{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:E4HBRODJICGWDHKBST4MIJ4RLP","short_pith_number":"pith:E4HBRODJ","canonical_record":{"source":{"id":"2507.05617","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-08T02:54:15Z","cross_cats_sorted":[],"title_canon_sha256":"3fad537d9bfbf2933e4fdb8ca9349c260771bdc7816e7c87dcf68170cd253620","abstract_canon_sha256":"f750d98a679309330a506cd0dee9f6f0865f1ded91b1de77a0d7897199423701"},"schema_version":"1.0"},"canonical_sha256":"270e18b869408d619d4194f8c427915bcd2606423d69f58b0f99f593eef229e7","source":{"kind":"arxiv","id":"2507.05617","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.05617","created_at":"2026-07-05T11:33:33Z"},{"alias_kind":"arxiv_version","alias_value":"2507.05617v1","created_at":"2026-07-05T11:33:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05617","created_at":"2026-07-05T11:33:33Z"},{"alias_kind":"pith_short_12","alias_value":"E4HBRODJICGW","created_at":"2026-07-05T11:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"E4HBRODJICGWDHKB","created_at":"2026-07-05T11:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"E4HBRODJ","created_at":"2026-07-05T11:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:E4HBRODJICGWDHKBST4MIJ4RLP","target":"record","payload":{"canonical_record":{"source":{"id":"2507.05617","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-08T02:54:15Z","cross_cats_sorted":[],"title_canon_sha256":"3fad537d9bfbf2933e4fdb8ca9349c260771bdc7816e7c87dcf68170cd253620","abstract_canon_sha256":"f750d98a679309330a506cd0dee9f6f0865f1ded91b1de77a0d7897199423701"},"schema_version":"1.0"},"canonical_sha256":"270e18b869408d619d4194f8c427915bcd2606423d69f58b0f99f593eef229e7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:33.505198Z","signature_b64":"RPeSW8bDVzo4Dlp/BrvfI9SIEEuuW8iZjsJ+mO54Yj+Z08m7RV8fmYw0KgS4tbpoAURTVZOkjaH4kFxPhzmHBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"270e18b869408d619d4194f8c427915bcd2606423d69f58b0f99f593eef229e7","last_reissued_at":"2026-07-05T11:33:33.504819Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:33.504819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.05617","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":"2026-07-05T11:33:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v3XwWS6MKmjejj2Ed/eK28I+UBNpsqWvrmSodoLtlNbw1gpvEO9POVb/uDrZwEgX7p/dAnM5SDkctdTfY245CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:31:43.081012Z"},"content_sha256":"6e911be3266650096822cb3de4854490695b5541df2d93813ce84a5c7f9ccd80","schema_version":"1.0","event_id":"sha256:6e911be3266650096822cb3de4854490695b5541df2d93813ce84a5c7f9ccd80"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:E4HBRODJICGWDHKBST4MIJ4RLP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Flipping Knowledge Distillation: Leveraging Small Models' Expertise to Enhance LLMs in Text Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jing Xiang, Kaiyang Wan, Mingzhe Li, Qishen Zhang, Xiuying Chen","submitted_at":"2025-07-08T02:54:15Z","abstract_excerpt":"Knowledge distillation typically involves transferring knowledge from a Large Language Model (LLM) to a Smaller Language Model (SLM). However, in tasks such as text matching, fine-tuned smaller models often yield more effective domain-specific representations, as they focus on optimizing the similarity of input pairs. To leverage both the specialized strengths of small models and the rich semantic understanding of LLMs, we introduce a flipped knowledge distillation paradigm, where LLM learns from SLM. Specifically, we address the architectural gap between decoder-only LLMs and smaller encoder-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05617","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/2507.05617/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":"2026-07-05T11:33:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HE7eNUCj6zvwMjGDrpz0O5tQC+wpqjHQtyHzNcNpf4wWIBQp5KTos1YSxiKmCfevKUNkm3EZ9kq798HhBD7JCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:31:43.081508Z"},"content_sha256":"3c4895b0443963486622dada91176cf27348530fa939e6b8cea96575f3f7498b","schema_version":"1.0","event_id":"sha256:3c4895b0443963486622dada91176cf27348530fa939e6b8cea96575f3f7498b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E4HBRODJICGWDHKBST4MIJ4RLP/bundle.json","state_url":"https://pith.science/pith/E4HBRODJICGWDHKBST4MIJ4RLP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E4HBRODJICGWDHKBST4MIJ4RLP/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":"2026-08-08T02:31:43Z","links":{"resolver":"https://pith.science/pith/E4HBRODJICGWDHKBST4MIJ4RLP","bundle":"https://pith.science/pith/E4HBRODJICGWDHKBST4MIJ4RLP/bundle.json","state":"https://pith.science/pith/E4HBRODJICGWDHKBST4MIJ4RLP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E4HBRODJICGWDHKBST4MIJ4RLP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:E4HBRODJICGWDHKBST4MIJ4RLP","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":"f750d98a679309330a506cd0dee9f6f0865f1ded91b1de77a0d7897199423701","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-08T02:54:15Z","title_canon_sha256":"3fad537d9bfbf2933e4fdb8ca9349c260771bdc7816e7c87dcf68170cd253620"},"schema_version":"1.0","source":{"id":"2507.05617","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.05617","created_at":"2026-07-05T11:33:33Z"},{"alias_kind":"arxiv_version","alias_value":"2507.05617v1","created_at":"2026-07-05T11:33:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05617","created_at":"2026-07-05T11:33:33Z"},{"alias_kind":"pith_short_12","alias_value":"E4HBRODJICGW","created_at":"2026-07-05T11:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"E4HBRODJICGWDHKB","created_at":"2026-07-05T11:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"E4HBRODJ","created_at":"2026-07-05T11:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:3c4895b0443963486622dada91176cf27348530fa939e6b8cea96575f3f7498b","target":"graph","created_at":"2026-07-05T11:33:33Z","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/2507.05617/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Knowledge distillation typically involves transferring knowledge from a Large Language Model (LLM) to a Smaller Language Model (SLM). However, in tasks such as text matching, fine-tuned smaller models often yield more effective domain-specific representations, as they focus on optimizing the similarity of input pairs. To leverage both the specialized strengths of small models and the rich semantic understanding of LLMs, we introduce a flipped knowledge distillation paradigm, where LLM learns from SLM. Specifically, we address the architectural gap between decoder-only LLMs and smaller encoder-","authors_text":"Jing Xiang, Kaiyang Wan, Mingzhe Li, Qishen Zhang, Xiuying Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-08T02:54:15Z","title":"Flipping Knowledge Distillation: Leveraging Small Models' Expertise to Enhance LLMs in Text Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05617","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":"sha256:6e911be3266650096822cb3de4854490695b5541df2d93813ce84a5c7f9ccd80","target":"record","created_at":"2026-07-05T11:33:33Z","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":"f750d98a679309330a506cd0dee9f6f0865f1ded91b1de77a0d7897199423701","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-08T02:54:15Z","title_canon_sha256":"3fad537d9bfbf2933e4fdb8ca9349c260771bdc7816e7c87dcf68170cd253620"},"schema_version":"1.0","source":{"id":"2507.05617","kind":"arxiv","version":1}},"canonical_sha256":"270e18b869408d619d4194f8c427915bcd2606423d69f58b0f99f593eef229e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"270e18b869408d619d4194f8c427915bcd2606423d69f58b0f99f593eef229e7","first_computed_at":"2026-07-05T11:33:33.504819Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:33.504819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RPeSW8bDVzo4Dlp/BrvfI9SIEEuuW8iZjsJ+mO54Yj+Z08m7RV8fmYw0KgS4tbpoAURTVZOkjaH4kFxPhzmHBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:33.505198Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.05617","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e911be3266650096822cb3de4854490695b5541df2d93813ce84a5c7f9ccd80","sha256:3c4895b0443963486622dada91176cf27348530fa939e6b8cea96575f3f7498b"],"state_sha256":"43c035c03224bae92c5b8e89a18af2f017b70db4d9e0c40b7c178924f5ae7d6d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f6ALn0yFn0W3VVXDdunMyf27YjWjSBg0tPXUiGMiptVtCO+10mY/yqzdh1mgtVo05aCHGsfmOURWJ5ANyhvcAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T02:31:43.086222Z","bundle_sha256":"2dae504066f188f894441e1cea933b49c4e2b1f2f2db439f5e56e11c767442c8"}}