{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TTFXGXN46NWYI442UKXEYP44FG","short_pith_number":"pith:TTFXGXN4","canonical_record":{"source":{"id":"2503.15055","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-19T09:46:54Z","cross_cats_sorted":[],"title_canon_sha256":"05faacb173082cdf7f0e425a802025469722d3b59f0d8743f98b4c70e1dbdafe","abstract_canon_sha256":"ccace67b6f547b96f1c9012ba1ef423ab29b4e0887c50ccd5eaef5569b4673dd"},"schema_version":"1.0"},"canonical_sha256":"9ccb735dbcf36d84739aa2ae4c3f9c299cbbf72ae7545db4bfe5fde427f78d12","source":{"kind":"arxiv","id":"2503.15055","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.15055","created_at":"2026-07-05T10:49:15Z"},{"alias_kind":"arxiv_version","alias_value":"2503.15055v2","created_at":"2026-07-05T10:49:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15055","created_at":"2026-07-05T10:49:15Z"},{"alias_kind":"pith_short_12","alias_value":"TTFXGXN46NWY","created_at":"2026-07-05T10:49:15Z"},{"alias_kind":"pith_short_16","alias_value":"TTFXGXN46NWYI442","created_at":"2026-07-05T10:49:15Z"},{"alias_kind":"pith_short_8","alias_value":"TTFXGXN4","created_at":"2026-07-05T10:49:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TTFXGXN46NWYI442UKXEYP44FG","target":"record","payload":{"canonical_record":{"source":{"id":"2503.15055","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-19T09:46:54Z","cross_cats_sorted":[],"title_canon_sha256":"05faacb173082cdf7f0e425a802025469722d3b59f0d8743f98b4c70e1dbdafe","abstract_canon_sha256":"ccace67b6f547b96f1c9012ba1ef423ab29b4e0887c50ccd5eaef5569b4673dd"},"schema_version":"1.0"},"canonical_sha256":"9ccb735dbcf36d84739aa2ae4c3f9c299cbbf72ae7545db4bfe5fde427f78d12","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:15.636695Z","signature_b64":"e36Y5nCuYhq1LMputtG7eMT+OMy/eBssHQPP062jG0nsWYUyxfvRxusGbujgNQ59JDoOOC7z89d5DVx4M5djDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ccb735dbcf36d84739aa2ae4c3f9c299cbbf72ae7545db4bfe5fde427f78d12","last_reissued_at":"2026-07-05T10:49:15.636239Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:15.636239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.15055","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":"2026-07-05T10:49:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U5uvgRP5AhnmFkrRucYJaw/LdzUmvYDlaxklqw6FUepzrVU/FkIQztYNkp6q41732jwZUGz9BXH96JRPNuMZCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T00:51:44.145359Z"},"content_sha256":"b45f9b3ce3ee058266fb2843f8ab7727f14506ff46d11c04741b524e8dfe59e5","schema_version":"1.0","event_id":"sha256:b45f9b3ce3ee058266fb2843f8ab7727f14506ff46d11c04741b524e8dfe59e5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TTFXGXN46NWYI442UKXEYP44FG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ELTEX: A Framework for Domain-Driven Synthetic Data Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arina Razmyslovich, Eugene Dmitriev, Julien Capitaine, Kseniia Murasheva, Sofia Sedlova","submitted_at":"2025-03-19T09:46:54Z","abstract_excerpt":"We introduce Efficient LLM Token Extraction (ELTEX), a framework addressing the critical challenge of LLM domain specialization by systematically extracting and integrating domain indicators throughout synthetic data generation. Unlike approaches relying on implicit knowledge transfer, ELTEX explicitly leverages domain signals to maintain specialized knowledge integrity. In our cybersecurity case study, ELTEX-enhanced data enables a fine-tuned Gemma-2B model to achieve performance competitive with GPT-4o on blockchain cyberattack classification while reducing computational requirements. Our Go"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.15055","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/2503.15055/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":"2026-07-05T10:49:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/dsbv1eCg7pYwMck58bQbpcNFsS7yq9LYsswt/iQzkHfqDVzj4UuhSgyeSUwt5gEv4HQ4edVWUZfBG232qjlBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T00:51:44.145981Z"},"content_sha256":"d1f7d480da026bf4c9f6b9e54c0c768a0e1665570e6efe11330da61bd2315eb5","schema_version":"1.0","event_id":"sha256:d1f7d480da026bf4c9f6b9e54c0c768a0e1665570e6efe11330da61bd2315eb5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TTFXGXN46NWYI442UKXEYP44FG/bundle.json","state_url":"https://pith.science/pith/TTFXGXN46NWYI442UKXEYP44FG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TTFXGXN46NWYI442UKXEYP44FG/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":"2026-07-07T00:51:44Z","links":{"resolver":"https://pith.science/pith/TTFXGXN46NWYI442UKXEYP44FG","bundle":"https://pith.science/pith/TTFXGXN46NWYI442UKXEYP44FG/bundle.json","state":"https://pith.science/pith/TTFXGXN46NWYI442UKXEYP44FG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TTFXGXN46NWYI442UKXEYP44FG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TTFXGXN46NWYI442UKXEYP44FG","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":"ccace67b6f547b96f1c9012ba1ef423ab29b4e0887c50ccd5eaef5569b4673dd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-19T09:46:54Z","title_canon_sha256":"05faacb173082cdf7f0e425a802025469722d3b59f0d8743f98b4c70e1dbdafe"},"schema_version":"1.0","source":{"id":"2503.15055","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.15055","created_at":"2026-07-05T10:49:15Z"},{"alias_kind":"arxiv_version","alias_value":"2503.15055v2","created_at":"2026-07-05T10:49:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15055","created_at":"2026-07-05T10:49:15Z"},{"alias_kind":"pith_short_12","alias_value":"TTFXGXN46NWY","created_at":"2026-07-05T10:49:15Z"},{"alias_kind":"pith_short_16","alias_value":"TTFXGXN46NWYI442","created_at":"2026-07-05T10:49:15Z"},{"alias_kind":"pith_short_8","alias_value":"TTFXGXN4","created_at":"2026-07-05T10:49:15Z"}],"graph_snapshots":[{"event_id":"sha256:d1f7d480da026bf4c9f6b9e54c0c768a0e1665570e6efe11330da61bd2315eb5","target":"graph","created_at":"2026-07-05T10:49:15Z","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/2503.15055/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Efficient LLM Token Extraction (ELTEX), a framework addressing the critical challenge of LLM domain specialization by systematically extracting and integrating domain indicators throughout synthetic data generation. Unlike approaches relying on implicit knowledge transfer, ELTEX explicitly leverages domain signals to maintain specialized knowledge integrity. In our cybersecurity case study, ELTEX-enhanced data enables a fine-tuned Gemma-2B model to achieve performance competitive with GPT-4o on blockchain cyberattack classification while reducing computational requirements. Our Go","authors_text":"Arina Razmyslovich, Eugene Dmitriev, Julien Capitaine, Kseniia Murasheva, Sofia Sedlova","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-19T09:46:54Z","title":"ELTEX: A Framework for Domain-Driven Synthetic Data Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.15055","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:b45f9b3ce3ee058266fb2843f8ab7727f14506ff46d11c04741b524e8dfe59e5","target":"record","created_at":"2026-07-05T10:49:15Z","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":"ccace67b6f547b96f1c9012ba1ef423ab29b4e0887c50ccd5eaef5569b4673dd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-19T09:46:54Z","title_canon_sha256":"05faacb173082cdf7f0e425a802025469722d3b59f0d8743f98b4c70e1dbdafe"},"schema_version":"1.0","source":{"id":"2503.15055","kind":"arxiv","version":2}},"canonical_sha256":"9ccb735dbcf36d84739aa2ae4c3f9c299cbbf72ae7545db4bfe5fde427f78d12","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9ccb735dbcf36d84739aa2ae4c3f9c299cbbf72ae7545db4bfe5fde427f78d12","first_computed_at":"2026-07-05T10:49:15.636239Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:49:15.636239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e36Y5nCuYhq1LMputtG7eMT+OMy/eBssHQPP062jG0nsWYUyxfvRxusGbujgNQ59JDoOOC7z89d5DVx4M5djDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:49:15.636695Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.15055","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b45f9b3ce3ee058266fb2843f8ab7727f14506ff46d11c04741b524e8dfe59e5","sha256:d1f7d480da026bf4c9f6b9e54c0c768a0e1665570e6efe11330da61bd2315eb5"],"state_sha256":"2397af244991f18d8df203fe0163d2e6a1aaeaa91c1d89f7f7e7ca7026594e5e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iQkDBF8gxr+dZs3lpIgwiuGPaabAjbubbAbUa8lzEcf1qgWyVlxaAgtJcODUnM0XJ/FMykJVx56gKm4jU89YAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T00:51:44.149619Z","bundle_sha256":"a833718aca1a7abdde51a0f2e69d242ae187e007743ba337d336f15b6958cbf5"}}