{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:BC5CKDZ4GYCOUF6FLFRQXAFESA","short_pith_number":"pith:BC5CKDZ4","canonical_record":{"source":{"id":"2007.12865","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-25T06:21:43Z","cross_cats_sorted":["cs.IR","stat.ML"],"title_canon_sha256":"5d9ea3691cb9aa8390984a7734cd5e12c211e03abb2124d836bbda64a764794d","abstract_canon_sha256":"fbf317567c2b2e8f28bccc135c007427c625fbcb05f113948c8e471781caec4a"},"schema_version":"1.0"},"canonical_sha256":"08ba250f3c3604ea17c559630b80a4900b467d6bacf6df35aeb0d4caacf184ee","source":{"kind":"arxiv","id":"2007.12865","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.12865","created_at":"2026-07-05T02:18:16Z"},{"alias_kind":"arxiv_version","alias_value":"2007.12865v4","created_at":"2026-07-05T02:18:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.12865","created_at":"2026-07-05T02:18:16Z"},{"alias_kind":"pith_short_12","alias_value":"BC5CKDZ4GYCO","created_at":"2026-07-05T02:18:16Z"},{"alias_kind":"pith_short_16","alias_value":"BC5CKDZ4GYCOUF6F","created_at":"2026-07-05T02:18:16Z"},{"alias_kind":"pith_short_8","alias_value":"BC5CKDZ4","created_at":"2026-07-05T02:18:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:BC5CKDZ4GYCOUF6FLFRQXAFESA","target":"record","payload":{"canonical_record":{"source":{"id":"2007.12865","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-25T06:21:43Z","cross_cats_sorted":["cs.IR","stat.ML"],"title_canon_sha256":"5d9ea3691cb9aa8390984a7734cd5e12c211e03abb2124d836bbda64a764794d","abstract_canon_sha256":"fbf317567c2b2e8f28bccc135c007427c625fbcb05f113948c8e471781caec4a"},"schema_version":"1.0"},"canonical_sha256":"08ba250f3c3604ea17c559630b80a4900b467d6bacf6df35aeb0d4caacf184ee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:18:16.676408Z","signature_b64":"p65SsVYH6G1W+ggRCTmf2wYJRIgEMIbaWOlnNEe6DMcxKEvHEzWFG6G2VJOk2z10tvOeaeTjlOEMppe5CmvjCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08ba250f3c3604ea17c559630b80a4900b467d6bacf6df35aeb0d4caacf184ee","last_reissued_at":"2026-07-05T02:18:16.675859Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:18:16.675859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.12865","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:18:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KzGCctti8BJn5UtZrINV8bpbkm4bLZX522cw1rVa4aCkbVlRon44YklXZjV2r9F3oZrMkGWhRkfNMFtqoqnrAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T20:42:53.643580Z"},"content_sha256":"2459455e54332bb0050b5d6e9c68b504b2f3353ff83d0e6eaa46b52e05f6885c","schema_version":"1.0","event_id":"sha256:2459455e54332bb0050b5d6e9c68b504b2f3353ff83d0e6eaa46b52e05f6885c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:BC5CKDZ4GYCOUF6FLFRQXAFESA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-supervised Learning for Large-scale Item Recommendations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aditya Menon, Derek Zhiyuan Cheng, Ed H. Chi, Evan Ettinger, Felix Yu, Jieqi Kang, Lichan Hong, Steve Tjoa, Tiansheng Yao, Ting Chen, Xinyang Yi","submitted_at":"2020-07-25T06:21:43Z","abstract_excerpt":"Large scale recommender models find most relevant items from huge catalogs, and they play a critical role in modern search and recommendation systems. To model the input space with large-vocab categorical features, a typical recommender model learns a joint embedding space through neural networks for both queries and items from user feedback data. However, with millions to billions of items in the corpus, users tend to provide feedback for a very small set of them, causing a power-law distribution. This makes the feedback data for long-tail items extremely sparse.\n  Inspired by the recent succ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.12865","kind":"arxiv","version":4},"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/2007.12865/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":"2026-07-05T02:18:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vhi/ydGGODKY1jFtvEWZ8hIZiHSst6xT1am2iqBUM+3gEwiC1I5SR1LWR5+Hd70QCz6ax8EKG5zTzTYDh/EHBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T20:42:53.644065Z"},"content_sha256":"500ac47961d35cd75260d7b77ecde5f0a82e1151bd179c2de5705707c82f86fe","schema_version":"1.0","event_id":"sha256:500ac47961d35cd75260d7b77ecde5f0a82e1151bd179c2de5705707c82f86fe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BC5CKDZ4GYCOUF6FLFRQXAFESA/bundle.json","state_url":"https://pith.science/pith/BC5CKDZ4GYCOUF6FLFRQXAFESA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BC5CKDZ4GYCOUF6FLFRQXAFESA/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":"2026-08-07T20:42:53Z","links":{"resolver":"https://pith.science/pith/BC5CKDZ4GYCOUF6FLFRQXAFESA","bundle":"https://pith.science/pith/BC5CKDZ4GYCOUF6FLFRQXAFESA/bundle.json","state":"https://pith.science/pith/BC5CKDZ4GYCOUF6FLFRQXAFESA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BC5CKDZ4GYCOUF6FLFRQXAFESA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:BC5CKDZ4GYCOUF6FLFRQXAFESA","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":"fbf317567c2b2e8f28bccc135c007427c625fbcb05f113948c8e471781caec4a","cross_cats_sorted":["cs.IR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-25T06:21:43Z","title_canon_sha256":"5d9ea3691cb9aa8390984a7734cd5e12c211e03abb2124d836bbda64a764794d"},"schema_version":"1.0","source":{"id":"2007.12865","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.12865","created_at":"2026-07-05T02:18:16Z"},{"alias_kind":"arxiv_version","alias_value":"2007.12865v4","created_at":"2026-07-05T02:18:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.12865","created_at":"2026-07-05T02:18:16Z"},{"alias_kind":"pith_short_12","alias_value":"BC5CKDZ4GYCO","created_at":"2026-07-05T02:18:16Z"},{"alias_kind":"pith_short_16","alias_value":"BC5CKDZ4GYCOUF6F","created_at":"2026-07-05T02:18:16Z"},{"alias_kind":"pith_short_8","alias_value":"BC5CKDZ4","created_at":"2026-07-05T02:18:16Z"}],"graph_snapshots":[{"event_id":"sha256:500ac47961d35cd75260d7b77ecde5f0a82e1151bd179c2de5705707c82f86fe","target":"graph","created_at":"2026-07-05T02:18:16Z","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/2007.12865/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large scale recommender models find most relevant items from huge catalogs, and they play a critical role in modern search and recommendation systems. To model the input space with large-vocab categorical features, a typical recommender model learns a joint embedding space through neural networks for both queries and items from user feedback data. However, with millions to billions of items in the corpus, users tend to provide feedback for a very small set of them, causing a power-law distribution. This makes the feedback data for long-tail items extremely sparse.\n  Inspired by the recent succ","authors_text":"Aditya Menon, Derek Zhiyuan Cheng, Ed H. Chi, Evan Ettinger, Felix Yu, Jieqi Kang, Lichan Hong, Steve Tjoa, Tiansheng Yao, Ting Chen, Xinyang Yi","cross_cats":["cs.IR","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-25T06:21:43Z","title":"Self-supervised Learning for Large-scale Item Recommendations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.12865","kind":"arxiv","version":4},"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":"sha256:2459455e54332bb0050b5d6e9c68b504b2f3353ff83d0e6eaa46b52e05f6885c","target":"record","created_at":"2026-07-05T02:18:16Z","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":"fbf317567c2b2e8f28bccc135c007427c625fbcb05f113948c8e471781caec4a","cross_cats_sorted":["cs.IR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-25T06:21:43Z","title_canon_sha256":"5d9ea3691cb9aa8390984a7734cd5e12c211e03abb2124d836bbda64a764794d"},"schema_version":"1.0","source":{"id":"2007.12865","kind":"arxiv","version":4}},"canonical_sha256":"08ba250f3c3604ea17c559630b80a4900b467d6bacf6df35aeb0d4caacf184ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08ba250f3c3604ea17c559630b80a4900b467d6bacf6df35aeb0d4caacf184ee","first_computed_at":"2026-07-05T02:18:16.675859Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:18:16.675859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p65SsVYH6G1W+ggRCTmf2wYJRIgEMIbaWOlnNEe6DMcxKEvHEzWFG6G2VJOk2z10tvOeaeTjlOEMppe5CmvjCw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:18:16.676408Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.12865","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2459455e54332bb0050b5d6e9c68b504b2f3353ff83d0e6eaa46b52e05f6885c","sha256:500ac47961d35cd75260d7b77ecde5f0a82e1151bd179c2de5705707c82f86fe"],"state_sha256":"432f87d3087ae426ac7cafc99d91801af43811887a72f57ff0ea8deb541508b4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8W5pb1gLIspXwDE33ddujF7HObugwRUx09CRj6dpo5dKi9IpsNOe0vl20iqP2MB0Pa/VxxOsaOnA9tf3zkb+DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T20:42:53.648710Z","bundle_sha256":"0e6d06a038d78a62d1bdba764b66c4f0b83e99f8b748a19f0b68995e873d257a"}}