{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AE52SANPDNLC7ICB7HUGUTRUSQ","short_pith_number":"pith:AE52SANP","schema_version":"1.0","canonical_sha256":"013ba901af1b562fa041f9e86a4e3494384a3ef6570dea0e7795a1cb1b0f5144","source":{"kind":"arxiv","id":"2606.23697","version":1},"attestation_state":"computed","paper":{"title":"SemChunk-C: Semantic Segmentation for C Code","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.PL"],"primary_cat":"cs.SE","authors_text":"Boris Nazarov, Darya Frolova, Pavel Kisilev, Shaked Leibzirer","submitted_at":"2026-05-12T09:52:56Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.23697","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-12T09:52:56Z","cross_cats_sorted":["cs.AI","cs.PL"],"title_canon_sha256":"6791aed4c237ac1e244ca509142aa562f826a80c502ef917a27a5cd7918f5945","abstract_canon_sha256":"0b423b7cca740fe65900bfc190996809c178809eed0be86b32a42969038bf521"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T00:14:23.634228Z","signature_b64":"zyGxu9hi4rtADCRKSlH1WAm+Pv1w38McqIITG/lnSHXEJBWMAmHkJi6r+SDRKIfP4JRxl5hHBw1G8Cxo/+CvDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"013ba901af1b562fa041f9e86a4e3494384a3ef6570dea0e7795a1cb1b0f5144","last_reissued_at":"2026-06-24T00:14:23.633741Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T00:14:23.633741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SemChunk-C: Semantic Segmentation for C Code","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.PL"],"primary_cat":"cs.SE","authors_text":"Boris Nazarov, Darya Frolova, Pavel Kisilev, Shaked Leibzirer","submitted_at":"2026-05-12T09:52:56Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23697","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/2606.23697/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.23697","created_at":"2026-06-24T00:14:23.633797+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.23697v1","created_at":"2026-06-24T00:14:23.633797+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23697","created_at":"2026-06-24T00:14:23.633797+00:00"},{"alias_kind":"pith_short_12","alias_value":"AE52SANPDNLC","created_at":"2026-06-24T00:14:23.633797+00:00"},{"alias_kind":"pith_short_16","alias_value":"AE52SANPDNLC7ICB","created_at":"2026-06-24T00:14:23.633797+00:00"},{"alias_kind":"pith_short_8","alias_value":"AE52SANP","created_at":"2026-06-24T00:14:23.633797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AE52SANPDNLC7ICB7HUGUTRUSQ","json":"https://pith.science/pith/AE52SANPDNLC7ICB7HUGUTRUSQ.json","graph_json":"https://pith.science/api/pith-number/AE52SANPDNLC7ICB7HUGUTRUSQ/graph.json","events_json":"https://pith.science/api/pith-number/AE52SANPDNLC7ICB7HUGUTRUSQ/events.json","paper":"https://pith.science/paper/AE52SANP"},"agent_actions":{"view_html":"https://pith.science/pith/AE52SANPDNLC7ICB7HUGUTRUSQ","download_json":"https://pith.science/pith/AE52SANPDNLC7ICB7HUGUTRUSQ.json","view_paper":"https://pith.science/paper/AE52SANP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.23697&json=true","fetch_graph":"https://pith.science/api/pith-number/AE52SANPDNLC7ICB7HUGUTRUSQ/graph.json","fetch_events":"https://pith.science/api/pith-number/AE52SANPDNLC7ICB7HUGUTRUSQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AE52SANPDNLC7ICB7HUGUTRUSQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AE52SANPDNLC7ICB7HUGUTRUSQ/action/storage_attestation","attest_author":"https://pith.science/pith/AE52SANPDNLC7ICB7HUGUTRUSQ/action/author_attestation","sign_citation":"https://pith.science/pith/AE52SANPDNLC7ICB7HUGUTRUSQ/action/citation_signature","submit_replication":"https://pith.science/pith/AE52SANPDNLC7ICB7HUGUTRUSQ/action/replication_record"}},"created_at":"2026-06-24T00:14:23.633797+00:00","updated_at":"2026-06-24T00:14:23.633797+00:00"}