{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:32KM4BMWNY6V5GNOMSDHLIEDHP","short_pith_number":"pith:32KM4BMW","canonical_record":{"source":{"id":"2503.09600","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-12T17:59:42Z","cross_cats_sorted":[],"title_canon_sha256":"6db20b2ea2b81fc6ffc6d49a466c0e9ceb247b98f5daccdc34033062a7bf73a8","abstract_canon_sha256":"84b257d62a9a13f1cbdac952d01de20adb4328b671d49cb0920e6c0f498da587"},"schema_version":"1.0"},"canonical_sha256":"de94ce05966e3d5e99ae648675a0833bc74b8d8d292bd0867c94d26bff7eb08e","source":{"kind":"arxiv","id":"2503.09600","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.09600","created_at":"2026-07-05T11:09:45Z"},{"alias_kind":"arxiv_version","alias_value":"2503.09600v2","created_at":"2026-07-05T11:09:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.09600","created_at":"2026-07-05T11:09:45Z"},{"alias_kind":"pith_short_12","alias_value":"32KM4BMWNY6V","created_at":"2026-07-05T11:09:45Z"},{"alias_kind":"pith_short_16","alias_value":"32KM4BMWNY6V5GNO","created_at":"2026-07-05T11:09:45Z"},{"alias_kind":"pith_short_8","alias_value":"32KM4BMW","created_at":"2026-07-05T11:09:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:32KM4BMWNY6V5GNOMSDHLIEDHP","target":"record","payload":{"canonical_record":{"source":{"id":"2503.09600","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-12T17:59:42Z","cross_cats_sorted":[],"title_canon_sha256":"6db20b2ea2b81fc6ffc6d49a466c0e9ceb247b98f5daccdc34033062a7bf73a8","abstract_canon_sha256":"84b257d62a9a13f1cbdac952d01de20adb4328b671d49cb0920e6c0f498da587"},"schema_version":"1.0"},"canonical_sha256":"de94ce05966e3d5e99ae648675a0833bc74b8d8d292bd0867c94d26bff7eb08e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:45.946890Z","signature_b64":"reONiwM2i0OjN5La6NmKhxAsi/p0tz08dmKXNiAoU85wottHfQ766uHQiPbWao7QBFs1a9fBLW+WswqgyJeZBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de94ce05966e3d5e99ae648675a0833bc74b8d8d292bd0867c94d26bff7eb08e","last_reissued_at":"2026-07-05T11:09:45.946382Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:45.946382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.09600","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":"2026-07-05T11:09:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KFaFwhtecz/OA9PPKRcJZD6+Nk3qtrjbsBI+RnO1AT8FmgtYM717P2CiGSbOYMcflG9MviCqYYyY+BHbRlfVCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T06:46:27.511652Z"},"content_sha256":"a93a0babf5d654ed2c19ae48ae1b1d1334c6655fa8ba697444c23659cd03de48","schema_version":"1.0","event_id":"sha256:a93a0babf5d654ed2c19ae48ae1b1d1334c6655fa8ba697444c23659cd03de48"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:32KM4BMWNY6V5GNOMSDHLIEDHP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MoC: Mixtures of Text Chunking Learners for Retrieval-Augmented Generation System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Tang, Feiyu Xiong, Hanyu Wang, Jihao Zhao, Simin Niu, Zhaoxin Fan, Zhiyuan Ji, Zhiyu Li","submitted_at":"2025-03-12T17:59:42Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG), while serving as a viable complement to large language models (LLMs), often overlooks the crucial aspect of text chunking within its pipeline. This paper initially introduces a dual-metric evaluation method, comprising Boundary Clarity and Chunk Stickiness, to enable the direct quantification of chunking quality. Leveraging this assessment method, we highlight the inherent limitations of traditional and semantic chunking in handling complex contextual nuances, thereby substantiating the necessity of integrating LLMs into chunking process. To address the in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.09600","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/2503.09600/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":"2026-07-05T11:09:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IVbFiAJe2MwQNy9RNYJsENAxZyaOgbTIjj+aIEWsGuLiGxP0j7sIMFjFyYeqjv0Vi776puTUGCAJfw4oUbD3CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T06:46:27.512651Z"},"content_sha256":"15806a143367f83e32a7a68d8cd193e67b9ca63e472022d8a4653ee29c828e90","schema_version":"1.0","event_id":"sha256:15806a143367f83e32a7a68d8cd193e67b9ca63e472022d8a4653ee29c828e90"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/32KM4BMWNY6V5GNOMSDHLIEDHP/bundle.json","state_url":"https://pith.science/pith/32KM4BMWNY6V5GNOMSDHLIEDHP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/32KM4BMWNY6V5GNOMSDHLIEDHP/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":"2026-08-18T06:46:27Z","links":{"resolver":"https://pith.science/pith/32KM4BMWNY6V5GNOMSDHLIEDHP","bundle":"https://pith.science/pith/32KM4BMWNY6V5GNOMSDHLIEDHP/bundle.json","state":"https://pith.science/pith/32KM4BMWNY6V5GNOMSDHLIEDHP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/32KM4BMWNY6V5GNOMSDHLIEDHP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:32KM4BMWNY6V5GNOMSDHLIEDHP","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":"84b257d62a9a13f1cbdac952d01de20adb4328b671d49cb0920e6c0f498da587","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-12T17:59:42Z","title_canon_sha256":"6db20b2ea2b81fc6ffc6d49a466c0e9ceb247b98f5daccdc34033062a7bf73a8"},"schema_version":"1.0","source":{"id":"2503.09600","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.09600","created_at":"2026-07-05T11:09:45Z"},{"alias_kind":"arxiv_version","alias_value":"2503.09600v2","created_at":"2026-07-05T11:09:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.09600","created_at":"2026-07-05T11:09:45Z"},{"alias_kind":"pith_short_12","alias_value":"32KM4BMWNY6V","created_at":"2026-07-05T11:09:45Z"},{"alias_kind":"pith_short_16","alias_value":"32KM4BMWNY6V5GNO","created_at":"2026-07-05T11:09:45Z"},{"alias_kind":"pith_short_8","alias_value":"32KM4BMW","created_at":"2026-07-05T11:09:45Z"}],"graph_snapshots":[{"event_id":"sha256:15806a143367f83e32a7a68d8cd193e67b9ca63e472022d8a4653ee29c828e90","target":"graph","created_at":"2026-07-05T11:09:45Z","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/2503.09600/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval-Augmented Generation (RAG), while serving as a viable complement to large language models (LLMs), often overlooks the crucial aspect of text chunking within its pipeline. This paper initially introduces a dual-metric evaluation method, comprising Boundary Clarity and Chunk Stickiness, to enable the direct quantification of chunking quality. Leveraging this assessment method, we highlight the inherent limitations of traditional and semantic chunking in handling complex contextual nuances, thereby substantiating the necessity of integrating LLMs into chunking process. To address the in","authors_text":"Bo Tang, Feiyu Xiong, Hanyu Wang, Jihao Zhao, Simin Niu, Zhaoxin Fan, Zhiyuan Ji, Zhiyu Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-12T17:59:42Z","title":"MoC: Mixtures of Text Chunking Learners for Retrieval-Augmented Generation System"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.09600","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:a93a0babf5d654ed2c19ae48ae1b1d1334c6655fa8ba697444c23659cd03de48","target":"record","created_at":"2026-07-05T11:09:45Z","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":"84b257d62a9a13f1cbdac952d01de20adb4328b671d49cb0920e6c0f498da587","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-12T17:59:42Z","title_canon_sha256":"6db20b2ea2b81fc6ffc6d49a466c0e9ceb247b98f5daccdc34033062a7bf73a8"},"schema_version":"1.0","source":{"id":"2503.09600","kind":"arxiv","version":2}},"canonical_sha256":"de94ce05966e3d5e99ae648675a0833bc74b8d8d292bd0867c94d26bff7eb08e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de94ce05966e3d5e99ae648675a0833bc74b8d8d292bd0867c94d26bff7eb08e","first_computed_at":"2026-07-05T11:09:45.946382Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:45.946382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"reONiwM2i0OjN5La6NmKhxAsi/p0tz08dmKXNiAoU85wottHfQ766uHQiPbWao7QBFs1a9fBLW+WswqgyJeZBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:45.946890Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.09600","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a93a0babf5d654ed2c19ae48ae1b1d1334c6655fa8ba697444c23659cd03de48","sha256:15806a143367f83e32a7a68d8cd193e67b9ca63e472022d8a4653ee29c828e90"],"state_sha256":"10f6937c8f571af9c005259e4642c63aaa5918cfc36fe074283e6197494806f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0W8lCTIBIiy/0yOX7RXlU/37jdpa5p4sMIbgXc25Tm8t6uIo+XVZqQCn0ewMbbLCJF8JHrh1zGPhhJbtxd8ADA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T06:46:27.533850Z","bundle_sha256":"7148c6d775412fa18530c004b9e63c4741f248971ba7763a4bdad0a8c996b041"}}