{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WCK3BKJZ3HIUNVVZQXN3TWVSAQ","short_pith_number":"pith:WCK3BKJZ","canonical_record":{"source":{"id":"2507.08992","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-11T19:49:59Z","cross_cats_sorted":["cs.CL","cs.PL"],"title_canon_sha256":"09c724e3fa6d567304d47b6fa67036d14816325d8618beffc0aa0acc58319084","abstract_canon_sha256":"e60c6b452f452b8060ecdcc947fa534954bf08bfb459158cd1db1fbeb2d97c41"},"schema_version":"1.0"},"canonical_sha256":"b095b0a939d9d146d6b985dbb9dab204179434b65dad9ba87817d2b64c5a5b2e","source":{"kind":"arxiv","id":"2507.08992","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.08992","created_at":"2026-07-05T11:36:01Z"},{"alias_kind":"arxiv_version","alias_value":"2507.08992v1","created_at":"2026-07-05T11:36:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.08992","created_at":"2026-07-05T11:36:01Z"},{"alias_kind":"pith_short_12","alias_value":"WCK3BKJZ3HIU","created_at":"2026-07-05T11:36:01Z"},{"alias_kind":"pith_short_16","alias_value":"WCK3BKJZ3HIUNVVZ","created_at":"2026-07-05T11:36:01Z"},{"alias_kind":"pith_short_8","alias_value":"WCK3BKJZ","created_at":"2026-07-05T11:36:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WCK3BKJZ3HIUNVVZQXN3TWVSAQ","target":"record","payload":{"canonical_record":{"source":{"id":"2507.08992","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-11T19:49:59Z","cross_cats_sorted":["cs.CL","cs.PL"],"title_canon_sha256":"09c724e3fa6d567304d47b6fa67036d14816325d8618beffc0aa0acc58319084","abstract_canon_sha256":"e60c6b452f452b8060ecdcc947fa534954bf08bfb459158cd1db1fbeb2d97c41"},"schema_version":"1.0"},"canonical_sha256":"b095b0a939d9d146d6b985dbb9dab204179434b65dad9ba87817d2b64c5a5b2e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:01.747207Z","signature_b64":"yq+KVUKgfN5UD/jW/+Cq1erpivdToDTt0y1SAWzzdHykZTeugj8wEp3NiQKTz8iydQkPxYLRAN4BN0P1Z7dpCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b095b0a939d9d146d6b985dbb9dab204179434b65dad9ba87817d2b64c5a5b2e","last_reissued_at":"2026-07-05T11:36:01.746748Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:01.746748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.08992","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":"2026-07-05T11:36:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vdb8pbT3sJGzrqKZwO0c96qS4blCq9K2lSfq21rO5CRkwy0lsYN6IK3OiNsHbTtyqPRifAHg7Zbr6aUxfjsaCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T21:38:18.209623Z"},"content_sha256":"86d53430907a6bd80601743b13a7cb8f505b92873ed70f1ae4b3d27da277e055","schema_version":"1.0","event_id":"sha256:86d53430907a6bd80601743b13a7cb8f505b92873ed70f1ae4b3d27da277e055"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WCK3BKJZ3HIUNVVZQXN3TWVSAQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semantic Source Code Segmentation using Small and Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.PL"],"primary_cat":"cs.SE","authors_text":"Abdelhalim Dahou, Ansgar Scherp, Brigitte Mathiak, Madhu Chauhan, Sebastian Kurten","submitted_at":"2025-07-11T19:49:59Z","abstract_excerpt":"Source code segmentation, dividing code into functionally coherent segments, is crucial for knowledge retrieval and maintenance in software development. While enabling efficient navigation and comprehension of large codebases, manual and syntactic analysis approaches have become impractical as repositories grow, especially for low-resource languages like R and their research domains (e.g., social sciences, psychology).This paper introduces an automated, domain-specific approach for research R code segmentation using Large and Small Language Models (LLMs/SLMs). It presents two novel approaches "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.08992","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/2507.08992/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":"2026-07-05T11:36:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WAV8ENS99wlhZhCHOCUOnHNOXkLSHDPklloXE8IshUXpzkgWeFx32UZl7s6aC9GGzOwHMvg7b9bvvOE7aF2HDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T21:38:18.209959Z"},"content_sha256":"fca517404fee0df3663345799bcc9c2625fcf731d4f613558facfad18429963d","schema_version":"1.0","event_id":"sha256:fca517404fee0df3663345799bcc9c2625fcf731d4f613558facfad18429963d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WCK3BKJZ3HIUNVVZQXN3TWVSAQ/bundle.json","state_url":"https://pith.science/pith/WCK3BKJZ3HIUNVVZQXN3TWVSAQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WCK3BKJZ3HIUNVVZQXN3TWVSAQ/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":"2026-08-19T21:38:18Z","links":{"resolver":"https://pith.science/pith/WCK3BKJZ3HIUNVVZQXN3TWVSAQ","bundle":"https://pith.science/pith/WCK3BKJZ3HIUNVVZQXN3TWVSAQ/bundle.json","state":"https://pith.science/pith/WCK3BKJZ3HIUNVVZQXN3TWVSAQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WCK3BKJZ3HIUNVVZQXN3TWVSAQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WCK3BKJZ3HIUNVVZQXN3TWVSAQ","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":"e60c6b452f452b8060ecdcc947fa534954bf08bfb459158cd1db1fbeb2d97c41","cross_cats_sorted":["cs.CL","cs.PL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-11T19:49:59Z","title_canon_sha256":"09c724e3fa6d567304d47b6fa67036d14816325d8618beffc0aa0acc58319084"},"schema_version":"1.0","source":{"id":"2507.08992","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.08992","created_at":"2026-07-05T11:36:01Z"},{"alias_kind":"arxiv_version","alias_value":"2507.08992v1","created_at":"2026-07-05T11:36:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.08992","created_at":"2026-07-05T11:36:01Z"},{"alias_kind":"pith_short_12","alias_value":"WCK3BKJZ3HIU","created_at":"2026-07-05T11:36:01Z"},{"alias_kind":"pith_short_16","alias_value":"WCK3BKJZ3HIUNVVZ","created_at":"2026-07-05T11:36:01Z"},{"alias_kind":"pith_short_8","alias_value":"WCK3BKJZ","created_at":"2026-07-05T11:36:01Z"}],"graph_snapshots":[{"event_id":"sha256:fca517404fee0df3663345799bcc9c2625fcf731d4f613558facfad18429963d","target":"graph","created_at":"2026-07-05T11:36:01Z","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/2507.08992/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Source code segmentation, dividing code into functionally coherent segments, is crucial for knowledge retrieval and maintenance in software development. While enabling efficient navigation and comprehension of large codebases, manual and syntactic analysis approaches have become impractical as repositories grow, especially for low-resource languages like R and their research domains (e.g., social sciences, psychology).This paper introduces an automated, domain-specific approach for research R code segmentation using Large and Small Language Models (LLMs/SLMs). It presents two novel approaches ","authors_text":"Abdelhalim Dahou, Ansgar Scherp, Brigitte Mathiak, Madhu Chauhan, Sebastian Kurten","cross_cats":["cs.CL","cs.PL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-11T19:49:59Z","title":"Semantic Source Code Segmentation using Small and Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.08992","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":"sha256:86d53430907a6bd80601743b13a7cb8f505b92873ed70f1ae4b3d27da277e055","target":"record","created_at":"2026-07-05T11:36:01Z","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":"e60c6b452f452b8060ecdcc947fa534954bf08bfb459158cd1db1fbeb2d97c41","cross_cats_sorted":["cs.CL","cs.PL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-11T19:49:59Z","title_canon_sha256":"09c724e3fa6d567304d47b6fa67036d14816325d8618beffc0aa0acc58319084"},"schema_version":"1.0","source":{"id":"2507.08992","kind":"arxiv","version":1}},"canonical_sha256":"b095b0a939d9d146d6b985dbb9dab204179434b65dad9ba87817d2b64c5a5b2e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b095b0a939d9d146d6b985dbb9dab204179434b65dad9ba87817d2b64c5a5b2e","first_computed_at":"2026-07-05T11:36:01.746748Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:36:01.746748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yq+KVUKgfN5UD/jW/+Cq1erpivdToDTt0y1SAWzzdHykZTeugj8wEp3NiQKTz8iydQkPxYLRAN4BN0P1Z7dpCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:36:01.747207Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.08992","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86d53430907a6bd80601743b13a7cb8f505b92873ed70f1ae4b3d27da277e055","sha256:fca517404fee0df3663345799bcc9c2625fcf731d4f613558facfad18429963d"],"state_sha256":"fda5d70a5a858fca455b045d10d8c0c6b41608ef0143ba8933c471bc38514496"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I4v/MGJ4OzYY/31Ps28lDgRU/0R5aYLCxfSuRaJM/ZSrF+b6P80AS3/T6OX4KaMvJHo5JkGyiOkVM3PNicPdCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T21:38:18.213599Z","bundle_sha256":"bdf0ff3d7a100063a61618e6f41d1ae4e3580993b8710916d4690d4d492c2d33"}}