTcKXa2r5eBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T05:02:02.418575Z"},"content_sha256":"14c93a705b1cef3ebde631c240d933dc7c728652cd0bd9a6b111557d36909ee5","schema_version":"1.0","event_id":"sha256:14c93a705b1cef3ebde631c240d933dc7c728652cd0bd9a6b111557d36909ee5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:XNAUCN672X57TT4DPNSRM2DDCW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unified Embedding: Battle-Tested Feature Representations for Web-Scale ML Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.LG","authors_text":"Benjamin Coleman, Derek Zhiyuan Cheng, Ed H. Chi, Lichan Hong, Matthew Fahrbach, Ruoxi Wang, Wang-Cheng Kang","submitted_at":"2023-05-20T05:35:40Z","abstract_excerpt":"Learning high-quality feature embeddings efficiently and effectively is critical for the performance of web-scale machine learning systems. A typical model ingests hundreds of features with vocabularies on the order of millions to billions of tokens. The standard approach is to represent each feature value as a d-dimensional embedding, introducing hundreds of billions of parameters for extremely high-cardinality features. This bottleneck has led to substantial progress in alternative embedding algorithms. Many of these methods, however, make the assumption that each feature uses an independent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12102","kind":"arxiv","version":3},"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/2305.12102/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":"2026-07-05T08:32:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hjUa2Rg9hXhWvjAtxvrbxP3le0f7fxm6zcXMfip1Woi8PvNq2Div3ZPTn5+HfbyASnUDmGtPIhk1OaPbV/gRCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T05:02:02.418960Z"},"content_sha256":"a99098ed4938a00c273b6111ee1ed39b56743ee779c6732c0a186a4a0054b0dc","schema_version":"1.0","event_id":"sha256:a99098ed4938a00c273b6111ee1ed39b56743ee779c6732c0a186a4a0054b0dc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XNAUCN672X57TT4DPNSRM2DDCW/bundle.json","state_url":"https://pith.science/pith/XNAUCN672X57TT4DPNSRM2DDCW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XNAUCN672X57TT4DPNSRM2DDCW/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":"2026-07-26T05:02:02Z","links":{"resolver":"https://pith.science/pith/XNAUCN672X57TT4DPNSRM2DDCW","bundle":"https://pith.science/pith/XNAUCN672X57TT4DPNSRM2DDCW/bundle.json","state":"https://pith.science/pith/XNAUCN672X57TT4DPNSRM2DDCW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XNAUCN672X57TT4DPNSRM2DDCW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XNAUCN672X57TT4DPNSRM2DDCW","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":"ab8ec8b7fcde34253d06b74c3562a397deaa90b9ce5127780d74c6bed3960f95","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-20T05:35:40Z","title_canon_sha256":"6debfb91e9d9d03d4be377564666c3ed9022541709fc75e6d5e909deb78ae472"},"schema_version":"1.0","source":{"id":"2305.12102","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.12102","created_at":"2026-07-05T08:32:59Z"},{"alias_kind":"arxiv_version","alias_value":"2305.12102v3","created_at":"2026-07-05T08:32:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12102","created_at":"2026-07-05T08:32:59Z"},{"alias_kind":"pith_short_12","alias_value":"XNAUCN672X57","created_at":"2026-07-05T08:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"XNAUCN672X57TT4D","created_at":"2026-07-05T08:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"XNAUCN67","created_at":"2026-07-05T08:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:a99098ed4938a00c273b6111ee1ed39b56743ee779c6732c0a186a4a0054b0dc","target":"graph","created_at":"2026-07-05T08:32:59Z","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/2305.12102/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning high-quality feature embeddings efficiently and effectively is critical for the performance of web-scale machine learning systems. A typical model ingests hundreds of features with vocabularies on the order of millions to billions of tokens. The standard approach is to represent each feature value as a d-dimensional embedding, introducing hundreds of billions of parameters for extremely high-cardinality features. This bottleneck has led to substantial progress in alternative embedding algorithms. Many of these methods, however, make the assumption that each feature uses an independent","authors_text":"Benjamin Coleman, Derek Zhiyuan Cheng, Ed H. Chi, Lichan Hong, Matthew Fahrbach, Ruoxi Wang, Wang-Cheng Kang","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-20T05:35:40Z","title":"Unified Embedding: Battle-Tested Feature Representations for Web-Scale ML Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12102","kind":"arxiv","version":3},"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":"sha256:14c93a705b1cef3ebde631c240d933dc7c728652cd0bd9a6b111557d36909ee5","target":"record","created_at":"2026-07-05T08:32:59Z","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":"ab8ec8b7fcde34253d06b74c3562a397deaa90b9ce5127780d74c6bed3960f95","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-20T05:35:40Z","title_canon_sha256":"6debfb91e9d9d03d4be377564666c3ed9022541709fc75e6d5e909deb78ae472"},"schema_version":"1.0","source":{"id":"2305.12102","kind":"arxiv","version":3}},"canonical_sha256":"bb414137dfd5fbf9cf837b6516686315b5a85f1564af6a684d3e833c6760bdb9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb414137dfd5fbf9cf837b6516686315b5a85f1564af6a684d3e833c6760bdb9","first_computed_at":"2026-07-05T08:32:59.124672Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:59.124672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+bjK1545j+utuzLbLtyNHpKNDNcQe5seZK5lIUdaAcy5FmvVrC8x2VWjSTGQ+WuFdNgavYk7Iek5PSv0joU9BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:59.125186Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.12102","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:14c93a705b1cef3ebde631c240d933dc7c728652cd0bd9a6b111557d36909ee5","sha256:a99098ed4938a00c273b6111ee1ed39b56743ee779c6732c0a186a4a0054b0dc"],"state_sha256":"69bdfd06a13669164cdc9f9de5dd6926e9918a3a0129913317e5063fd162c20c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/sBsA5wy0DMXtPwLsKJjFIdAiQnHq+6iiVvaq3LE1IjX/D6p3Gps49SXlVTDkVciGTXIHpi/0ijbrhDqWOJOCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-26T05:02:02.421171Z","bundle_sha256":"f2c7d8001399a21c5f5ca454609c30ba3bf8ba227d97cb00b81b42870dbab488"}}