{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:YYRMUERRMPWJ3YX2AOMKRHRQI7","short_pith_number":"pith:YYRMUERR","canonical_record":{"source":{"id":"2310.16605","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-10-25T12:50:34Z","cross_cats_sorted":[],"title_canon_sha256":"1e4e4d015357a69b778b014f474bb59e4dd457d8f49acbb06ee32e5ad00845b1","abstract_canon_sha256":"c965b489a887f82ac97b10c25e73b7ded5e5a434b84b784c5e64c767e38a587e"},"schema_version":"1.0"},"canonical_sha256":"c622ca123163ec9de2fa0398a89e3047c9520df0ab5a47337e2e561a28a4c9a0","source":{"kind":"arxiv","id":"2310.16605","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.16605","created_at":"2026-07-05T09:19:52Z"},{"alias_kind":"arxiv_version","alias_value":"2310.16605v4","created_at":"2026-07-05T09:19:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16605","created_at":"2026-07-05T09:19:52Z"},{"alias_kind":"pith_short_12","alias_value":"YYRMUERRMPWJ","created_at":"2026-07-05T09:19:52Z"},{"alias_kind":"pith_short_16","alias_value":"YYRMUERRMPWJ3YX2","created_at":"2026-07-05T09:19:52Z"},{"alias_kind":"pith_short_8","alias_value":"YYRMUERR","created_at":"2026-07-05T09:19:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:YYRMUERRMPWJ3YX2AOMKRHRQI7","target":"record","payload":{"canonical_record":{"source":{"id":"2310.16605","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-10-25T12:50:34Z","cross_cats_sorted":[],"title_canon_sha256":"1e4e4d015357a69b778b014f474bb59e4dd457d8f49acbb06ee32e5ad00845b1","abstract_canon_sha256":"c965b489a887f82ac97b10c25e73b7ded5e5a434b84b784c5e64c767e38a587e"},"schema_version":"1.0"},"canonical_sha256":"c622ca123163ec9de2fa0398a89e3047c9520df0ab5a47337e2e561a28a4c9a0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:52.583699Z","signature_b64":"UNBbzyzYJa3ScBkdyeWpg1jwND2TA5XaNAVKyXq+St2fzkvOrHzjHu/vYlkMvG0iSZL2LjxQwh6FkfQCXH5vBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c622ca123163ec9de2fa0398a89e3047c9520df0ab5a47337e2e561a28a4c9a0","last_reissued_at":"2026-07-05T09:19:52.583225Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:52.583225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.16605","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":"2026-07-05T09:19:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t4DumS2WzzgiJQZsi/oWV9Izrv7m6hechPUXtqSNuinLsR7Vhh12TdWu4vQTqvPYlD9AVdll6GMQr8TKQvfFBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T21:47:43.803816Z"},"content_sha256":"69a2e1e7b6907a09e987c9ba035e5f59fc3e25caebc447f68ffbefdb81a42428","schema_version":"1.0","event_id":"sha256:69a2e1e7b6907a09e987c9ba035e5f59fc3e25caebc447f68ffbefdb81a42428"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:YYRMUERRMPWJ3YX2AOMKRHRQI7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Dense Retrievers' Robustness with Group-level Reweighting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chenyan Xiong, Peixuan Han, Zhenghao Liu, Zhiyuan Liu","submitted_at":"2023-10-25T12:50:34Z","abstract_excerpt":"The anchor-document data derived from web graphs offers a wealth of paired information for training dense retrieval models in an unsupervised manner. However, unsupervised data contains diverse patterns across the web graph and often exhibits significant imbalance, leading to suboptimal performance in underrepresented or difficult groups. In this paper, we introduce WebDRO, an efficient approach for clustering the web graph data and optimizing group weights to enhance the robustness of dense retrieval models. Initially, we build an embedding model for clustering anchor-document pairs. Specific"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16605","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/2310.16605/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":"2026-07-05T09:19:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9wnr59vyxnoNmhQHTuz+8Z4iKm0h4hQrBMMXXvMSjJE1AyxOF2N4PXoVwXQZL5nkvTqhU9rttxE1Zv5RY69VBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T21:47:43.805725Z"},"content_sha256":"aa961c54aee450d6b6c69be15fc2fc2250317d526a755ca2bd2efba4f4a9a6b0","schema_version":"1.0","event_id":"sha256:aa961c54aee450d6b6c69be15fc2fc2250317d526a755ca2bd2efba4f4a9a6b0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YYRMUERRMPWJ3YX2AOMKRHRQI7/bundle.json","state_url":"https://pith.science/pith/YYRMUERRMPWJ3YX2AOMKRHRQI7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YYRMUERRMPWJ3YX2AOMKRHRQI7/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":"2026-08-17T21:47:43Z","links":{"resolver":"https://pith.science/pith/YYRMUERRMPWJ3YX2AOMKRHRQI7","bundle":"https://pith.science/pith/YYRMUERRMPWJ3YX2AOMKRHRQI7/bundle.json","state":"https://pith.science/pith/YYRMUERRMPWJ3YX2AOMKRHRQI7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YYRMUERRMPWJ3YX2AOMKRHRQI7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YYRMUERRMPWJ3YX2AOMKRHRQI7","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":"c965b489a887f82ac97b10c25e73b7ded5e5a434b84b784c5e64c767e38a587e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-10-25T12:50:34Z","title_canon_sha256":"1e4e4d015357a69b778b014f474bb59e4dd457d8f49acbb06ee32e5ad00845b1"},"schema_version":"1.0","source":{"id":"2310.16605","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.16605","created_at":"2026-07-05T09:19:52Z"},{"alias_kind":"arxiv_version","alias_value":"2310.16605v4","created_at":"2026-07-05T09:19:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16605","created_at":"2026-07-05T09:19:52Z"},{"alias_kind":"pith_short_12","alias_value":"YYRMUERRMPWJ","created_at":"2026-07-05T09:19:52Z"},{"alias_kind":"pith_short_16","alias_value":"YYRMUERRMPWJ3YX2","created_at":"2026-07-05T09:19:52Z"},{"alias_kind":"pith_short_8","alias_value":"YYRMUERR","created_at":"2026-07-05T09:19:52Z"}],"graph_snapshots":[{"event_id":"sha256:aa961c54aee450d6b6c69be15fc2fc2250317d526a755ca2bd2efba4f4a9a6b0","target":"graph","created_at":"2026-07-05T09:19:52Z","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/2310.16605/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The anchor-document data derived from web graphs offers a wealth of paired information for training dense retrieval models in an unsupervised manner. However, unsupervised data contains diverse patterns across the web graph and often exhibits significant imbalance, leading to suboptimal performance in underrepresented or difficult groups. In this paper, we introduce WebDRO, an efficient approach for clustering the web graph data and optimizing group weights to enhance the robustness of dense retrieval models. Initially, we build an embedding model for clustering anchor-document pairs. Specific","authors_text":"Chenyan Xiong, Peixuan Han, Zhenghao Liu, Zhiyuan Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-10-25T12:50:34Z","title":"Enhancing Dense Retrievers' Robustness with Group-level Reweighting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16605","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":"sha256:69a2e1e7b6907a09e987c9ba035e5f59fc3e25caebc447f68ffbefdb81a42428","target":"record","created_at":"2026-07-05T09:19:52Z","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":"c965b489a887f82ac97b10c25e73b7ded5e5a434b84b784c5e64c767e38a587e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-10-25T12:50:34Z","title_canon_sha256":"1e4e4d015357a69b778b014f474bb59e4dd457d8f49acbb06ee32e5ad00845b1"},"schema_version":"1.0","source":{"id":"2310.16605","kind":"arxiv","version":4}},"canonical_sha256":"c622ca123163ec9de2fa0398a89e3047c9520df0ab5a47337e2e561a28a4c9a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c622ca123163ec9de2fa0398a89e3047c9520df0ab5a47337e2e561a28a4c9a0","first_computed_at":"2026-07-05T09:19:52.583225Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:19:52.583225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UNBbzyzYJa3ScBkdyeWpg1jwND2TA5XaNAVKyXq+St2fzkvOrHzjHu/vYlkMvG0iSZL2LjxQwh6FkfQCXH5vBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:19:52.583699Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.16605","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:69a2e1e7b6907a09e987c9ba035e5f59fc3e25caebc447f68ffbefdb81a42428","sha256:aa961c54aee450d6b6c69be15fc2fc2250317d526a755ca2bd2efba4f4a9a6b0"],"state_sha256":"9cd1df87cc96436aa9f71013844e5a60cf6faf60e3b4507cf12aec39bcdb5117"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3XT7R/vudp0cfzq2Synei0fc0lsF1PwUIuddkHY1+zlQP8xxAb7NyMQ+9Z2StvrAAUQ1lk5Uha8cRpqMv4tDBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T21:47:43.812708Z","bundle_sha256":"39598c7b22811dc434906ed01c5bb86d65b4b07b797d467e8248ecca60aed737"}}