{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:35V5DSP53PIUPTYGY3QXTXU52D","short_pith_number":"pith:35V5DSP5","canonical_record":{"source":{"id":"2608.00824","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-08-01T19:01:46Z","cross_cats_sorted":[],"title_canon_sha256":"709a149b3db5302776383fff466f0aa1e0170bdd5f5068879ec1e74a41d9a84c","abstract_canon_sha256":"f4b8b43a07ad639d043d80bbef32e917d68b8ff7520c46cbcf25692b1926c231"},"schema_version":"1.0"},"canonical_sha256":"df6bd1c9fddbd147cf06c6e179de9dd0e343149f2fd17e015b35f7a449ee9351","source":{"kind":"arxiv","id":"2608.00824","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.00824","created_at":"2026-08-04T01:55:12Z"},{"alias_kind":"arxiv_version","alias_value":"2608.00824v1","created_at":"2026-08-04T01:55:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00824","created_at":"2026-08-04T01:55:12Z"},{"alias_kind":"pith_short_12","alias_value":"35V5DSP53PIU","created_at":"2026-08-04T01:55:12Z"},{"alias_kind":"pith_short_16","alias_value":"35V5DSP53PIUPTYG","created_at":"2026-08-04T01:55:12Z"},{"alias_kind":"pith_short_8","alias_value":"35V5DSP5","created_at":"2026-08-04T01:55:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:35V5DSP53PIUPTYGY3QXTXU52D","target":"record","payload":{"canonical_record":{"source":{"id":"2608.00824","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-08-01T19:01:46Z","cross_cats_sorted":[],"title_canon_sha256":"709a149b3db5302776383fff466f0aa1e0170bdd5f5068879ec1e74a41d9a84c","abstract_canon_sha256":"f4b8b43a07ad639d043d80bbef32e917d68b8ff7520c46cbcf25692b1926c231"},"schema_version":"1.0"},"canonical_sha256":"df6bd1c9fddbd147cf06c6e179de9dd0e343149f2fd17e015b35f7a449ee9351","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T01:55:12.715957Z","signature_b64":"6XMpH1V06H+qfsoaJixaj/zY5FCxEvEs1B8uxW55cK/Mi37ineJ8qiKm0Ful9SRYWrIhO/gSioByTv/0m5LEDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df6bd1c9fddbd147cf06c6e179de9dd0e343149f2fd17e015b35f7a449ee9351","last_reissued_at":"2026-08-04T01:55:12.714182Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T01:55:12.714182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.00824","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":"2026-08-04T01:55:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r1KwF268hXH+K6vZQI5cvYR/wg7pnGOnQGYik1AJ1x4TiI/c4BIWrY9JWnkMeesd3NOkVCXiB5ShR4EPJqKcAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:57:04.208936Z"},"content_sha256":"9d5eb77263c6e410a85b7c8f2cd224ddc584cd96b0a67197550ba7d028afdb40","schema_version":"1.0","event_id":"sha256:9d5eb77263c6e410a85b7c8f2cd224ddc584cd96b0a67197550ba7d028afdb40"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:35V5DSP53PIUPTYGY3QXTXU52D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Structure-Aware Semantic Chunking with Title-Chain Prefixes: A 1600-Query Evaluation and the Measurement Trap in Text-Transform Ablations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Yang Yang","submitted_at":"2026-08-01T19:01:46Z","abstract_excerpt":"Chunking is the first and most consequential step in retrieval-augmented generation (RAG): every downstream retrieval decision inherits the chunk boundaries. We present a three-stage, chunk-side-only semantic chunking pipeline---header-split, semantic merge, and title-chain prefixing---that costs zero additional LLM calls: the title chain reuses the document's own header hierarchy instead of a generated summary. On a 1600-query stratified evaluation over a production Markdown knowledge base, the pipeline improves MRR@5 from 0.374 to 0.463 (+23.8%) on the full set and from 0.828 to 0.925 (+11.7"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00824","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/2608.00824/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":"2026-08-04T01:55:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wTq8l3HrJ3rvECMXQPVKLJNRsyhMi/G1PtKpH/3bJ+Aezww3cbzuw0cv6ljyOlFSyULikPHRvx8LU7LjreXGBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:57:04.209471Z"},"content_sha256":"833e1a0f6ad49b1328fc4dd5dfb286bd1729322ebb85b2306ca83006dfa7e70b","schema_version":"1.0","event_id":"sha256:833e1a0f6ad49b1328fc4dd5dfb286bd1729322ebb85b2306ca83006dfa7e70b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/35V5DSP53PIUPTYGY3QXTXU52D/bundle.json","state_url":"https://pith.science/pith/35V5DSP53PIUPTYGY3QXTXU52D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/35V5DSP53PIUPTYGY3QXTXU52D/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":"2026-08-05T10:57:04Z","links":{"resolver":"https://pith.science/pith/35V5DSP53PIUPTYGY3QXTXU52D","bundle":"https://pith.science/pith/35V5DSP53PIUPTYGY3QXTXU52D/bundle.json","state":"https://pith.science/pith/35V5DSP53PIUPTYGY3QXTXU52D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/35V5DSP53PIUPTYGY3QXTXU52D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:35V5DSP53PIUPTYGY3QXTXU52D","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":"f4b8b43a07ad639d043d80bbef32e917d68b8ff7520c46cbcf25692b1926c231","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-08-01T19:01:46Z","title_canon_sha256":"709a149b3db5302776383fff466f0aa1e0170bdd5f5068879ec1e74a41d9a84c"},"schema_version":"1.0","source":{"id":"2608.00824","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.00824","created_at":"2026-08-04T01:55:12Z"},{"alias_kind":"arxiv_version","alias_value":"2608.00824v1","created_at":"2026-08-04T01:55:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00824","created_at":"2026-08-04T01:55:12Z"},{"alias_kind":"pith_short_12","alias_value":"35V5DSP53PIU","created_at":"2026-08-04T01:55:12Z"},{"alias_kind":"pith_short_16","alias_value":"35V5DSP53PIUPTYG","created_at":"2026-08-04T01:55:12Z"},{"alias_kind":"pith_short_8","alias_value":"35V5DSP5","created_at":"2026-08-04T01:55:12Z"}],"graph_snapshots":[{"event_id":"sha256:833e1a0f6ad49b1328fc4dd5dfb286bd1729322ebb85b2306ca83006dfa7e70b","target":"graph","created_at":"2026-08-04T01:55:12Z","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/2608.00824/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Chunking is the first and most consequential step in retrieval-augmented generation (RAG): every downstream retrieval decision inherits the chunk boundaries. We present a three-stage, chunk-side-only semantic chunking pipeline---header-split, semantic merge, and title-chain prefixing---that costs zero additional LLM calls: the title chain reuses the document's own header hierarchy instead of a generated summary. On a 1600-query stratified evaluation over a production Markdown knowledge base, the pipeline improves MRR@5 from 0.374 to 0.463 (+23.8%) on the full set and from 0.828 to 0.925 (+11.7","authors_text":"Yang Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-08-01T19:01:46Z","title":"Structure-Aware Semantic Chunking with Title-Chain Prefixes: A 1600-Query Evaluation and the Measurement Trap in Text-Transform Ablations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00824","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":"sha256:9d5eb77263c6e410a85b7c8f2cd224ddc584cd96b0a67197550ba7d028afdb40","target":"record","created_at":"2026-08-04T01:55:12Z","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":"f4b8b43a07ad639d043d80bbef32e917d68b8ff7520c46cbcf25692b1926c231","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-08-01T19:01:46Z","title_canon_sha256":"709a149b3db5302776383fff466f0aa1e0170bdd5f5068879ec1e74a41d9a84c"},"schema_version":"1.0","source":{"id":"2608.00824","kind":"arxiv","version":1}},"canonical_sha256":"df6bd1c9fddbd147cf06c6e179de9dd0e343149f2fd17e015b35f7a449ee9351","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df6bd1c9fddbd147cf06c6e179de9dd0e343149f2fd17e015b35f7a449ee9351","first_computed_at":"2026-08-04T01:55:12.714182Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T01:55:12.714182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6XMpH1V06H+qfsoaJixaj/zY5FCxEvEs1B8uxW55cK/Mi37ineJ8qiKm0Ful9SRYWrIhO/gSioByTv/0m5LEDQ==","signature_status":"signed_v1","signed_at":"2026-08-04T01:55:12.715957Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.00824","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9d5eb77263c6e410a85b7c8f2cd224ddc584cd96b0a67197550ba7d028afdb40","sha256:833e1a0f6ad49b1328fc4dd5dfb286bd1729322ebb85b2306ca83006dfa7e70b"],"state_sha256":"223f8cc42e559ef5c6a5f39b43ce3e9dc1790a56366260c0b6bcc488bba14f30"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ogh/1hELmCzUpSH8BmJluVN8Sb3vVqyo8Tg63wlEQJ1m2Q+rBWnG9LY/BPPHIejap72vrhlTS3zn4MBUW+3aAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T10:57:04.214460Z","bundle_sha256":"4988cc5ed348064dd629f2ef384e7f23f30f1d52ffc682c07e6782243ce8b875"}}