{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SMSSSSHWPSXPMOERH7BY6BLJ2G","short_pith_number":"pith:SMSSSSHW","canonical_record":{"source":{"id":"2606.01304","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-31T15:48:30Z","cross_cats_sorted":[],"title_canon_sha256":"7abba1768d83521b12c6db5d87ea6e5e90b64ad0e350ab110fb0915c4de14cfa","abstract_canon_sha256":"eaf3171053492740462d262da45cf20df6ee12f3f74da64938d384f099b3d5df"},"schema_version":"1.0"},"canonical_sha256":"93252948f67caef638913fc38f0569d1b03a14b50d21f4807a7a522a284b21b3","source":{"kind":"arxiv","id":"2606.01304","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01304","created_at":"2026-06-02T02:04:29Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01304v1","created_at":"2026-06-02T02:04:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01304","created_at":"2026-06-02T02:04:29Z"},{"alias_kind":"pith_short_12","alias_value":"SMSSSSHWPSXP","created_at":"2026-06-02T02:04:29Z"},{"alias_kind":"pith_short_16","alias_value":"SMSSSSHWPSXPMOER","created_at":"2026-06-02T02:04:29Z"},{"alias_kind":"pith_short_8","alias_value":"SMSSSSHW","created_at":"2026-06-02T02:04:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SMSSSSHWPSXPMOERH7BY6BLJ2G","target":"record","payload":{"canonical_record":{"source":{"id":"2606.01304","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-31T15:48:30Z","cross_cats_sorted":[],"title_canon_sha256":"7abba1768d83521b12c6db5d87ea6e5e90b64ad0e350ab110fb0915c4de14cfa","abstract_canon_sha256":"eaf3171053492740462d262da45cf20df6ee12f3f74da64938d384f099b3d5df"},"schema_version":"1.0"},"canonical_sha256":"93252948f67caef638913fc38f0569d1b03a14b50d21f4807a7a522a284b21b3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:29.604326Z","signature_b64":"Zi5SzAkVGpHqHVZzfWs+n7oF6tMYCY2UHgOEYOLfFF+0yWKGvbjlGhMGOYRAcb489gvbZ0O2uLrCnPwjGSB3Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93252948f67caef638913fc38f0569d1b03a14b50d21f4807a7a522a284b21b3","last_reissued_at":"2026-06-02T02:04:29.603905Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:29.603905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.01304","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":"2026-06-02T02:04:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y/cqSvVoXW9tX3pX6d/jesYawWfIYescxjrADkc8Jv7YUN6+BJLWjxTc89sTv+kQIsk5Ik07nLWV8+aDVfVyDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T12:47:05.140633Z"},"content_sha256":"e7dc77879c6f3cbef8f588c1615d4d29fc51dec2304998fe73cc4050bdc32f7c","schema_version":"1.0","event_id":"sha256:e7dc77879c6f3cbef8f588c1615d4d29fc51dec2304998fe73cc4050bdc32f7c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SMSSSSHWPSXPMOERH7BY6BLJ2G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When Hard Negatives Hurt: Bridging the Generative-Discriminative Gap in Hard Negative Synthesis for Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fengyuan Lu, Gang Wang, Hai-Tao Zheng, Jieming Zhu, Jingyu Li, Jiwei Tang, Kuicai Dong, Qianhui Zhu, Wang Jiaheng, Xiaopeng Li, Zhaocheng Du, Zhicheng Zhang","submitted_at":"2026-05-31T15:48:30Z","abstract_excerpt":"Hard negative mining has become the dominant strategy for training retrievers, yet it faces intrinsic limitations: negatives are bounded by corpus availability, selected by retriever score rather than diagnostic value, and increasingly contaminated by false positives as the retriever improves. LLM-based synthesis offers a principled alternative, where negatives that are unconstrained, targeted, and free from false positive risk. But we show that naively incorporating generated negatives into contrastive learning often degrades retrieval performance. We identify and formalize the root cause as "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01304","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/2606.01304/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":"2026-06-02T02:04:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NUdv8p4ecU58aWc1wIl0WzkU9wNGuQXw7rfqVPiLKQRAP6zNa879appLEpyHVSVBLrKinJwarMq0d/5k3XI2Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T12:47:05.141018Z"},"content_sha256":"a3f277ba39e5e2c0c37984ca67ba6579fefb2c3b0d9b9ff74aea02cd7a68ed74","schema_version":"1.0","event_id":"sha256:a3f277ba39e5e2c0c37984ca67ba6579fefb2c3b0d9b9ff74aea02cd7a68ed74"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SMSSSSHWPSXPMOERH7BY6BLJ2G/bundle.json","state_url":"https://pith.science/pith/SMSSSSHWPSXPMOERH7BY6BLJ2G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SMSSSSHWPSXPMOERH7BY6BLJ2G/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":"2026-06-05T12:47:05Z","links":{"resolver":"https://pith.science/pith/SMSSSSHWPSXPMOERH7BY6BLJ2G","bundle":"https://pith.science/pith/SMSSSSHWPSXPMOERH7BY6BLJ2G/bundle.json","state":"https://pith.science/pith/SMSSSSHWPSXPMOERH7BY6BLJ2G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SMSSSSHWPSXPMOERH7BY6BLJ2G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SMSSSSHWPSXPMOERH7BY6BLJ2G","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":"eaf3171053492740462d262da45cf20df6ee12f3f74da64938d384f099b3d5df","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-31T15:48:30Z","title_canon_sha256":"7abba1768d83521b12c6db5d87ea6e5e90b64ad0e350ab110fb0915c4de14cfa"},"schema_version":"1.0","source":{"id":"2606.01304","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01304","created_at":"2026-06-02T02:04:29Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01304v1","created_at":"2026-06-02T02:04:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01304","created_at":"2026-06-02T02:04:29Z"},{"alias_kind":"pith_short_12","alias_value":"SMSSSSHWPSXP","created_at":"2026-06-02T02:04:29Z"},{"alias_kind":"pith_short_16","alias_value":"SMSSSSHWPSXPMOER","created_at":"2026-06-02T02:04:29Z"},{"alias_kind":"pith_short_8","alias_value":"SMSSSSHW","created_at":"2026-06-02T02:04:29Z"}],"graph_snapshots":[{"event_id":"sha256:a3f277ba39e5e2c0c37984ca67ba6579fefb2c3b0d9b9ff74aea02cd7a68ed74","target":"graph","created_at":"2026-06-02T02:04:29Z","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/2606.01304/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hard negative mining has become the dominant strategy for training retrievers, yet it faces intrinsic limitations: negatives are bounded by corpus availability, selected by retriever score rather than diagnostic value, and increasingly contaminated by false positives as the retriever improves. LLM-based synthesis offers a principled alternative, where negatives that are unconstrained, targeted, and free from false positive risk. But we show that naively incorporating generated negatives into contrastive learning often degrades retrieval performance. We identify and formalize the root cause as ","authors_text":"Fengyuan Lu, Gang Wang, Hai-Tao Zheng, Jieming Zhu, Jingyu Li, Jiwei Tang, Kuicai Dong, Qianhui Zhu, Wang Jiaheng, Xiaopeng Li, Zhaocheng Du, Zhicheng Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-31T15:48:30Z","title":"When Hard Negatives Hurt: Bridging the Generative-Discriminative Gap in Hard Negative Synthesis for Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01304","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:e7dc77879c6f3cbef8f588c1615d4d29fc51dec2304998fe73cc4050bdc32f7c","target":"record","created_at":"2026-06-02T02:04:29Z","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":"eaf3171053492740462d262da45cf20df6ee12f3f74da64938d384f099b3d5df","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-31T15:48:30Z","title_canon_sha256":"7abba1768d83521b12c6db5d87ea6e5e90b64ad0e350ab110fb0915c4de14cfa"},"schema_version":"1.0","source":{"id":"2606.01304","kind":"arxiv","version":1}},"canonical_sha256":"93252948f67caef638913fc38f0569d1b03a14b50d21f4807a7a522a284b21b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"93252948f67caef638913fc38f0569d1b03a14b50d21f4807a7a522a284b21b3","first_computed_at":"2026-06-02T02:04:29.603905Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:29.603905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zi5SzAkVGpHqHVZzfWs+n7oF6tMYCY2UHgOEYOLfFF+0yWKGvbjlGhMGOYRAcb489gvbZ0O2uLrCnPwjGSB3Bg==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:29.604326Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.01304","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e7dc77879c6f3cbef8f588c1615d4d29fc51dec2304998fe73cc4050bdc32f7c","sha256:a3f277ba39e5e2c0c37984ca67ba6579fefb2c3b0d9b9ff74aea02cd7a68ed74"],"state_sha256":"c0d1d26626870d1e05c1bc41de2c64a53de83f4b60c382bc8a570e4a3f451c06"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u9HPYikKqXqBSIVjwvljFYekR62eKAe8E1457Mw5DGGpYLk5dAVZGmcrYuvMtQHW/GsmgfoIHZe8MvTAHl4vBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T12:47:05.143177Z","bundle_sha256":"de52fa9c41c5402f760940cfa435b9dc2673cfd83b823c0de4c53362d04d7698"}}