{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:M2P3SPPQ3M6W7OQUFWWUIJ64KX","short_pith_number":"pith:M2P3SPPQ","canonical_record":{"source":{"id":"2309.09530","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-18T07:17:52Z","cross_cats_sorted":[],"title_canon_sha256":"6113eb21caaf05f8b02f31fcdc48725e9d0cd3ed9dd8952ee07fce62b365f3ed","abstract_canon_sha256":"5e7d7307adf01c2e803c22715e73eb3e448fb52892aa64768bc9533f3a8923c5"},"schema_version":"1.0"},"canonical_sha256":"669fb93df0db3d6fba142dad4427dc55f516dbafb3f0ef046b470cd4db80075c","source":{"kind":"arxiv","id":"2309.09530","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.09530","created_at":"2026-07-05T08:48:11Z"},{"alias_kind":"arxiv_version","alias_value":"2309.09530v4","created_at":"2026-07-05T08:48:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.09530","created_at":"2026-07-05T08:48:11Z"},{"alias_kind":"pith_short_12","alias_value":"M2P3SPPQ3M6W","created_at":"2026-07-05T08:48:11Z"},{"alias_kind":"pith_short_16","alias_value":"M2P3SPPQ3M6W7OQU","created_at":"2026-07-05T08:48:11Z"},{"alias_kind":"pith_short_8","alias_value":"M2P3SPPQ","created_at":"2026-07-05T08:48:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:M2P3SPPQ3M6W7OQUFWWUIJ64KX","target":"record","payload":{"canonical_record":{"source":{"id":"2309.09530","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-18T07:17:52Z","cross_cats_sorted":[],"title_canon_sha256":"6113eb21caaf05f8b02f31fcdc48725e9d0cd3ed9dd8952ee07fce62b365f3ed","abstract_canon_sha256":"5e7d7307adf01c2e803c22715e73eb3e448fb52892aa64768bc9533f3a8923c5"},"schema_version":"1.0"},"canonical_sha256":"669fb93df0db3d6fba142dad4427dc55f516dbafb3f0ef046b470cd4db80075c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:11.043527Z","signature_b64":"fOXTcjNxjsF69ra1smq7kIcx1VLCekuU1VJdDG9yxBr+284u1pr5LpXKvbzsGWGYUZNtKZoyftUiE/n1qEz6CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"669fb93df0db3d6fba142dad4427dc55f516dbafb3f0ef046b470cd4db80075c","last_reissued_at":"2026-07-05T08:48:11.043052Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:11.043052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.09530","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:48:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8P829hElIi1BSNdcOULBqsXAqAczCBbHLIQULaXKWOO+xraS9u81jZn+scY/SwtGDplmIN6H1B/4IL+wi/smDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:05:23.308536Z"},"content_sha256":"4792aeccbc78bc7622672b74eaf597b51cfad3f5a72b03b8c5a44ef396b1e7d7","schema_version":"1.0","event_id":"sha256:4792aeccbc78bc7622672b74eaf597b51cfad3f5a72b03b8c5a44ef396b1e7d7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:M2P3SPPQ3M6W7OQUFWWUIJ64KX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adapting Large Language Models to Domains via Reading Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daixuan Cheng, Furu Wei, Shaohan Huang","submitted_at":"2023-09-18T07:17:52Z","abstract_excerpt":"We explore how continued pre-training on domain-specific corpora influences large language models, revealing that training on the raw corpora endows the model with domain knowledge, but drastically hurts its prompting ability for question answering. Taken inspiration from human learning via reading comprehension--practice after reading improves the ability to answer questions based on the learned knowledge--we propose a simple method for transforming raw corpora into reading comprehension texts. Each raw text is enriched with a series of tasks related to its content. Our method, highly scalabl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.09530","kind":"arxiv","version":4},"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/2309.09530/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":"2026-07-05T08:48:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YoDHnzCG0qkL+YWbU/ZAlL24IcSddf9b4jLLnWQelLKwpBHP0q4R8r6BeDHe4JMiN2tdzVwTKm3w0RofNmcDAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:05:23.309064Z"},"content_sha256":"891cbcca30e80947beaaf82327f54b3bbcb4ad1bf8d4c2782e8efb1a72478581","schema_version":"1.0","event_id":"sha256:891cbcca30e80947beaaf82327f54b3bbcb4ad1bf8d4c2782e8efb1a72478581"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M2P3SPPQ3M6W7OQUFWWUIJ64KX/bundle.json","state_url":"https://pith.science/pith/M2P3SPPQ3M6W7OQUFWWUIJ64KX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M2P3SPPQ3M6W7OQUFWWUIJ64KX/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":"2026-08-07T18:05:23Z","links":{"resolver":"https://pith.science/pith/M2P3SPPQ3M6W7OQUFWWUIJ64KX","bundle":"https://pith.science/pith/M2P3SPPQ3M6W7OQUFWWUIJ64KX/bundle.json","state":"https://pith.science/pith/M2P3SPPQ3M6W7OQUFWWUIJ64KX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M2P3SPPQ3M6W7OQUFWWUIJ64KX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:M2P3SPPQ3M6W7OQUFWWUIJ64KX","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":"5e7d7307adf01c2e803c22715e73eb3e448fb52892aa64768bc9533f3a8923c5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-18T07:17:52Z","title_canon_sha256":"6113eb21caaf05f8b02f31fcdc48725e9d0cd3ed9dd8952ee07fce62b365f3ed"},"schema_version":"1.0","source":{"id":"2309.09530","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.09530","created_at":"2026-07-05T08:48:11Z"},{"alias_kind":"arxiv_version","alias_value":"2309.09530v4","created_at":"2026-07-05T08:48:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.09530","created_at":"2026-07-05T08:48:11Z"},{"alias_kind":"pith_short_12","alias_value":"M2P3SPPQ3M6W","created_at":"2026-07-05T08:48:11Z"},{"alias_kind":"pith_short_16","alias_value":"M2P3SPPQ3M6W7OQU","created_at":"2026-07-05T08:48:11Z"},{"alias_kind":"pith_short_8","alias_value":"M2P3SPPQ","created_at":"2026-07-05T08:48:11Z"}],"graph_snapshots":[{"event_id":"sha256:891cbcca30e80947beaaf82327f54b3bbcb4ad1bf8d4c2782e8efb1a72478581","target":"graph","created_at":"2026-07-05T08:48:11Z","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/2309.09530/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We explore how continued pre-training on domain-specific corpora influences large language models, revealing that training on the raw corpora endows the model with domain knowledge, but drastically hurts its prompting ability for question answering. Taken inspiration from human learning via reading comprehension--practice after reading improves the ability to answer questions based on the learned knowledge--we propose a simple method for transforming raw corpora into reading comprehension texts. Each raw text is enriched with a series of tasks related to its content. Our method, highly scalabl","authors_text":"Daixuan Cheng, Furu Wei, Shaohan Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-18T07:17:52Z","title":"Adapting Large Language Models to Domains via Reading Comprehension"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.09530","kind":"arxiv","version":4},"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":"sha256:4792aeccbc78bc7622672b74eaf597b51cfad3f5a72b03b8c5a44ef396b1e7d7","target":"record","created_at":"2026-07-05T08:48:11Z","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":"5e7d7307adf01c2e803c22715e73eb3e448fb52892aa64768bc9533f3a8923c5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-18T07:17:52Z","title_canon_sha256":"6113eb21caaf05f8b02f31fcdc48725e9d0cd3ed9dd8952ee07fce62b365f3ed"},"schema_version":"1.0","source":{"id":"2309.09530","kind":"arxiv","version":4}},"canonical_sha256":"669fb93df0db3d6fba142dad4427dc55f516dbafb3f0ef046b470cd4db80075c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"669fb93df0db3d6fba142dad4427dc55f516dbafb3f0ef046b470cd4db80075c","first_computed_at":"2026-07-05T08:48:11.043052Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:48:11.043052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fOXTcjNxjsF69ra1smq7kIcx1VLCekuU1VJdDG9yxBr+284u1pr5LpXKvbzsGWGYUZNtKZoyftUiE/n1qEz6CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:48:11.043527Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.09530","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4792aeccbc78bc7622672b74eaf597b51cfad3f5a72b03b8c5a44ef396b1e7d7","sha256:891cbcca30e80947beaaf82327f54b3bbcb4ad1bf8d4c2782e8efb1a72478581"],"state_sha256":"d5a87b19e03673592f896c8d6805f66627f88f11b3fa10d1272ff025faed7361"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Dd65WGZz4H5inPBt/3rQParzSitVCXvQ1mjN66gR0wS5eC5qIVIV0TYK08stXZzHjWYlHQV933kq+RAHmniVDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T18:05:23.313299Z","bundle_sha256":"e898000deb19e5c43c07dd831b15d56d9a313c4710af504610a132d0fe848363"}}