{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HSCQ3LEYAECKWK43VVUEMCAZAA","short_pith_number":"pith:HSCQ3LEY","canonical_record":{"source":{"id":"2504.19856","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-28T14:49:00Z","cross_cats_sorted":[],"title_canon_sha256":"0126228fe17fd6cfb2b3bf516a5ae273b678018b9e22272fa9cad00be9020f32","abstract_canon_sha256":"c5b5dbceb8b1bdfbc80f28e10d03bc7f48515e980c6cee6fb835a2da091701c5"},"schema_version":"1.0"},"canonical_sha256":"3c850dac980104ab2b9bad684608190034fbb50bc2ee547d998d846979f7db60","source":{"kind":"arxiv","id":"2504.19856","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.19856","created_at":"2026-07-05T11:29:58Z"},{"alias_kind":"arxiv_version","alias_value":"2504.19856v3","created_at":"2026-07-05T11:29:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.19856","created_at":"2026-07-05T11:29:58Z"},{"alias_kind":"pith_short_12","alias_value":"HSCQ3LEYAECK","created_at":"2026-07-05T11:29:58Z"},{"alias_kind":"pith_short_16","alias_value":"HSCQ3LEYAECKWK43","created_at":"2026-07-05T11:29:58Z"},{"alias_kind":"pith_short_8","alias_value":"HSCQ3LEY","created_at":"2026-07-05T11:29:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HSCQ3LEYAECKWK43VVUEMCAZAA","target":"record","payload":{"canonical_record":{"source":{"id":"2504.19856","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-28T14:49:00Z","cross_cats_sorted":[],"title_canon_sha256":"0126228fe17fd6cfb2b3bf516a5ae273b678018b9e22272fa9cad00be9020f32","abstract_canon_sha256":"c5b5dbceb8b1bdfbc80f28e10d03bc7f48515e980c6cee6fb835a2da091701c5"},"schema_version":"1.0"},"canonical_sha256":"3c850dac980104ab2b9bad684608190034fbb50bc2ee547d998d846979f7db60","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:58.543779Z","signature_b64":"pzwklZBGPCE/i5fU7kiK9g8o6KrQLH274EsEljfNAkb2coKicMe9ERqUFc1a8Fu0+8CqQDIGhnUwLwPBDT/+AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c850dac980104ab2b9bad684608190034fbb50bc2ee547d998d846979f7db60","last_reissued_at":"2026-07-05T11:29:58.543207Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:58.543207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.19856","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:29:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fms5/evNboRiJqdSY3yq/yVDCf6U1g6VahBnFNTYppe3JqVu0MGkEE4idMYkVdUd8qWCa9idMLbCJb3MC/r/Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:14:51.854182Z"},"content_sha256":"ac7d4a1958ca8d3ad720c3113c992d3bbbd23ef5ac4bb74393f52d6bac250e3b","schema_version":"1.0","event_id":"sha256:ac7d4a1958ca8d3ad720c3113c992d3bbbd23ef5ac4bb74393f52d6bac250e3b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HSCQ3LEYAECKWK43VVUEMCAZAA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Domain-adaptive Continual Pretraining for the Process Industry in the German Language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anastasia Zhukova, Bela Gipp, Christian E. Matt","submitted_at":"2025-04-28T14:49:00Z","abstract_excerpt":"Domain-adaptive continual pretraining (DAPT) is a state-of-the-art technique that further trains a language model (LM) on its pretraining task, e.g., masked language modeling (MLM), when common domain adaptation via LM fine-tuning is not possible due to a lack of labeled task data. Although popular, MLM requires a significant corpus of domain-related data, which is difficult to obtain for specific domains in languages other than English, such as the process industry in the German language. This paper introduces an efficient approach called ICL-augmented pretraining or ICL-APT that leverages in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.19856","kind":"arxiv","version":3},"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/2504.19856/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":"2026-07-05T11:29:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d28HXVQRKwHcksDeqjPX3NqnwDYJJRqBUyvR9kf2uglwD5zjYXVYG1koBnpqFaBZB5q4rD5seth/tA263beQDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:14:51.854807Z"},"content_sha256":"6fdfcdcc3df40a41f98500d4809d46d6e5a4020215635bf3ab3fde6125df9d0d","schema_version":"1.0","event_id":"sha256:6fdfcdcc3df40a41f98500d4809d46d6e5a4020215635bf3ab3fde6125df9d0d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HSCQ3LEYAECKWK43VVUEMCAZAA/bundle.json","state_url":"https://pith.science/pith/HSCQ3LEYAECKWK43VVUEMCAZAA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HSCQ3LEYAECKWK43VVUEMCAZAA/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":"2026-07-07T05:14:51Z","links":{"resolver":"https://pith.science/pith/HSCQ3LEYAECKWK43VVUEMCAZAA","bundle":"https://pith.science/pith/HSCQ3LEYAECKWK43VVUEMCAZAA/bundle.json","state":"https://pith.science/pith/HSCQ3LEYAECKWK43VVUEMCAZAA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HSCQ3LEYAECKWK43VVUEMCAZAA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HSCQ3LEYAECKWK43VVUEMCAZAA","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":"c5b5dbceb8b1bdfbc80f28e10d03bc7f48515e980c6cee6fb835a2da091701c5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-28T14:49:00Z","title_canon_sha256":"0126228fe17fd6cfb2b3bf516a5ae273b678018b9e22272fa9cad00be9020f32"},"schema_version":"1.0","source":{"id":"2504.19856","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.19856","created_at":"2026-07-05T11:29:58Z"},{"alias_kind":"arxiv_version","alias_value":"2504.19856v3","created_at":"2026-07-05T11:29:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.19856","created_at":"2026-07-05T11:29:58Z"},{"alias_kind":"pith_short_12","alias_value":"HSCQ3LEYAECK","created_at":"2026-07-05T11:29:58Z"},{"alias_kind":"pith_short_16","alias_value":"HSCQ3LEYAECKWK43","created_at":"2026-07-05T11:29:58Z"},{"alias_kind":"pith_short_8","alias_value":"HSCQ3LEY","created_at":"2026-07-05T11:29:58Z"}],"graph_snapshots":[{"event_id":"sha256:6fdfcdcc3df40a41f98500d4809d46d6e5a4020215635bf3ab3fde6125df9d0d","target":"graph","created_at":"2026-07-05T11:29:58Z","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/2504.19856/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Domain-adaptive continual pretraining (DAPT) is a state-of-the-art technique that further trains a language model (LM) on its pretraining task, e.g., masked language modeling (MLM), when common domain adaptation via LM fine-tuning is not possible due to a lack of labeled task data. Although popular, MLM requires a significant corpus of domain-related data, which is difficult to obtain for specific domains in languages other than English, such as the process industry in the German language. This paper introduces an efficient approach called ICL-augmented pretraining or ICL-APT that leverages in","authors_text":"Anastasia Zhukova, Bela Gipp, Christian E. Matt","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-28T14:49:00Z","title":"Efficient Domain-adaptive Continual Pretraining for the Process Industry in the German Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.19856","kind":"arxiv","version":3},"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:ac7d4a1958ca8d3ad720c3113c992d3bbbd23ef5ac4bb74393f52d6bac250e3b","target":"record","created_at":"2026-07-05T11:29:58Z","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":"c5b5dbceb8b1bdfbc80f28e10d03bc7f48515e980c6cee6fb835a2da091701c5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-28T14:49:00Z","title_canon_sha256":"0126228fe17fd6cfb2b3bf516a5ae273b678018b9e22272fa9cad00be9020f32"},"schema_version":"1.0","source":{"id":"2504.19856","kind":"arxiv","version":3}},"canonical_sha256":"3c850dac980104ab2b9bad684608190034fbb50bc2ee547d998d846979f7db60","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3c850dac980104ab2b9bad684608190034fbb50bc2ee547d998d846979f7db60","first_computed_at":"2026-07-05T11:29:58.543207Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:58.543207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pzwklZBGPCE/i5fU7kiK9g8o6KrQLH274EsEljfNAkb2coKicMe9ERqUFc1a8Fu0+8CqQDIGhnUwLwPBDT/+AA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:58.543779Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.19856","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac7d4a1958ca8d3ad720c3113c992d3bbbd23ef5ac4bb74393f52d6bac250e3b","sha256:6fdfcdcc3df40a41f98500d4809d46d6e5a4020215635bf3ab3fde6125df9d0d"],"state_sha256":"34b73fcfc87ebcb290ec76d2b7f759c020c508a13ffa6c60f5588c350b8451a3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xw4VPpahn9ZcrdcZx2iZmwA6DwiPa0FVi3sj88zLAKZPWJtTWGtHXWl8KNTfup8EV7kiDeoKX/nm9dRo962qAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T05:14:51.858418Z","bundle_sha256":"e530bdf2df66214b7f4da4d97e85037d9500dab13c76f049bc65a7aaab9e44cc"}}