{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HLIUMWDXHFVG7GWECW2TNOQWHH","short_pith_number":"pith:HLIUMWDX","canonical_record":{"source":{"id":"2504.04915","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-07T10:52:22Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"c57ab9f1c73d30be28457cb1874d3e7c00a0268e0542d0e8af45edb96c74a57d","abstract_canon_sha256":"c6dc2c012d3742bbd5c6e0541260a9f2a6ef8dc457461378042167348b0791b5"},"schema_version":"1.0"},"canonical_sha256":"3ad1465877396a6f9ac415b536ba1639d4f0ef92393cb3ac3f68eb79ff204ecd","source":{"kind":"arxiv","id":"2504.04915","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.04915","created_at":"2026-07-05T10:45:31Z"},{"alias_kind":"arxiv_version","alias_value":"2504.04915v1","created_at":"2026-07-05T10:45:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04915","created_at":"2026-07-05T10:45:31Z"},{"alias_kind":"pith_short_12","alias_value":"HLIUMWDXHFVG","created_at":"2026-07-05T10:45:31Z"},{"alias_kind":"pith_short_16","alias_value":"HLIUMWDXHFVG7GWE","created_at":"2026-07-05T10:45:31Z"},{"alias_kind":"pith_short_8","alias_value":"HLIUMWDX","created_at":"2026-07-05T10:45:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HLIUMWDXHFVG7GWECW2TNOQWHH","target":"record","payload":{"canonical_record":{"source":{"id":"2504.04915","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-07T10:52:22Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"c57ab9f1c73d30be28457cb1874d3e7c00a0268e0542d0e8af45edb96c74a57d","abstract_canon_sha256":"c6dc2c012d3742bbd5c6e0541260a9f2a6ef8dc457461378042167348b0791b5"},"schema_version":"1.0"},"canonical_sha256":"3ad1465877396a6f9ac415b536ba1639d4f0ef92393cb3ac3f68eb79ff204ecd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:31.499543Z","signature_b64":"yfHpMrPrl4nK2dxfEJPvSpYXdBnNKDYNXsZwF3NOCtpDOPYySM8bCXIiLnDCpj2uqM9SEiaIf66U4ncJi2QDAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ad1465877396a6f9ac415b536ba1639d4f0ef92393cb3ac3f68eb79ff204ecd","last_reissued_at":"2026-07-05T10:45:31.499144Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:31.499144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.04915","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":"2026-07-05T10:45:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oJ01SGs3RRwvLfzFFnPQgt4szAdizPH0gTeqTISv3Xi7P0oo236/nhRPv5BvuZABLzJMt47lvIrCxR3iEEByCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:52:02.278860Z"},"content_sha256":"7eeda67320f34b970a70f343aca310fa1f3115ebb348c15cc4dd17e7c511e251","schema_version":"1.0","event_id":"sha256:7eeda67320f34b970a70f343aca310fa1f3115ebb348c15cc4dd17e7c511e251"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HLIUMWDXHFVG7GWECW2TNOQWHH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Collab-RAG: Boosting Retrieval-Augmented Generation for Complex Question Answering via White-Box and Black-Box LLM Collaboration","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Carl Yang, Haoyu Wang, Joyce C. Ho, Ran Xu, Wenqi Shi, Yuchen Zhuang, Yue Yu","submitted_at":"2025-04-07T10:52:22Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) systems often struggle to handle multi-hop question-answering tasks accurately due to irrelevant context retrieval and limited complex reasoning capabilities. We introduce Collab-RAG, a collaborative training framework that leverages mutual enhancement between a white-box small language model (SLM) and a blackbox large language model (LLM) for RAG. Specifically, the SLM decomposes complex queries into simpler sub-questions, thus enhancing the accuracy of the retrieval and facilitating more effective reasoning by the black-box LLM. Concurrently, the black-bo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04915","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/2504.04915/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":"2026-07-05T10:45:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cbjw5qa1yfgFOvUNr8MlL8eP6NSUZSKjLAZnrGsbUUUonlLcPDsWaPd54Sdb0bbfe5rQ5Wd3CAmh8WDE6RJSCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:52:02.279299Z"},"content_sha256":"841f3992c4eb08eba308a059c64b33b67751b902a2f5069d61b8aac096fe03fe","schema_version":"1.0","event_id":"sha256:841f3992c4eb08eba308a059c64b33b67751b902a2f5069d61b8aac096fe03fe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HLIUMWDXHFVG7GWECW2TNOQWHH/bundle.json","state_url":"https://pith.science/pith/HLIUMWDXHFVG7GWECW2TNOQWHH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HLIUMWDXHFVG7GWECW2TNOQWHH/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":"2026-08-07T19:52:02Z","links":{"resolver":"https://pith.science/pith/HLIUMWDXHFVG7GWECW2TNOQWHH","bundle":"https://pith.science/pith/HLIUMWDXHFVG7GWECW2TNOQWHH/bundle.json","state":"https://pith.science/pith/HLIUMWDXHFVG7GWECW2TNOQWHH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HLIUMWDXHFVG7GWECW2TNOQWHH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HLIUMWDXHFVG7GWECW2TNOQWHH","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":"c6dc2c012d3742bbd5c6e0541260a9f2a6ef8dc457461378042167348b0791b5","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-07T10:52:22Z","title_canon_sha256":"c57ab9f1c73d30be28457cb1874d3e7c00a0268e0542d0e8af45edb96c74a57d"},"schema_version":"1.0","source":{"id":"2504.04915","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.04915","created_at":"2026-07-05T10:45:31Z"},{"alias_kind":"arxiv_version","alias_value":"2504.04915v1","created_at":"2026-07-05T10:45:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04915","created_at":"2026-07-05T10:45:31Z"},{"alias_kind":"pith_short_12","alias_value":"HLIUMWDXHFVG","created_at":"2026-07-05T10:45:31Z"},{"alias_kind":"pith_short_16","alias_value":"HLIUMWDXHFVG7GWE","created_at":"2026-07-05T10:45:31Z"},{"alias_kind":"pith_short_8","alias_value":"HLIUMWDX","created_at":"2026-07-05T10:45:31Z"}],"graph_snapshots":[{"event_id":"sha256:841f3992c4eb08eba308a059c64b33b67751b902a2f5069d61b8aac096fe03fe","target":"graph","created_at":"2026-07-05T10:45:31Z","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/2504.04915/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval-Augmented Generation (RAG) systems often struggle to handle multi-hop question-answering tasks accurately due to irrelevant context retrieval and limited complex reasoning capabilities. We introduce Collab-RAG, a collaborative training framework that leverages mutual enhancement between a white-box small language model (SLM) and a blackbox large language model (LLM) for RAG. Specifically, the SLM decomposes complex queries into simpler sub-questions, thus enhancing the accuracy of the retrieval and facilitating more effective reasoning by the black-box LLM. Concurrently, the black-bo","authors_text":"Carl Yang, Haoyu Wang, Joyce C. Ho, Ran Xu, Wenqi Shi, Yuchen Zhuang, Yue Yu","cross_cats":["cs.AI","cs.IR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-07T10:52:22Z","title":"Collab-RAG: Boosting Retrieval-Augmented Generation for Complex Question Answering via White-Box and Black-Box LLM Collaboration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04915","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":"sha256:7eeda67320f34b970a70f343aca310fa1f3115ebb348c15cc4dd17e7c511e251","target":"record","created_at":"2026-07-05T10:45:31Z","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":"c6dc2c012d3742bbd5c6e0541260a9f2a6ef8dc457461378042167348b0791b5","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-07T10:52:22Z","title_canon_sha256":"c57ab9f1c73d30be28457cb1874d3e7c00a0268e0542d0e8af45edb96c74a57d"},"schema_version":"1.0","source":{"id":"2504.04915","kind":"arxiv","version":1}},"canonical_sha256":"3ad1465877396a6f9ac415b536ba1639d4f0ef92393cb3ac3f68eb79ff204ecd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ad1465877396a6f9ac415b536ba1639d4f0ef92393cb3ac3f68eb79ff204ecd","first_computed_at":"2026-07-05T10:45:31.499144Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:45:31.499144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yfHpMrPrl4nK2dxfEJPvSpYXdBnNKDYNXsZwF3NOCtpDOPYySM8bCXIiLnDCpj2uqM9SEiaIf66U4ncJi2QDAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:45:31.499543Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.04915","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7eeda67320f34b970a70f343aca310fa1f3115ebb348c15cc4dd17e7c511e251","sha256:841f3992c4eb08eba308a059c64b33b67751b902a2f5069d61b8aac096fe03fe"],"state_sha256":"dd3d3e2d0a467263245955f5710f5fe1bd7273a5fb8408ac45c4d07625d402e1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4alK3jO94q4CsaK06wzPEXMgyAUctYxbypVFgQN77JbjN9fZXplu5Wxfid/tg1PK/X7FQemH/dc3dXJXyNtmCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T19:52:02.282195Z","bundle_sha256":"6fc7f501511c056607a4cd53edd2ac4d7b15faa40a8cb2cb28faa4dc4a287c89"}}