{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WQ4OR5WG3AR6VYO27DN3EJ5O5Z","short_pith_number":"pith:WQ4OR5WG","canonical_record":{"source":{"id":"2505.19274","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-05-25T19:06:19Z","cross_cats_sorted":[],"title_canon_sha256":"0ffd7ad3a59e3961ecaf17e23841f6fa59288267e2295b57ccddb1a8be84e699","abstract_canon_sha256":"d7b980f1a1a44fa693d5efcaa1500da4b9318c47b2532f699521576a84ecc36d"},"schema_version":"1.0"},"canonical_sha256":"b438e8f6c6d823eae1daf8dbb227aeee556ac70475a719108e2b36962b95166c","source":{"kind":"arxiv","id":"2505.19274","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19274","created_at":"2026-07-05T11:09:27Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19274v1","created_at":"2026-07-05T11:09:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19274","created_at":"2026-07-05T11:09:27Z"},{"alias_kind":"pith_short_12","alias_value":"WQ4OR5WG3AR6","created_at":"2026-07-05T11:09:27Z"},{"alias_kind":"pith_short_16","alias_value":"WQ4OR5WG3AR6VYO2","created_at":"2026-07-05T11:09:27Z"},{"alias_kind":"pith_short_8","alias_value":"WQ4OR5WG","created_at":"2026-07-05T11:09:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WQ4OR5WG3AR6VYO27DN3EJ5O5Z","target":"record","payload":{"canonical_record":{"source":{"id":"2505.19274","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-05-25T19:06:19Z","cross_cats_sorted":[],"title_canon_sha256":"0ffd7ad3a59e3961ecaf17e23841f6fa59288267e2295b57ccddb1a8be84e699","abstract_canon_sha256":"d7b980f1a1a44fa693d5efcaa1500da4b9318c47b2532f699521576a84ecc36d"},"schema_version":"1.0"},"canonical_sha256":"b438e8f6c6d823eae1daf8dbb227aeee556ac70475a719108e2b36962b95166c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:27.346058Z","signature_b64":"95PJmOEhA8S7I3CTs6iVBzVmJ2CeBPYPS4obb49U8e/OR5FdfVtRHYH4WG7Ce8G4g7OPQmOV8EXHZcdO7IsWBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b438e8f6c6d823eae1daf8dbb227aeee556ac70475a719108e2b36962b95166c","last_reissued_at":"2026-07-05T11:09:27.345537Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:27.345537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.19274","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":"2026-07-05T11:09:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YMFe8wgcvw+LyWNbuPGYzSwucVK3YnPeOrfAIqs5ywqvcs7es7cbx/Fv5ZwQsSy/eATq+j/yK67O6BcIUAhRCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T02:39:12.647742Z"},"content_sha256":"49cbd1e3df03255a101a2a0e58cfab770bdad3083471c7e5307cc209ec4f0510","schema_version":"1.0","event_id":"sha256:49cbd1e3df03255a101a2a0e58cfab770bdad3083471c7e5307cc209ec4f0510"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WQ4OR5WG3AR6VYO27DN3EJ5O5Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Conventional Contrastive Learning Often Falls Short: Improving Dense Retrieval with Cross-Encoder Listwise Distillation and Synthetic Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Jimmy Lin, Manveer Singh Tamber, Suleman Kazi, Vivek Sourabh","submitted_at":"2025-05-25T19:06:19Z","abstract_excerpt":"We investigate improving the retrieval effectiveness of embedding models through the lens of corpus-specific fine-tuning. Prior work has shown that fine-tuning with queries generated using a dataset's retrieval corpus can boost retrieval effectiveness for the dataset. However, we find that surprisingly, fine-tuning using the conventional InfoNCE contrastive loss often reduces effectiveness in state-of-the-art models. To overcome this, we revisit cross-encoder listwise distillation and demonstrate that, unlike using contrastive learning alone, listwise distillation can help more consistently im"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19274","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/2505.19274/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":"2026-07-05T11:09:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G1+em2Z7jbVTCpIfPrVTh6/O1IZwkP3X1N2zLgk2kbeiZh4TV4kH0zoF5l4/EhMx2/Wyn7rEVys+Ao/jArmuBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T02:39:12.648444Z"},"content_sha256":"561e570eaa6caf7302e87c6688f98c730fd06c5ef99b403626a778ad0ab9414d","schema_version":"1.0","event_id":"sha256:561e570eaa6caf7302e87c6688f98c730fd06c5ef99b403626a778ad0ab9414d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WQ4OR5WG3AR6VYO27DN3EJ5O5Z/bundle.json","state_url":"https://pith.science/pith/WQ4OR5WG3AR6VYO27DN3EJ5O5Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WQ4OR5WG3AR6VYO27DN3EJ5O5Z/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":"2026-07-07T02:39:12Z","links":{"resolver":"https://pith.science/pith/WQ4OR5WG3AR6VYO27DN3EJ5O5Z","bundle":"https://pith.science/pith/WQ4OR5WG3AR6VYO27DN3EJ5O5Z/bundle.json","state":"https://pith.science/pith/WQ4OR5WG3AR6VYO27DN3EJ5O5Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WQ4OR5WG3AR6VYO27DN3EJ5O5Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WQ4OR5WG3AR6VYO27DN3EJ5O5Z","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":"d7b980f1a1a44fa693d5efcaa1500da4b9318c47b2532f699521576a84ecc36d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-05-25T19:06:19Z","title_canon_sha256":"0ffd7ad3a59e3961ecaf17e23841f6fa59288267e2295b57ccddb1a8be84e699"},"schema_version":"1.0","source":{"id":"2505.19274","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19274","created_at":"2026-07-05T11:09:27Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19274v1","created_at":"2026-07-05T11:09:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19274","created_at":"2026-07-05T11:09:27Z"},{"alias_kind":"pith_short_12","alias_value":"WQ4OR5WG3AR6","created_at":"2026-07-05T11:09:27Z"},{"alias_kind":"pith_short_16","alias_value":"WQ4OR5WG3AR6VYO2","created_at":"2026-07-05T11:09:27Z"},{"alias_kind":"pith_short_8","alias_value":"WQ4OR5WG","created_at":"2026-07-05T11:09:27Z"}],"graph_snapshots":[{"event_id":"sha256:561e570eaa6caf7302e87c6688f98c730fd06c5ef99b403626a778ad0ab9414d","target":"graph","created_at":"2026-07-05T11:09:27Z","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/2505.19274/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We investigate improving the retrieval effectiveness of embedding models through the lens of corpus-specific fine-tuning. Prior work has shown that fine-tuning with queries generated using a dataset's retrieval corpus can boost retrieval effectiveness for the dataset. However, we find that surprisingly, fine-tuning using the conventional InfoNCE contrastive loss often reduces effectiveness in state-of-the-art models. To overcome this, we revisit cross-encoder listwise distillation and demonstrate that, unlike using contrastive learning alone, listwise distillation can help more consistently im","authors_text":"Jimmy Lin, Manveer Singh Tamber, Suleman Kazi, Vivek Sourabh","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-05-25T19:06:19Z","title":"Conventional Contrastive Learning Often Falls Short: Improving Dense Retrieval with Cross-Encoder Listwise Distillation and Synthetic Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19274","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":"sha256:49cbd1e3df03255a101a2a0e58cfab770bdad3083471c7e5307cc209ec4f0510","target":"record","created_at":"2026-07-05T11:09:27Z","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":"d7b980f1a1a44fa693d5efcaa1500da4b9318c47b2532f699521576a84ecc36d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-05-25T19:06:19Z","title_canon_sha256":"0ffd7ad3a59e3961ecaf17e23841f6fa59288267e2295b57ccddb1a8be84e699"},"schema_version":"1.0","source":{"id":"2505.19274","kind":"arxiv","version":1}},"canonical_sha256":"b438e8f6c6d823eae1daf8dbb227aeee556ac70475a719108e2b36962b95166c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b438e8f6c6d823eae1daf8dbb227aeee556ac70475a719108e2b36962b95166c","first_computed_at":"2026-07-05T11:09:27.345537Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:27.345537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"95PJmOEhA8S7I3CTs6iVBzVmJ2CeBPYPS4obb49U8e/OR5FdfVtRHYH4WG7Ce8G4g7OPQmOV8EXHZcdO7IsWBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:27.346058Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.19274","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:49cbd1e3df03255a101a2a0e58cfab770bdad3083471c7e5307cc209ec4f0510","sha256:561e570eaa6caf7302e87c6688f98c730fd06c5ef99b403626a778ad0ab9414d"],"state_sha256":"0476d435b51b0d8a77803f73084ae9bff78277231db14683b799b398df1477e1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ly6FEe2yqdH3P67lhZYbmW+DAc71Rht5Sy978QWFDcDX/NatUYcxDZJvixY7C1HXsgT5TT2tLKZRxIuMebCeCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T02:39:12.651847Z","bundle_sha256":"70e195361c85d97bb692c1a491d38a34ff4eca0654ca457a5c9981ecedf08503"}}