{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Y7KN6F7EIVZL7X2CFGY5FCFKLA","short_pith_number":"pith:Y7KN6F7E","canonical_record":{"source":{"id":"2406.00456","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-01T14:45:03Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"1e540ba2edaa036b6d00ddf355af8ea3d0c7d9e71557e47ebb71185573566252","abstract_canon_sha256":"515bdc9262fcaf629d928ac6fff96ffc35bacdaa2d9ea72883192f05efc63af8"},"schema_version":"1.0"},"canonical_sha256":"c7d4df17e44572bfdf4229b1d288aa5833609a2747ebfccbae289fdfead6588f","source":{"kind":"arxiv","id":"2406.00456","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.00456","created_at":"2026-07-05T10:05:10Z"},{"alias_kind":"arxiv_version","alias_value":"2406.00456v2","created_at":"2026-07-05T10:05:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00456","created_at":"2026-07-05T10:05:10Z"},{"alias_kind":"pith_short_12","alias_value":"Y7KN6F7EIVZL","created_at":"2026-07-05T10:05:10Z"},{"alias_kind":"pith_short_16","alias_value":"Y7KN6F7EIVZL7X2C","created_at":"2026-07-05T10:05:10Z"},{"alias_kind":"pith_short_8","alias_value":"Y7KN6F7E","created_at":"2026-07-05T10:05:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Y7KN6F7EIVZL7X2CFGY5FCFKLA","target":"record","payload":{"canonical_record":{"source":{"id":"2406.00456","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-01T14:45:03Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"1e540ba2edaa036b6d00ddf355af8ea3d0c7d9e71557e47ebb71185573566252","abstract_canon_sha256":"515bdc9262fcaf629d928ac6fff96ffc35bacdaa2d9ea72883192f05efc63af8"},"schema_version":"1.0"},"canonical_sha256":"c7d4df17e44572bfdf4229b1d288aa5833609a2747ebfccbae289fdfead6588f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:10.926371Z","signature_b64":"f1X8Dr+3em9bfMt8r/cvBBRJlk9d04k3ERFm/aFHS0ntMOIBsXuVpt2WPFv0H1Ydk5N8tZyybEa1uOog1pSKAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7d4df17e44572bfdf4229b1d288aa5833609a2747ebfccbae289fdfead6588f","last_reissued_at":"2026-07-05T10:05:10.925926Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:10.925926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.00456","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:05:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y7XG8mQrnJa8WSfUtml8DwnCPdHMNfE22gfGdNH/nGPJQ1NPTBGAohohRiWbEDL3Gr8YZN1sy8TwiNQnB2TnCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T01:36:40.057209Z"},"content_sha256":"a6076e76ca4b4877870dbf346f727ff9ea1bcde6a13793c6319c9ac2f85b974f","schema_version":"1.0","event_id":"sha256:a6076e76ca4b4877870dbf346f727ff9ea1bcde6a13793c6319c9ac2f85b974f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Y7KN6F7EIVZL7X2CFGY5FCFKLA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mix-of-Granularity: Optimize the Chunking Granularity for Retrieval-Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Hanwen Liu, Xiaofan Zhang, Xiaoya Cui, Zengchang Qin, Zijie Zhong","submitted_at":"2024-06-01T14:45:03Z","abstract_excerpt":"Integrating information from various reference databases is a major challenge for Retrieval-Augmented Generation (RAG) systems because each knowledge source adopts a unique data structure and follows different conventions. Retrieving from multiple knowledge sources with one fixed strategy usually leads to under-exploitation of information. To mitigate this drawback, inspired by Mix-of-Expert, we introduce Mix-of-Granularity (MoG), a method that dynamically determines the optimal granularity of a knowledge source based on input queries using a router. The router is efficiently trained with a ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00456","kind":"arxiv","version":2},"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/2406.00456/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":"2026-07-05T10:05:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jrfFXbnLDHnKs60mTVdEe24C4kSOvQkXLY0l2Bdkzkh2cP4p5XTzbQmYrhv2pbnB24f4AgVuOwQIpzefE1PEDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T01:36:40.057785Z"},"content_sha256":"000c7f9c4617aea5d4c725b1d77b731ef0d769320cd5ad06e378eb777b5924ec","schema_version":"1.0","event_id":"sha256:000c7f9c4617aea5d4c725b1d77b731ef0d769320cd5ad06e378eb777b5924ec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y7KN6F7EIVZL7X2CFGY5FCFKLA/bundle.json","state_url":"https://pith.science/pith/Y7KN6F7EIVZL7X2CFGY5FCFKLA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y7KN6F7EIVZL7X2CFGY5FCFKLA/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":"2026-08-09T01:36:40Z","links":{"resolver":"https://pith.science/pith/Y7KN6F7EIVZL7X2CFGY5FCFKLA","bundle":"https://pith.science/pith/Y7KN6F7EIVZL7X2CFGY5FCFKLA/bundle.json","state":"https://pith.science/pith/Y7KN6F7EIVZL7X2CFGY5FCFKLA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y7KN6F7EIVZL7X2CFGY5FCFKLA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Y7KN6F7EIVZL7X2CFGY5FCFKLA","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":"515bdc9262fcaf629d928ac6fff96ffc35bacdaa2d9ea72883192f05efc63af8","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-01T14:45:03Z","title_canon_sha256":"1e540ba2edaa036b6d00ddf355af8ea3d0c7d9e71557e47ebb71185573566252"},"schema_version":"1.0","source":{"id":"2406.00456","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.00456","created_at":"2026-07-05T10:05:10Z"},{"alias_kind":"arxiv_version","alias_value":"2406.00456v2","created_at":"2026-07-05T10:05:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00456","created_at":"2026-07-05T10:05:10Z"},{"alias_kind":"pith_short_12","alias_value":"Y7KN6F7EIVZL","created_at":"2026-07-05T10:05:10Z"},{"alias_kind":"pith_short_16","alias_value":"Y7KN6F7EIVZL7X2C","created_at":"2026-07-05T10:05:10Z"},{"alias_kind":"pith_short_8","alias_value":"Y7KN6F7E","created_at":"2026-07-05T10:05:10Z"}],"graph_snapshots":[{"event_id":"sha256:000c7f9c4617aea5d4c725b1d77b731ef0d769320cd5ad06e378eb777b5924ec","target":"graph","created_at":"2026-07-05T10:05:10Z","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/2406.00456/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Integrating information from various reference databases is a major challenge for Retrieval-Augmented Generation (RAG) systems because each knowledge source adopts a unique data structure and follows different conventions. Retrieving from multiple knowledge sources with one fixed strategy usually leads to under-exploitation of information. To mitigate this drawback, inspired by Mix-of-Expert, we introduce Mix-of-Granularity (MoG), a method that dynamically determines the optimal granularity of a knowledge source based on input queries using a router. The router is efficiently trained with a ne","authors_text":"Hanwen Liu, Xiaofan Zhang, Xiaoya Cui, Zengchang Qin, Zijie Zhong","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-01T14:45:03Z","title":"Mix-of-Granularity: Optimize the Chunking Granularity for Retrieval-Augmented Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00456","kind":"arxiv","version":2},"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:a6076e76ca4b4877870dbf346f727ff9ea1bcde6a13793c6319c9ac2f85b974f","target":"record","created_at":"2026-07-05T10:05:10Z","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":"515bdc9262fcaf629d928ac6fff96ffc35bacdaa2d9ea72883192f05efc63af8","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-01T14:45:03Z","title_canon_sha256":"1e540ba2edaa036b6d00ddf355af8ea3d0c7d9e71557e47ebb71185573566252"},"schema_version":"1.0","source":{"id":"2406.00456","kind":"arxiv","version":2}},"canonical_sha256":"c7d4df17e44572bfdf4229b1d288aa5833609a2747ebfccbae289fdfead6588f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c7d4df17e44572bfdf4229b1d288aa5833609a2747ebfccbae289fdfead6588f","first_computed_at":"2026-07-05T10:05:10.925926Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:05:10.925926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f1X8Dr+3em9bfMt8r/cvBBRJlk9d04k3ERFm/aFHS0ntMOIBsXuVpt2WPFv0H1Ydk5N8tZyybEa1uOog1pSKAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:05:10.926371Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.00456","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a6076e76ca4b4877870dbf346f727ff9ea1bcde6a13793c6319c9ac2f85b974f","sha256:000c7f9c4617aea5d4c725b1d77b731ef0d769320cd5ad06e378eb777b5924ec"],"state_sha256":"6052707ceaed3b9a030ccd7828925a87f1c0488a741d6ec41a39180dee93cfd7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WIDTiqtcNjB/5/4XMTZzC9raSXnw2iMvSB4/Nvh4Ojib32tKjpcImcVxBcnNfnGglSnjAdD2gmCRDrn9XXeoAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T01:36:40.062676Z","bundle_sha256":"4cdda24a90431c38ff6ba4954ab24c30c05f3e462d5df0d0cc613644598610bc"}}