{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PAS7HMCVPANYR3II4RCZ36OJHD","short_pith_number":"pith:PAS7HMCV","canonical_record":{"source":{"id":"2509.04139","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2025-09-04T12:11:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c325041a7888ab8c2c962c2460ab65a60545bd761986cefd28a60bb38fd2e7f1","abstract_canon_sha256":"dc4e9cda1cb30ec86fd5aa084e9629b9a9138f78195f1d1b66d66d483677d28a"},"schema_version":"1.0"},"canonical_sha256":"7825f3b055781b88ed08e4459df9c938e0b17e92c8b18196f47ee0ae5c53f695","source":{"kind":"arxiv","id":"2509.04139","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.04139","created_at":"2026-07-05T12:04:54Z"},{"alias_kind":"arxiv_version","alias_value":"2509.04139v1","created_at":"2026-07-05T12:04:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04139","created_at":"2026-07-05T12:04:54Z"},{"alias_kind":"pith_short_12","alias_value":"PAS7HMCVPANY","created_at":"2026-07-05T12:04:54Z"},{"alias_kind":"pith_short_16","alias_value":"PAS7HMCVPANYR3II","created_at":"2026-07-05T12:04:54Z"},{"alias_kind":"pith_short_8","alias_value":"PAS7HMCV","created_at":"2026-07-05T12:04:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PAS7HMCVPANYR3II4RCZ36OJHD","target":"record","payload":{"canonical_record":{"source":{"id":"2509.04139","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2025-09-04T12:11:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c325041a7888ab8c2c962c2460ab65a60545bd761986cefd28a60bb38fd2e7f1","abstract_canon_sha256":"dc4e9cda1cb30ec86fd5aa084e9629b9a9138f78195f1d1b66d66d483677d28a"},"schema_version":"1.0"},"canonical_sha256":"7825f3b055781b88ed08e4459df9c938e0b17e92c8b18196f47ee0ae5c53f695","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:54.125727Z","signature_b64":"XmXQaX+HSGxQkSZUIOIb/bkqWwJg6mWHbKugI/uQiGnuQ/zrzCPeYGqfS8DVPwlt/BInFpu2Iu7uagwcPbAmCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7825f3b055781b88ed08e4459df9c938e0b17e92c8b18196f47ee0ae5c53f695","last_reissued_at":"2026-07-05T12:04:54.125080Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:54.125080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.04139","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":"2026-07-05T12:04:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kTHsuNBrWCJ/Ku6MKEckY7087i5KMJehIQbvnCOUr2QZiCG+de1ShtN1/O+uWXvk+1uURSbgBLJF+6WQBFiuAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:54:54.863164Z"},"content_sha256":"9fb44645eb51b54a067f53bef6af7a6ce323fecf677595644309a618bbfe1958","schema_version":"1.0","event_id":"sha256:9fb44645eb51b54a067f53bef6af7a6ce323fecf677595644309a618bbfe1958"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PAS7HMCVPANYR3II4RCZ36OJHD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Technical Documents Retrieval for RAG","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Ka-Chun Fung, Kaiwen Xue, Kin-man Lam, Kwan-Ho Lin, Songjiang Lai, Tsun-Hin Cheung, Vincent Ng, Yan-Ming Choi","submitted_at":"2025-09-04T12:11:03Z","abstract_excerpt":"In this paper, we introduce Technical-Embeddings, a novel framework designed to optimize semantic retrieval in technical documentation, with applications in both hardware and software development. Our approach addresses the challenges of understanding and retrieving complex technical content by leveraging the capabilities of Large Language Models (LLMs). First, we enhance user queries by generating expanded representations that better capture user intent and improve dataset diversity, thereby enriching the fine-tuning process for embedding models. Second, we apply summary extraction techniques"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04139","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/2509.04139/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":"2026-07-05T12:04:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4N49g+6CYdgI1gRmGpOHQVlISqaMLfQzpSrsEWjOSnjaK4fdYuFAHFT6PlDOuHZD8c3DCleQ2O3cKDMG6nfwCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:54:54.863612Z"},"content_sha256":"d964f78b31300380555ffb3f6c33b8d7dee79df29e8aaa4052ce6be1b281d469","schema_version":"1.0","event_id":"sha256:d964f78b31300380555ffb3f6c33b8d7dee79df29e8aaa4052ce6be1b281d469"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PAS7HMCVPANYR3II4RCZ36OJHD/bundle.json","state_url":"https://pith.science/pith/PAS7HMCVPANYR3II4RCZ36OJHD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PAS7HMCVPANYR3II4RCZ36OJHD/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":"2026-07-09T05:54:54Z","links":{"resolver":"https://pith.science/pith/PAS7HMCVPANYR3II4RCZ36OJHD","bundle":"https://pith.science/pith/PAS7HMCVPANYR3II4RCZ36OJHD/bundle.json","state":"https://pith.science/pith/PAS7HMCVPANYR3II4RCZ36OJHD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PAS7HMCVPANYR3II4RCZ36OJHD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PAS7HMCVPANYR3II4RCZ36OJHD","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":"dc4e9cda1cb30ec86fd5aa084e9629b9a9138f78195f1d1b66d66d483677d28a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2025-09-04T12:11:03Z","title_canon_sha256":"c325041a7888ab8c2c962c2460ab65a60545bd761986cefd28a60bb38fd2e7f1"},"schema_version":"1.0","source":{"id":"2509.04139","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.04139","created_at":"2026-07-05T12:04:54Z"},{"alias_kind":"arxiv_version","alias_value":"2509.04139v1","created_at":"2026-07-05T12:04:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04139","created_at":"2026-07-05T12:04:54Z"},{"alias_kind":"pith_short_12","alias_value":"PAS7HMCVPANY","created_at":"2026-07-05T12:04:54Z"},{"alias_kind":"pith_short_16","alias_value":"PAS7HMCVPANYR3II","created_at":"2026-07-05T12:04:54Z"},{"alias_kind":"pith_short_8","alias_value":"PAS7HMCV","created_at":"2026-07-05T12:04:54Z"}],"graph_snapshots":[{"event_id":"sha256:d964f78b31300380555ffb3f6c33b8d7dee79df29e8aaa4052ce6be1b281d469","target":"graph","created_at":"2026-07-05T12:04:54Z","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/2509.04139/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we introduce Technical-Embeddings, a novel framework designed to optimize semantic retrieval in technical documentation, with applications in both hardware and software development. Our approach addresses the challenges of understanding and retrieving complex technical content by leveraging the capabilities of Large Language Models (LLMs). First, we enhance user queries by generating expanded representations that better capture user intent and improve dataset diversity, thereby enriching the fine-tuning process for embedding models. Second, we apply summary extraction techniques","authors_text":"Ka-Chun Fung, Kaiwen Xue, Kin-man Lam, Kwan-Ho Lin, Songjiang Lai, Tsun-Hin Cheung, Vincent Ng, Yan-Ming Choi","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2025-09-04T12:11:03Z","title":"Enhancing Technical Documents Retrieval for RAG"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04139","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":"sha256:9fb44645eb51b54a067f53bef6af7a6ce323fecf677595644309a618bbfe1958","target":"record","created_at":"2026-07-05T12:04:54Z","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":"dc4e9cda1cb30ec86fd5aa084e9629b9a9138f78195f1d1b66d66d483677d28a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2025-09-04T12:11:03Z","title_canon_sha256":"c325041a7888ab8c2c962c2460ab65a60545bd761986cefd28a60bb38fd2e7f1"},"schema_version":"1.0","source":{"id":"2509.04139","kind":"arxiv","version":1}},"canonical_sha256":"7825f3b055781b88ed08e4459df9c938e0b17e92c8b18196f47ee0ae5c53f695","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7825f3b055781b88ed08e4459df9c938e0b17e92c8b18196f47ee0ae5c53f695","first_computed_at":"2026-07-05T12:04:54.125080Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:04:54.125080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XmXQaX+HSGxQkSZUIOIb/bkqWwJg6mWHbKugI/uQiGnuQ/zrzCPeYGqfS8DVPwlt/BInFpu2Iu7uagwcPbAmCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:04:54.125727Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.04139","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9fb44645eb51b54a067f53bef6af7a6ce323fecf677595644309a618bbfe1958","sha256:d964f78b31300380555ffb3f6c33b8d7dee79df29e8aaa4052ce6be1b281d469"],"state_sha256":"149999cf0f6bc7703f8562fc16f231279554fabb131221354daeae02a50db4f3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9l+dhQSBT+2RmEgKTnttwM2mWYE+gmUClLVQ1Q4RUlIp3/Mp3axiJhaK9BomgZM9QMQqlZpbKO0VQWGNdG/KBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T05:54:54.866332Z","bundle_sha256":"daacf605569998dbfb5e8b8065c87ce6a270b1b76ace68510c022479cf280d28"}}