{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:W3WUYNPWKQAXUZUDG2HXVVYEL5","short_pith_number":"pith:W3WUYNPW","canonical_record":{"source":{"id":"2506.00049","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-28T18:39:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e10c367824cb7ef6c81f58fc9939b2126f27f586b9d6e9e222f01f5133efdc10","abstract_canon_sha256":"fa3efb6795950dac763f95e02c240c86dc88c147103944a5341ba2e7cb8a7a3a"},"schema_version":"1.0"},"canonical_sha256":"b6ed4c35f654017a6683368f7ad7045f670d2de898042390364c7d5afa51103f","source":{"kind":"arxiv","id":"2506.00049","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00049","created_at":"2026-07-05T11:13:28Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00049v1","created_at":"2026-07-05T11:13:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00049","created_at":"2026-07-05T11:13:28Z"},{"alias_kind":"pith_short_12","alias_value":"W3WUYNPWKQAX","created_at":"2026-07-05T11:13:28Z"},{"alias_kind":"pith_short_16","alias_value":"W3WUYNPWKQAXUZUD","created_at":"2026-07-05T11:13:28Z"},{"alias_kind":"pith_short_8","alias_value":"W3WUYNPW","created_at":"2026-07-05T11:13:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:W3WUYNPWKQAXUZUDG2HXVVYEL5","target":"record","payload":{"canonical_record":{"source":{"id":"2506.00049","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-28T18:39:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e10c367824cb7ef6c81f58fc9939b2126f27f586b9d6e9e222f01f5133efdc10","abstract_canon_sha256":"fa3efb6795950dac763f95e02c240c86dc88c147103944a5341ba2e7cb8a7a3a"},"schema_version":"1.0"},"canonical_sha256":"b6ed4c35f654017a6683368f7ad7045f670d2de898042390364c7d5afa51103f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:28.121707Z","signature_b64":"5CLDd/gBzzirRHzIvJVeIhj7o8WrsdfzXPSBRIbjoDPDpw/wOqPkc7QmZhofBxZRpQW4Yj/AMaKwOSKV84hCAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6ed4c35f654017a6683368f7ad7045f670d2de898042390364c7d5afa51103f","last_reissued_at":"2026-07-05T11:13:28.121106Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:28.121106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.00049","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":"2026-07-05T11:13:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yEaoWkKwyh7jhnS/+ctX37Y+QulvTrCj5a4ffYV0vE6KoR9PyUUgmC+C/zf+Q3ZjOcLZluXwFEDMtWQncPNnBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T01:19:21.322332Z"},"content_sha256":"8fb33d185cafdfd36c27cdaadbd27c7b3b9a3ba76d7660f5ce887e27a1b38616","schema_version":"1.0","event_id":"sha256:8fb33d185cafdfd36c27cdaadbd27c7b3b9a3ba76d7660f5ce887e27a1b38616"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:W3WUYNPWKQAXUZUDG2HXVVYEL5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Arjun Rao, Hanieh Alipour, Nick Pendar","submitted_at":"2025-05-28T18:39:40Z","abstract_excerpt":"This paper presents a comparison of embedding models in tri-modal hybrid retrieval for Retrieval-Augmented Generation (RAG) systems. We investigate the fusion of dense semantic, sparse lexical, and graph-based embeddings, focusing on the performance of the MiniLM-v6 and BGE-Large architectures. Contrary to conventional assumptions, our results show that the compact MiniLM-v6 outperforms the larger BGE-Large when integrated with LLM-based re-ranking within our tri-modal hybrid framework. Experiments conducted on the SciFact, FIQA, and NFCorpus datasets demonstrate significant improvements in re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00049","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/2506.00049/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":"2026-07-05T11:13:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SY1BEPqKFFcXVoMt+YHMjC/5+7VET5Fd1LsjrpGR1DdKJVmjOk8m0KvKR9aTGOckf6q6YLz4bkuaam+5j9ZjAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T01:19:21.323288Z"},"content_sha256":"1faf14d016808a44d9340e6ecd2fe978ae9ee364c6935f8ac6ead51a8f35a08e","schema_version":"1.0","event_id":"sha256:1faf14d016808a44d9340e6ecd2fe978ae9ee364c6935f8ac6ead51a8f35a08e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W3WUYNPWKQAXUZUDG2HXVVYEL5/bundle.json","state_url":"https://pith.science/pith/W3WUYNPWKQAXUZUDG2HXVVYEL5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W3WUYNPWKQAXUZUDG2HXVVYEL5/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":"2026-08-10T01:19:21Z","links":{"resolver":"https://pith.science/pith/W3WUYNPWKQAXUZUDG2HXVVYEL5","bundle":"https://pith.science/pith/W3WUYNPWKQAXUZUDG2HXVVYEL5/bundle.json","state":"https://pith.science/pith/W3WUYNPWKQAXUZUDG2HXVVYEL5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W3WUYNPWKQAXUZUDG2HXVVYEL5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:W3WUYNPWKQAXUZUDG2HXVVYEL5","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":"fa3efb6795950dac763f95e02c240c86dc88c147103944a5341ba2e7cb8a7a3a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-28T18:39:40Z","title_canon_sha256":"e10c367824cb7ef6c81f58fc9939b2126f27f586b9d6e9e222f01f5133efdc10"},"schema_version":"1.0","source":{"id":"2506.00049","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00049","created_at":"2026-07-05T11:13:28Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00049v1","created_at":"2026-07-05T11:13:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00049","created_at":"2026-07-05T11:13:28Z"},{"alias_kind":"pith_short_12","alias_value":"W3WUYNPWKQAX","created_at":"2026-07-05T11:13:28Z"},{"alias_kind":"pith_short_16","alias_value":"W3WUYNPWKQAXUZUD","created_at":"2026-07-05T11:13:28Z"},{"alias_kind":"pith_short_8","alias_value":"W3WUYNPW","created_at":"2026-07-05T11:13:28Z"}],"graph_snapshots":[{"event_id":"sha256:1faf14d016808a44d9340e6ecd2fe978ae9ee364c6935f8ac6ead51a8f35a08e","target":"graph","created_at":"2026-07-05T11:13:28Z","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/2506.00049/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents a comparison of embedding models in tri-modal hybrid retrieval for Retrieval-Augmented Generation (RAG) systems. We investigate the fusion of dense semantic, sparse lexical, and graph-based embeddings, focusing on the performance of the MiniLM-v6 and BGE-Large architectures. Contrary to conventional assumptions, our results show that the compact MiniLM-v6 outperforms the larger BGE-Large when integrated with LLM-based re-ranking within our tri-modal hybrid framework. Experiments conducted on the SciFact, FIQA, and NFCorpus datasets demonstrate significant improvements in re","authors_text":"Arjun Rao, Hanieh Alipour, Nick Pendar","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-28T18:39:40Z","title":"Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00049","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":"sha256:8fb33d185cafdfd36c27cdaadbd27c7b3b9a3ba76d7660f5ce887e27a1b38616","target":"record","created_at":"2026-07-05T11:13:28Z","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":"fa3efb6795950dac763f95e02c240c86dc88c147103944a5341ba2e7cb8a7a3a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-28T18:39:40Z","title_canon_sha256":"e10c367824cb7ef6c81f58fc9939b2126f27f586b9d6e9e222f01f5133efdc10"},"schema_version":"1.0","source":{"id":"2506.00049","kind":"arxiv","version":1}},"canonical_sha256":"b6ed4c35f654017a6683368f7ad7045f670d2de898042390364c7d5afa51103f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b6ed4c35f654017a6683368f7ad7045f670d2de898042390364c7d5afa51103f","first_computed_at":"2026-07-05T11:13:28.121106Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:28.121106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5CLDd/gBzzirRHzIvJVeIhj7o8WrsdfzXPSBRIbjoDPDpw/wOqPkc7QmZhofBxZRpQW4Yj/AMaKwOSKV84hCAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:28.121707Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00049","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8fb33d185cafdfd36c27cdaadbd27c7b3b9a3ba76d7660f5ce887e27a1b38616","sha256:1faf14d016808a44d9340e6ecd2fe978ae9ee364c6935f8ac6ead51a8f35a08e"],"state_sha256":"c7894a4722bcfde2a142db120c15cfdb7c36abdc1a66f6d29af64f4d96d70558"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wWmtEAMb0wZOMZt9UGUItw9qzCe9gpePsQD2Nk4iH8jZD89V2acJhNJXhEPQMFNdYmZLahHyocKVlINKZHPTCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T01:19:21.330284Z","bundle_sha256":"40b09bbbe521eaaab43c78bcdc06923cd6d028b02bf8a25c2f425a0961bd78b3"}}