{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:O3NJZI7Y25OVCTBVIFP6VFVTIJ","short_pith_number":"pith:O3NJZI7Y","canonical_record":{"source":{"id":"2406.17262","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-25T04:03:04Z","cross_cats_sorted":[],"title_canon_sha256":"4670c3450ab33876094ef57a4f8a1d2818157fff9f7cb9065f45df8538897174","abstract_canon_sha256":"03d48f769dfb176f7b4bc4ac513f332beef4b0df6fb3c764690050a9c5e2dd33"},"schema_version":"1.0"},"canonical_sha256":"76da9ca3f8d75d514c35415fea96b3427c78c1dc5d1635ea69781cd39577ba0e","source":{"kind":"arxiv","id":"2406.17262","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.17262","created_at":"2026-07-05T08:36:31Z"},{"alias_kind":"arxiv_version","alias_value":"2406.17262v1","created_at":"2026-07-05T08:36:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17262","created_at":"2026-07-05T08:36:31Z"},{"alias_kind":"pith_short_12","alias_value":"O3NJZI7Y25OV","created_at":"2026-07-05T08:36:31Z"},{"alias_kind":"pith_short_16","alias_value":"O3NJZI7Y25OVCTBV","created_at":"2026-07-05T08:36:31Z"},{"alias_kind":"pith_short_8","alias_value":"O3NJZI7Y","created_at":"2026-07-05T08:36:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:O3NJZI7Y25OVCTBVIFP6VFVTIJ","target":"record","payload":{"canonical_record":{"source":{"id":"2406.17262","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-25T04:03:04Z","cross_cats_sorted":[],"title_canon_sha256":"4670c3450ab33876094ef57a4f8a1d2818157fff9f7cb9065f45df8538897174","abstract_canon_sha256":"03d48f769dfb176f7b4bc4ac513f332beef4b0df6fb3c764690050a9c5e2dd33"},"schema_version":"1.0"},"canonical_sha256":"76da9ca3f8d75d514c35415fea96b3427c78c1dc5d1635ea69781cd39577ba0e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:31.876842Z","signature_b64":"RxRtb43QYOHNL0zFTptW7AeECP6S3sEHsjWmBpjreMU+AHXU7HrJZ+64QdMf4P9CH1KT1UturUW6M0vraH1fDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76da9ca3f8d75d514c35415fea96b3427c78c1dc5d1635ea69781cd39577ba0e","last_reissued_at":"2026-07-05T08:36:31.876428Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:31.876428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.17262","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":"2026-07-05T08:36:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"unCfTabdk5fz0H/kki4ezMt+XZ2asOlRGX9aPOaKo6k2VJ+6MBMHegyddnC1pYleqKOCw/dV9Mv09E89wo77DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T14:51:06.048736Z"},"content_sha256":"59bd11229bb396f271aafc841b0f71f49e150560dfd329cbae7c2f7b5b828ff9","schema_version":"1.0","event_id":"sha256:59bd11229bb396f271aafc841b0f71f49e150560dfd329cbae7c2f7b5b828ff9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:O3NJZI7Y25OVCTBVIFP6VFVTIJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"D2LLM: Decomposed and Distilled Large Language Models for Semantic Search","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hang Yu, Jianguo Li, Jun Wang, Wei Zhang, Zihan Liao","submitted_at":"2024-06-25T04:03:04Z","abstract_excerpt":"The key challenge in semantic search is to create models that are both accurate and efficient in pinpointing relevant sentences for queries. While BERT-style bi-encoders excel in efficiency with pre-computed embeddings, they often miss subtle nuances in search tasks. Conversely, GPT-style LLMs with cross-encoder designs capture these nuances but are computationally intensive, hindering real-time applications. In this paper, we present D2LLMs-Decomposed and Distilled LLMs for semantic search-that combines the best of both worlds. We decompose a cross-encoder into an efficient bi-encoder integra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17262","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/2406.17262/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":"2026-07-05T08:36:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b2IRARbGoVR7h5RJRm2t4qH0aO4o+HRvrE4VI7tdsIg6ldsMp+t0AuqxlFBYj1z7vgKYDrT8R8gdQNwtjZ3AAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T14:51:06.049216Z"},"content_sha256":"b13cdd26f531123190d2f574563dc05fecf9d5b9032bb8847bd8c68fd36cba87","schema_version":"1.0","event_id":"sha256:b13cdd26f531123190d2f574563dc05fecf9d5b9032bb8847bd8c68fd36cba87"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O3NJZI7Y25OVCTBVIFP6VFVTIJ/bundle.json","state_url":"https://pith.science/pith/O3NJZI7Y25OVCTBVIFP6VFVTIJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O3NJZI7Y25OVCTBVIFP6VFVTIJ/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":"2026-08-05T14:51:06Z","links":{"resolver":"https://pith.science/pith/O3NJZI7Y25OVCTBVIFP6VFVTIJ","bundle":"https://pith.science/pith/O3NJZI7Y25OVCTBVIFP6VFVTIJ/bundle.json","state":"https://pith.science/pith/O3NJZI7Y25OVCTBVIFP6VFVTIJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O3NJZI7Y25OVCTBVIFP6VFVTIJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:O3NJZI7Y25OVCTBVIFP6VFVTIJ","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":"03d48f769dfb176f7b4bc4ac513f332beef4b0df6fb3c764690050a9c5e2dd33","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-25T04:03:04Z","title_canon_sha256":"4670c3450ab33876094ef57a4f8a1d2818157fff9f7cb9065f45df8538897174"},"schema_version":"1.0","source":{"id":"2406.17262","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.17262","created_at":"2026-07-05T08:36:31Z"},{"alias_kind":"arxiv_version","alias_value":"2406.17262v1","created_at":"2026-07-05T08:36:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17262","created_at":"2026-07-05T08:36:31Z"},{"alias_kind":"pith_short_12","alias_value":"O3NJZI7Y25OV","created_at":"2026-07-05T08:36:31Z"},{"alias_kind":"pith_short_16","alias_value":"O3NJZI7Y25OVCTBV","created_at":"2026-07-05T08:36:31Z"},{"alias_kind":"pith_short_8","alias_value":"O3NJZI7Y","created_at":"2026-07-05T08:36:31Z"}],"graph_snapshots":[{"event_id":"sha256:b13cdd26f531123190d2f574563dc05fecf9d5b9032bb8847bd8c68fd36cba87","target":"graph","created_at":"2026-07-05T08:36:31Z","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/2406.17262/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The key challenge in semantic search is to create models that are both accurate and efficient in pinpointing relevant sentences for queries. While BERT-style bi-encoders excel in efficiency with pre-computed embeddings, they often miss subtle nuances in search tasks. Conversely, GPT-style LLMs with cross-encoder designs capture these nuances but are computationally intensive, hindering real-time applications. In this paper, we present D2LLMs-Decomposed and Distilled LLMs for semantic search-that combines the best of both worlds. We decompose a cross-encoder into an efficient bi-encoder integra","authors_text":"Hang Yu, Jianguo Li, Jun Wang, Wei Zhang, Zihan Liao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-25T04:03:04Z","title":"D2LLM: Decomposed and Distilled Large Language Models for Semantic Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17262","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":"sha256:59bd11229bb396f271aafc841b0f71f49e150560dfd329cbae7c2f7b5b828ff9","target":"record","created_at":"2026-07-05T08:36:31Z","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":"03d48f769dfb176f7b4bc4ac513f332beef4b0df6fb3c764690050a9c5e2dd33","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-25T04:03:04Z","title_canon_sha256":"4670c3450ab33876094ef57a4f8a1d2818157fff9f7cb9065f45df8538897174"},"schema_version":"1.0","source":{"id":"2406.17262","kind":"arxiv","version":1}},"canonical_sha256":"76da9ca3f8d75d514c35415fea96b3427c78c1dc5d1635ea69781cd39577ba0e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"76da9ca3f8d75d514c35415fea96b3427c78c1dc5d1635ea69781cd39577ba0e","first_computed_at":"2026-07-05T08:36:31.876428Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:36:31.876428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RxRtb43QYOHNL0zFTptW7AeECP6S3sEHsjWmBpjreMU+AHXU7HrJZ+64QdMf4P9CH1KT1UturUW6M0vraH1fDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:36:31.876842Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.17262","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:59bd11229bb396f271aafc841b0f71f49e150560dfd329cbae7c2f7b5b828ff9","sha256:b13cdd26f531123190d2f574563dc05fecf9d5b9032bb8847bd8c68fd36cba87"],"state_sha256":"45deb0171125839e143e7ca7e50d3a8394571bcdeed2871bb4daad84f5e3824a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ARAjwhh9DMrRDK1dkIyU4wnDOB3RjVdNx/s240fZe13rBCQToaM4YqazmiWs1C5rz2H9ZkVBMGyzp0h/TKriBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T14:51:06.052549Z","bundle_sha256":"9d70116f52f4cb5d9922135d41866394d0e9493af2cfbda798f471de63dfe458"}}