{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:TF6IPNIFWG4WS6FTHNDWJGND36","short_pith_number":"pith:TF6IPNIF","canonical_record":{"source":{"id":"2110.15154","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-10-28T14:26:42Z","cross_cats_sorted":[],"title_canon_sha256":"376935ad46a4d844f5d9f9075fbdf86f885e9bad02d8faa525615fb2b2bc3a85","abstract_canon_sha256":"e8e1394ec18ce75609dbe7938349ab58a606f1625a7a5a55bd3845b2a1f24d03"},"schema_version":"1.0"},"canonical_sha256":"997c87b505b1b96978b33b476499a3dfb2303c403e0455bf45ec12f52c5494f3","source":{"kind":"arxiv","id":"2110.15154","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.15154","created_at":"2026-07-05T03:26:52Z"},{"alias_kind":"arxiv_version","alias_value":"2110.15154v1","created_at":"2026-07-05T03:26:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.15154","created_at":"2026-07-05T03:26:52Z"},{"alias_kind":"pith_short_12","alias_value":"TF6IPNIFWG4W","created_at":"2026-07-05T03:26:52Z"},{"alias_kind":"pith_short_16","alias_value":"TF6IPNIFWG4WS6FT","created_at":"2026-07-05T03:26:52Z"},{"alias_kind":"pith_short_8","alias_value":"TF6IPNIF","created_at":"2026-07-05T03:26:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:TF6IPNIFWG4WS6FTHNDWJGND36","target":"record","payload":{"canonical_record":{"source":{"id":"2110.15154","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-10-28T14:26:42Z","cross_cats_sorted":[],"title_canon_sha256":"376935ad46a4d844f5d9f9075fbdf86f885e9bad02d8faa525615fb2b2bc3a85","abstract_canon_sha256":"e8e1394ec18ce75609dbe7938349ab58a606f1625a7a5a55bd3845b2a1f24d03"},"schema_version":"1.0"},"canonical_sha256":"997c87b505b1b96978b33b476499a3dfb2303c403e0455bf45ec12f52c5494f3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:26:52.279097Z","signature_b64":"qjekNyWgKKUx34cbnSKOt7dij3bCJBqyoiGmRa1cQYbWftzjgjnJgK9d/95sEPk7eTQN3eotfp/76yac5ka8Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"997c87b505b1b96978b33b476499a3dfb2303c403e0455bf45ec12f52c5494f3","last_reissued_at":"2026-07-05T03:26:52.278753Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:26:52.278753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.15154","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:26:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Dy7PdOOlJrX8rzyk//U5741NpwBMNxDBenub47bVbIxym7aUvlTr9nZRrRUmroveIbAjLybeyMZr1nHYK0eFAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T00:27:15.013174Z"},"content_sha256":"deac466ff34c494aa1d1077a253448c548eaf7603b0b09fa6509fd828d585d24","schema_version":"1.0","event_id":"sha256:deac466ff34c494aa1d1077a253448c548eaf7603b0b09fa6509fd828d585d24"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:TF6IPNIFWG4WS6FTHNDWJGND36","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cross-Batch Negative Sampling for Training Two-Tower Recommenders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Jieming Zhu, Jinpeng Wang, Xiuqiang He","submitted_at":"2021-10-28T14:26:42Z","abstract_excerpt":"The two-tower architecture has been widely applied for learning item and user representations, which is important for large-scale recommender systems. Many two-tower models are trained using various in-batch negative sampling strategies, where the effects of such strategies inherently rely on the size of mini-batches. However, training two-tower models with a large batch size is inefficient, as it demands a large volume of memory for item and user contents and consumes a lot of time for feature encoding. Interestingly, we find that neural encoders can output relatively stable features for the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.15154","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/2110.15154/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":"2026-07-05T03:26:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RtKeIANUktU99h4H5QWfiTUqANGByZbFMF0cnc9+Aj+kbu5lpxm14DcjGCd4tjUTrAckS3Rover8NsWMNKr6BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T00:27:15.013877Z"},"content_sha256":"b2d2496b5470af4cd859b7a672ce3746bd9c051ca87bca652f927934276678a3","schema_version":"1.0","event_id":"sha256:b2d2496b5470af4cd859b7a672ce3746bd9c051ca87bca652f927934276678a3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TF6IPNIFWG4WS6FTHNDWJGND36/bundle.json","state_url":"https://pith.science/pith/TF6IPNIFWG4WS6FTHNDWJGND36/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TF6IPNIFWG4WS6FTHNDWJGND36/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":"2026-08-05T00:27:15Z","links":{"resolver":"https://pith.science/pith/TF6IPNIFWG4WS6FTHNDWJGND36","bundle":"https://pith.science/pith/TF6IPNIFWG4WS6FTHNDWJGND36/bundle.json","state":"https://pith.science/pith/TF6IPNIFWG4WS6FTHNDWJGND36/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TF6IPNIFWG4WS6FTHNDWJGND36/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:TF6IPNIFWG4WS6FTHNDWJGND36","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":"e8e1394ec18ce75609dbe7938349ab58a606f1625a7a5a55bd3845b2a1f24d03","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-10-28T14:26:42Z","title_canon_sha256":"376935ad46a4d844f5d9f9075fbdf86f885e9bad02d8faa525615fb2b2bc3a85"},"schema_version":"1.0","source":{"id":"2110.15154","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.15154","created_at":"2026-07-05T03:26:52Z"},{"alias_kind":"arxiv_version","alias_value":"2110.15154v1","created_at":"2026-07-05T03:26:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.15154","created_at":"2026-07-05T03:26:52Z"},{"alias_kind":"pith_short_12","alias_value":"TF6IPNIFWG4W","created_at":"2026-07-05T03:26:52Z"},{"alias_kind":"pith_short_16","alias_value":"TF6IPNIFWG4WS6FT","created_at":"2026-07-05T03:26:52Z"},{"alias_kind":"pith_short_8","alias_value":"TF6IPNIF","created_at":"2026-07-05T03:26:52Z"}],"graph_snapshots":[{"event_id":"sha256:b2d2496b5470af4cd859b7a672ce3746bd9c051ca87bca652f927934276678a3","target":"graph","created_at":"2026-07-05T03:26:52Z","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/2110.15154/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The two-tower architecture has been widely applied for learning item and user representations, which is important for large-scale recommender systems. Many two-tower models are trained using various in-batch negative sampling strategies, where the effects of such strategies inherently rely on the size of mini-batches. However, training two-tower models with a large batch size is inefficient, as it demands a large volume of memory for item and user contents and consumes a lot of time for feature encoding. Interestingly, we find that neural encoders can output relatively stable features for the ","authors_text":"Jieming Zhu, Jinpeng Wang, Xiuqiang He","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-10-28T14:26:42Z","title":"Cross-Batch Negative Sampling for Training Two-Tower Recommenders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.15154","kind":"arxiv","version":1},"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:deac466ff34c494aa1d1077a253448c548eaf7603b0b09fa6509fd828d585d24","target":"record","created_at":"2026-07-05T03:26:52Z","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":"e8e1394ec18ce75609dbe7938349ab58a606f1625a7a5a55bd3845b2a1f24d03","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-10-28T14:26:42Z","title_canon_sha256":"376935ad46a4d844f5d9f9075fbdf86f885e9bad02d8faa525615fb2b2bc3a85"},"schema_version":"1.0","source":{"id":"2110.15154","kind":"arxiv","version":1}},"canonical_sha256":"997c87b505b1b96978b33b476499a3dfb2303c403e0455bf45ec12f52c5494f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"997c87b505b1b96978b33b476499a3dfb2303c403e0455bf45ec12f52c5494f3","first_computed_at":"2026-07-05T03:26:52.278753Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:26:52.278753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qjekNyWgKKUx34cbnSKOt7dij3bCJBqyoiGmRa1cQYbWftzjgjnJgK9d/95sEPk7eTQN3eotfp/76yac5ka8Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:26:52.279097Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.15154","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:deac466ff34c494aa1d1077a253448c548eaf7603b0b09fa6509fd828d585d24","sha256:b2d2496b5470af4cd859b7a672ce3746bd9c051ca87bca652f927934276678a3"],"state_sha256":"4cd92bc1406ceb47de13a316d9827a0cdbea3f99243c25835c02d79c46c8a99c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yQP4X5zG5dQN+esIMCKYb29DH/BLZaqps7My+Kaq5VB7Zyh9BZ5mYnBdOAOGTJ0AuKU5VPz6mIeceFa6qh1mAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T00:27:15.234349Z","bundle_sha256":"1f3eaa1654782006c46b83fe5007bd842213fd63004799912933cdb70c53d3b3"}}