{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:YM372FHBVGCCJLJUINL77ZP72R","short_pith_number":"pith:YM372FHB","canonical_record":{"source":{"id":"2110.08534","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-16T09:59:33Z","cross_cats_sorted":[],"title_canon_sha256":"7fda81c287e10c56f978b348ccbd50f9a6e1dbffef9a0d176e4418da4d508b74","abstract_canon_sha256":"7e099bfb43f5ef4224b61bb9513bd35ba1bb85e7b18eaa08736f654878c2bcf2"},"schema_version":"1.0"},"canonical_sha256":"c337fd14e1a98424ad344357ffe5ffd4472d5406acb20d81177d357418b2cd63","source":{"kind":"arxiv","id":"2110.08534","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.08534","created_at":"2026-07-05T04:41:10Z"},{"alias_kind":"arxiv_version","alias_value":"2110.08534v3","created_at":"2026-07-05T04:41:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.08534","created_at":"2026-07-05T04:41:10Z"},{"alias_kind":"pith_short_12","alias_value":"YM372FHBVGCC","created_at":"2026-07-05T04:41:10Z"},{"alias_kind":"pith_short_16","alias_value":"YM372FHBVGCCJLJU","created_at":"2026-07-05T04:41:10Z"},{"alias_kind":"pith_short_8","alias_value":"YM372FHB","created_at":"2026-07-05T04:41:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:YM372FHBVGCCJLJUINL77ZP72R","target":"record","payload":{"canonical_record":{"source":{"id":"2110.08534","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-16T09:59:33Z","cross_cats_sorted":[],"title_canon_sha256":"7fda81c287e10c56f978b348ccbd50f9a6e1dbffef9a0d176e4418da4d508b74","abstract_canon_sha256":"7e099bfb43f5ef4224b61bb9513bd35ba1bb85e7b18eaa08736f654878c2bcf2"},"schema_version":"1.0"},"canonical_sha256":"c337fd14e1a98424ad344357ffe5ffd4472d5406acb20d81177d357418b2cd63","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:41:10.310392Z","signature_b64":"Ao2Ky7tEo5suKIirxUBClsSJwq0jxd5uez80OP0EMrA+D1JgauZwV1Dj7IT7yow4FPZQ6QomQkkEsPfaMuquBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c337fd14e1a98424ad344357ffe5ffd4472d5406acb20d81177d357418b2cd63","last_reissued_at":"2026-07-05T04:41:10.309908Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:41:10.309908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.08534","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":"2026-07-05T04:41:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HckUQWfsqmyZgDxXPCAewsW+u3B5n5VMvjGP5HaWn+IZW2x3cdk2QpDE5hyVJSAtmXlD7RNsMtgoEqfRZGUvCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:48:54.190732Z"},"content_sha256":"afda7e595045394e72a48c9c319e288578f956815fc82132105338ceac7cf142","schema_version":"1.0","event_id":"sha256:afda7e595045394e72a48c9c319e288578f956815fc82132105338ceac7cf142"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:YM372FHBVGCCJLJUINL77ZP72R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Lifelong Pretraining: Continually Adapting Language Models to Emerging Corpora","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrew Arnold, Dejiao Zhang, Henghui Zhu, Shang-Wen Li, Wei Xiao, Xiang Ren, Xiaokai Wei, Xisen Jin","submitted_at":"2021-10-16T09:59:33Z","abstract_excerpt":"Pretrained language models (PTLMs) are typically learned over a large, static corpus and further fine-tuned for various downstream tasks. However, when deployed in the real world, a PTLM-based model must deal with data distributions that deviate from what the PTLM was initially trained on. In this paper, we study a lifelong language model pretraining challenge where a PTLM is continually updated so as to adapt to emerging data. Over a domain-incremental research paper stream and a chronologically-ordered tweet stream, we incrementally pretrain a PTLM with different continual learning algorithm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.08534","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/2110.08534/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":"2026-07-05T04:41:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a/RvpUr4pxP9D/Rrkx21CwlYT7vaKdTXkQ3VmW7MFX+TLSYVXncFpsbtWzrYmitrDclXgS6Fd/mnvP1WsbY7DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:48:54.191099Z"},"content_sha256":"15623f95aa707a4007f00e7c4ac0ca520f88d5980bb595b3723ab2f53877df43","schema_version":"1.0","event_id":"sha256:15623f95aa707a4007f00e7c4ac0ca520f88d5980bb595b3723ab2f53877df43"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YM372FHBVGCCJLJUINL77ZP72R/bundle.json","state_url":"https://pith.science/pith/YM372FHBVGCCJLJUINL77ZP72R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YM372FHBVGCCJLJUINL77ZP72R/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":"2026-07-07T12:48:54Z","links":{"resolver":"https://pith.science/pith/YM372FHBVGCCJLJUINL77ZP72R","bundle":"https://pith.science/pith/YM372FHBVGCCJLJUINL77ZP72R/bundle.json","state":"https://pith.science/pith/YM372FHBVGCCJLJUINL77ZP72R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YM372FHBVGCCJLJUINL77ZP72R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:YM372FHBVGCCJLJUINL77ZP72R","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":"7e099bfb43f5ef4224b61bb9513bd35ba1bb85e7b18eaa08736f654878c2bcf2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-16T09:59:33Z","title_canon_sha256":"7fda81c287e10c56f978b348ccbd50f9a6e1dbffef9a0d176e4418da4d508b74"},"schema_version":"1.0","source":{"id":"2110.08534","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.08534","created_at":"2026-07-05T04:41:10Z"},{"alias_kind":"arxiv_version","alias_value":"2110.08534v3","created_at":"2026-07-05T04:41:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.08534","created_at":"2026-07-05T04:41:10Z"},{"alias_kind":"pith_short_12","alias_value":"YM372FHBVGCC","created_at":"2026-07-05T04:41:10Z"},{"alias_kind":"pith_short_16","alias_value":"YM372FHBVGCCJLJU","created_at":"2026-07-05T04:41:10Z"},{"alias_kind":"pith_short_8","alias_value":"YM372FHB","created_at":"2026-07-05T04:41:10Z"}],"graph_snapshots":[{"event_id":"sha256:15623f95aa707a4007f00e7c4ac0ca520f88d5980bb595b3723ab2f53877df43","target":"graph","created_at":"2026-07-05T04:41:10Z","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/2110.08534/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretrained language models (PTLMs) are typically learned over a large, static corpus and further fine-tuned for various downstream tasks. However, when deployed in the real world, a PTLM-based model must deal with data distributions that deviate from what the PTLM was initially trained on. In this paper, we study a lifelong language model pretraining challenge where a PTLM is continually updated so as to adapt to emerging data. Over a domain-incremental research paper stream and a chronologically-ordered tweet stream, we incrementally pretrain a PTLM with different continual learning algorithm","authors_text":"Andrew Arnold, Dejiao Zhang, Henghui Zhu, Shang-Wen Li, Wei Xiao, Xiang Ren, Xiaokai Wei, Xisen Jin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-16T09:59:33Z","title":"Lifelong Pretraining: Continually Adapting Language Models to Emerging Corpora"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.08534","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:afda7e595045394e72a48c9c319e288578f956815fc82132105338ceac7cf142","target":"record","created_at":"2026-07-05T04:41:10Z","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":"7e099bfb43f5ef4224b61bb9513bd35ba1bb85e7b18eaa08736f654878c2bcf2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-16T09:59:33Z","title_canon_sha256":"7fda81c287e10c56f978b348ccbd50f9a6e1dbffef9a0d176e4418da4d508b74"},"schema_version":"1.0","source":{"id":"2110.08534","kind":"arxiv","version":3}},"canonical_sha256":"c337fd14e1a98424ad344357ffe5ffd4472d5406acb20d81177d357418b2cd63","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c337fd14e1a98424ad344357ffe5ffd4472d5406acb20d81177d357418b2cd63","first_computed_at":"2026-07-05T04:41:10.309908Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:41:10.309908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ao2Ky7tEo5suKIirxUBClsSJwq0jxd5uez80OP0EMrA+D1JgauZwV1Dj7IT7yow4FPZQ6QomQkkEsPfaMuquBw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:41:10.310392Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.08534","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:afda7e595045394e72a48c9c319e288578f956815fc82132105338ceac7cf142","sha256:15623f95aa707a4007f00e7c4ac0ca520f88d5980bb595b3723ab2f53877df43"],"state_sha256":"c329dd72aedb15da4e60f02a54a8ca8b12ad23664847f767002dbb92cabee57d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BlTEDArogupkuRH0Z4FK726EdV9sy/Irz0YoUDkBW5DOxqQYEu8KWRgMEsfKcb/eIbarUz12rhDOezYTU4cSAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:48:54.193051Z","bundle_sha256":"eca3f29fdeeff245d0b689e39bb9e2e66d59ec9372ccbea21e6d777345f2a75c"}}