{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:IZQ7P7RRZUOBCY4KWASH6FM4XK","short_pith_number":"pith:IZQ7P7RR","canonical_record":{"source":{"id":"2002.03932","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-10T16:44:00Z","cross_cats_sorted":["cs.CL","cs.IR","stat.ML"],"title_canon_sha256":"5557308ba3aff06aef66e3a9b58dc45c4a0bf283f3d0c5be34512637dc86b920","abstract_canon_sha256":"68c6f729db32cbcb4972ede5f50cad5c65bbb06e44ac08497b01a79fc0e69549"},"schema_version":"1.0"},"canonical_sha256":"4661f7fe31cd1c11638ab0247f159cbab6a78854813109aea626ddb95a36450a","source":{"kind":"arxiv","id":"2002.03932","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.03932","created_at":"2026-07-05T00:39:27Z"},{"alias_kind":"arxiv_version","alias_value":"2002.03932v1","created_at":"2026-07-05T00:39:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.03932","created_at":"2026-07-05T00:39:27Z"},{"alias_kind":"pith_short_12","alias_value":"IZQ7P7RRZUOB","created_at":"2026-07-05T00:39:27Z"},{"alias_kind":"pith_short_16","alias_value":"IZQ7P7RRZUOBCY4K","created_at":"2026-07-05T00:39:27Z"},{"alias_kind":"pith_short_8","alias_value":"IZQ7P7RR","created_at":"2026-07-05T00:39:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:IZQ7P7RRZUOBCY4KWASH6FM4XK","target":"record","payload":{"canonical_record":{"source":{"id":"2002.03932","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-10T16:44:00Z","cross_cats_sorted":["cs.CL","cs.IR","stat.ML"],"title_canon_sha256":"5557308ba3aff06aef66e3a9b58dc45c4a0bf283f3d0c5be34512637dc86b920","abstract_canon_sha256":"68c6f729db32cbcb4972ede5f50cad5c65bbb06e44ac08497b01a79fc0e69549"},"schema_version":"1.0"},"canonical_sha256":"4661f7fe31cd1c11638ab0247f159cbab6a78854813109aea626ddb95a36450a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:39:27.671655Z","signature_b64":"sh6tp2MKiLGiSW6qEPZH/KoPd4uLcz82VBYr6OCjN+AKl1dYgL5txqVu0yYLhOzoOHpi4GwtNINWb47zDFkTCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4661f7fe31cd1c11638ab0247f159cbab6a78854813109aea626ddb95a36450a","last_reissued_at":"2026-07-05T00:39:27.671238Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:39:27.671238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.03932","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":"2026-07-05T00:39:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LEaNIdADGxukCg3T4ehJ9n31f6dKs5DQ8EB7SApbHY566HGB9aOWinqnY4amL6lZRT+yMsFRN6+IgZIZ8UdfBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T03:27:28.816078Z"},"content_sha256":"46352bd9361eae6df6913077b2a5da483a2333de90445424beecd6678b8b4ecf","schema_version":"1.0","event_id":"sha256:46352bd9361eae6df6913077b2a5da483a2333de90445424beecd6678b8b4ecf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:IZQ7P7RRZUOBCY4KWASH6FM4XK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pre-training Tasks for Embedding-based Large-scale Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Felix X. Yu, Sanjiv Kumar, Wei-Cheng Chang, Yiming Yang, Yin-Wen Chang","submitted_at":"2020-02-10T16:44:00Z","abstract_excerpt":"We consider the large-scale query-document retrieval problem: given a query (e.g., a question), return the set of relevant documents (e.g., paragraphs containing the answer) from a large document corpus. This problem is often solved in two steps. The retrieval phase first reduces the solution space, returning a subset of candidate documents. The scoring phase then re-ranks the documents. Critically, the retrieval algorithm not only desires high recall but also requires to be highly efficient, returning candidates in time sublinear to the number of documents. Unlike the scoring phase witnessing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.03932","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/2002.03932/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":"2026-07-05T00:39:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f44xPCJPNyRvPadEwTZ5RS7uqCs/o6211H1pPY/S9LY/AYPteaHjg0dlAa/wnYTk/0uDmdajLOLzor5vEyVzDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T03:27:28.816975Z"},"content_sha256":"3b288f6cd36e3c8fe35fab535b3380a370bac7f7c744e70c051d1bc31178cb7c","schema_version":"1.0","event_id":"sha256:3b288f6cd36e3c8fe35fab535b3380a370bac7f7c744e70c051d1bc31178cb7c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IZQ7P7RRZUOBCY4KWASH6FM4XK/bundle.json","state_url":"https://pith.science/pith/IZQ7P7RRZUOBCY4KWASH6FM4XK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IZQ7P7RRZUOBCY4KWASH6FM4XK/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":"2026-08-14T03:27:28Z","links":{"resolver":"https://pith.science/pith/IZQ7P7RRZUOBCY4KWASH6FM4XK","bundle":"https://pith.science/pith/IZQ7P7RRZUOBCY4KWASH6FM4XK/bundle.json","state":"https://pith.science/pith/IZQ7P7RRZUOBCY4KWASH6FM4XK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IZQ7P7RRZUOBCY4KWASH6FM4XK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:IZQ7P7RRZUOBCY4KWASH6FM4XK","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":"68c6f729db32cbcb4972ede5f50cad5c65bbb06e44ac08497b01a79fc0e69549","cross_cats_sorted":["cs.CL","cs.IR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-10T16:44:00Z","title_canon_sha256":"5557308ba3aff06aef66e3a9b58dc45c4a0bf283f3d0c5be34512637dc86b920"},"schema_version":"1.0","source":{"id":"2002.03932","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.03932","created_at":"2026-07-05T00:39:27Z"},{"alias_kind":"arxiv_version","alias_value":"2002.03932v1","created_at":"2026-07-05T00:39:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.03932","created_at":"2026-07-05T00:39:27Z"},{"alias_kind":"pith_short_12","alias_value":"IZQ7P7RRZUOB","created_at":"2026-07-05T00:39:27Z"},{"alias_kind":"pith_short_16","alias_value":"IZQ7P7RRZUOBCY4K","created_at":"2026-07-05T00:39:27Z"},{"alias_kind":"pith_short_8","alias_value":"IZQ7P7RR","created_at":"2026-07-05T00:39:27Z"}],"graph_snapshots":[{"event_id":"sha256:3b288f6cd36e3c8fe35fab535b3380a370bac7f7c744e70c051d1bc31178cb7c","target":"graph","created_at":"2026-07-05T00:39:27Z","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/2002.03932/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider the large-scale query-document retrieval problem: given a query (e.g., a question), return the set of relevant documents (e.g., paragraphs containing the answer) from a large document corpus. This problem is often solved in two steps. The retrieval phase first reduces the solution space, returning a subset of candidate documents. The scoring phase then re-ranks the documents. Critically, the retrieval algorithm not only desires high recall but also requires to be highly efficient, returning candidates in time sublinear to the number of documents. Unlike the scoring phase witnessing","authors_text":"Felix X. Yu, Sanjiv Kumar, Wei-Cheng Chang, Yiming Yang, Yin-Wen Chang","cross_cats":["cs.CL","cs.IR","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-10T16:44:00Z","title":"Pre-training Tasks for Embedding-based Large-scale Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.03932","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":"sha256:46352bd9361eae6df6913077b2a5da483a2333de90445424beecd6678b8b4ecf","target":"record","created_at":"2026-07-05T00:39:27Z","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":"68c6f729db32cbcb4972ede5f50cad5c65bbb06e44ac08497b01a79fc0e69549","cross_cats_sorted":["cs.CL","cs.IR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-10T16:44:00Z","title_canon_sha256":"5557308ba3aff06aef66e3a9b58dc45c4a0bf283f3d0c5be34512637dc86b920"},"schema_version":"1.0","source":{"id":"2002.03932","kind":"arxiv","version":1}},"canonical_sha256":"4661f7fe31cd1c11638ab0247f159cbab6a78854813109aea626ddb95a36450a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4661f7fe31cd1c11638ab0247f159cbab6a78854813109aea626ddb95a36450a","first_computed_at":"2026-07-05T00:39:27.671238Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:39:27.671238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sh6tp2MKiLGiSW6qEPZH/KoPd4uLcz82VBYr6OCjN+AKl1dYgL5txqVu0yYLhOzoOHpi4GwtNINWb47zDFkTCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:39:27.671655Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.03932","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:46352bd9361eae6df6913077b2a5da483a2333de90445424beecd6678b8b4ecf","sha256:3b288f6cd36e3c8fe35fab535b3380a370bac7f7c744e70c051d1bc31178cb7c"],"state_sha256":"42aeebd689a461f559c83e7a6afd95be33902dbd566fe77706df029fb823190f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9xVqPPe/O7mD/asowzZYUTEeOpSxWPsZsjFSw/F4vPx/KUD+f7FAbaocf1xovmis3zgxjtgW9L20etDoy8T3AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T03:27:28.822473Z","bundle_sha256":"0f6f1094896670138ed96a6f855b6ea10463316b04feb77ebc06833ef0f9901c"}}