{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AE52SANPDNLC7ICB7HUGUTRUSQ","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":"0b423b7cca740fe65900bfc190996809c178809eed0be86b32a42969038bf521","cross_cats_sorted":["cs.AI","cs.PL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-12T09:52:56Z","title_canon_sha256":"6791aed4c237ac1e244ca509142aa562f826a80c502ef917a27a5cd7918f5945"},"schema_version":"1.0","source":{"id":"2606.23697","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.23697","created_at":"2026-06-24T00:14:23Z"},{"alias_kind":"arxiv_version","alias_value":"2606.23697v1","created_at":"2026-06-24T00:14:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23697","created_at":"2026-06-24T00:14:23Z"},{"alias_kind":"pith_short_12","alias_value":"AE52SANPDNLC","created_at":"2026-06-24T00:14:23Z"},{"alias_kind":"pith_short_16","alias_value":"AE52SANPDNLC7ICB","created_at":"2026-06-24T00:14:23Z"},{"alias_kind":"pith_short_8","alias_value":"AE52SANP","created_at":"2026-06-24T00:14:23Z"}],"graph_snapshots":[{"event_id":"sha256:1409a51da399b8ad68dfd334f80eef1fa4b1948cd2d5021d64cfc0f353a9feaa","target":"graph","created_at":"2026-06-24T00:14:23Z","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/2606.23697/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Semantic segmentation of code written in a C-family language remains a challenging problem, due to the language's complex syntax, macro expansion, and irregular structural patterns. Existing chunking methods, such as fixed-sized windows, heuristic splitting, and syntax-based tools, often fail to capture meaningful functional units, limiting the efficacy of retrieval and other downstream LLM driven tasks.\n  In this paper, we address the problem of chunking in C-related languages. First, we define a set of code chunk categories. Second, we train an LLM-based classifier to a) identify chunk bound","authors_text":"Boris Nazarov, Darya Frolova, Pavel Kisilev, Shaked Leibzirer","cross_cats":["cs.AI","cs.PL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-12T09:52:56Z","title":"SemChunk-C: Semantic Segmentation for C Code"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23697","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":"sha256:2008123dc4641e6b070c02f64dc11105fef1d6010b7a2ee061e7ad9db005a757","target":"record","created_at":"2026-06-24T00:14:23Z","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":"0b423b7cca740fe65900bfc190996809c178809eed0be86b32a42969038bf521","cross_cats_sorted":["cs.AI","cs.PL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-12T09:52:56Z","title_canon_sha256":"6791aed4c237ac1e244ca509142aa562f826a80c502ef917a27a5cd7918f5945"},"schema_version":"1.0","source":{"id":"2606.23697","kind":"arxiv","version":1}},"canonical_sha256":"013ba901af1b562fa041f9e86a4e3494384a3ef6570dea0e7795a1cb1b0f5144","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"013ba901af1b562fa041f9e86a4e3494384a3ef6570dea0e7795a1cb1b0f5144","first_computed_at":"2026-06-24T00:14:23.633741Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T00:14:23.633741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zyGxu9hi4rtADCRKSlH1WAm+Pv1w38McqIITG/lnSHXEJBWMAmHkJi6r+SDRKIfP4JRxl5hHBw1G8Cxo/+CvDw==","signature_status":"signed_v1","signed_at":"2026-06-24T00:14:23.634228Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.23697","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2008123dc4641e6b070c02f64dc11105fef1d6010b7a2ee061e7ad9db005a757","sha256:1409a51da399b8ad68dfd334f80eef1fa4b1948cd2d5021d64cfc0f353a9feaa"],"state_sha256":"9280f396a3cdd1260043fedc1127c4ac0f46149e7f0a74a03129b639b9666980"}