{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:AWWYTM7XNBSICHPATBUYLQMXSY","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":"a1a0c8e7a9033fd43c673f01426330a6395c937b2f5fe1beced95a80d75c4b9c","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-05-18T15:43:09Z","title_canon_sha256":"0406d13cc28f1917201e4e77879a1fcb1247c9e2a6441827fe65d26907faf41c"},"schema_version":"1.0","source":{"id":"2305.11052","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.11052","created_at":"2026-07-05T06:11:29Z"},{"alias_kind":"arxiv_version","alias_value":"2305.11052v1","created_at":"2026-07-05T06:11:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11052","created_at":"2026-07-05T06:11:29Z"},{"alias_kind":"pith_short_12","alias_value":"AWWYTM7XNBSI","created_at":"2026-07-05T06:11:29Z"},{"alias_kind":"pith_short_16","alias_value":"AWWYTM7XNBSICHPA","created_at":"2026-07-05T06:11:29Z"},{"alias_kind":"pith_short_8","alias_value":"AWWYTM7X","created_at":"2026-07-05T06:11:29Z"}],"graph_snapshots":[{"event_id":"sha256:b803c918c2c1335da89b2830308ee0fe4becf5fa003f14ddeb3ccb48571d29b1","target":"graph","created_at":"2026-07-05T06:11:29Z","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/2305.11052/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dense retrieval has shown promise in the first-stage retrieval process when trained on in-domain labeled datasets. However, previous studies have found that dense retrieval is hard to generalize to unseen domains due to its weak modeling of domain-invariant and interpretable feature (i.e., matching signal between two texts, which is the essence of information retrieval). In this paper, we propose a novel method to improve the generalization of dense retrieval via capturing matching signal called BERM. Fully fine-grained expression and query-oriented saliency are two properties of the matching ","authors_text":"Huawei Shen, Liang Pang, Shicheng Xu, Xueqi Cheng","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-05-18T15:43:09Z","title":"BERM: Training the Balanced and Extractable Representation for Matching to Improve Generalization Ability of Dense Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11052","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:b3ffa474e4e6a594244d3de86f28f59080f38facd02032829d3269aee7e8c53d","target":"record","created_at":"2026-07-05T06:11:29Z","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":"a1a0c8e7a9033fd43c673f01426330a6395c937b2f5fe1beced95a80d75c4b9c","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-05-18T15:43:09Z","title_canon_sha256":"0406d13cc28f1917201e4e77879a1fcb1247c9e2a6441827fe65d26907faf41c"},"schema_version":"1.0","source":{"id":"2305.11052","kind":"arxiv","version":1}},"canonical_sha256":"05ad89b3f76864811de0986985c197961a8984d329741abb291f20a81f6fa3ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"05ad89b3f76864811de0986985c197961a8984d329741abb291f20a81f6fa3ae","first_computed_at":"2026-07-05T06:11:29.770612Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:11:29.770612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GeLK+C/wXyQ2Xyiw7hez8FAI0jBHwzYOXv94ww864zwQDKjGd/gq2Km9EYHSC15NOAQ31fvzWaKpcP08qrEdCA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:11:29.771094Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.11052","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b3ffa474e4e6a594244d3de86f28f59080f38facd02032829d3269aee7e8c53d","sha256:b803c918c2c1335da89b2830308ee0fe4becf5fa003f14ddeb3ccb48571d29b1"],"state_sha256":"f3750cd5b1e0834e8294a7c64fcf6f9e444545d9f22221e72a32e042bbb525c5"}