{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/continual-pre-training-mitigates-forgetting","title":"Continual Pre-Training Mitigates Forgetting in Language and Vision","arxiv_id":"2205.09357","date":"2022-05-19","proceeding":null,"authors":["Andrea Cossu","Tinne Tuytelaars","Antonio Carta","Lucia Passaro","Vincenzo Lomonaco","Davide Bacciu"],"abstract":"Pre-trained models are nowadays a fundamental component of machine learning research. In continual learning, they are commonly used to initialize the model before training on the stream of non-stationary data. However, pre-training is rarely applied during continual learning. We formalize and investigate the characteristics of the continual pre-training scenario in both language and vision environments, where a model is continually pre-trained on a stream of incoming data and only later fine-tuned to different downstream tasks. We show that continually pre-trained models are robust against catastrophic forgetting and we provide strong empirical evidence supporting the fact that self-supervised pre-training is more effective in retaining previous knowledge than supervised protocols. Code is provided at https://github.com/AndreaCossu/continual-pretraining-nlp-vision .","url_abs":"https://arxiv.org/abs/2205.09357v1","url_pdf":"https://arxiv.org/pdf/2205.09357v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"continual-pre-training-mitigates-forgetting","repo_url":"https://github.com/andreacossu/continual-pretraining-nlp-vision","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"continual-pretraining","task_name":"Continual Pretraining"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2205.09357","atlas_url":"https://app.syntology.ai/?focus=2205.09357","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.09357"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2205.09357"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2205.09357"},"call":"get_harvested_code_for_paper(arxiv_id=\"2205.09357\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2205.09357"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2205.09357\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2205.09357"},"call":"get_concepts_for_paper(arxiv_id=\"2205.09357\")"}],"by_repo":[{"repo":"andreacossu/continual-pretraining-nlp-vision","kind":"official","samples":7,"ran":6,"instrument":0,"unverified":1}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2205.09357.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2205.09357.svg"},"claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/andreacossu/continual-pretraining-nlp-vision","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":6,"unverified":1},"n_samples":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":7,"ran":6,"n_ran_checked":6,"n_instrument":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":6,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-24","last":"2026-09-24","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"4f1b09f46b03c233","code_sha256_prefix":"4f1b09f46b03c233","entry":"add_colorbar","repo":"andreacossu/continual-pretraining-nlp-vision","repo_kind":"official","path":"cka.py","file_url":"https://github.com/andreacossu/continual-pretraining-nlp-vision/blob/HEAD/cka.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"im:AxesImage/0/?, aspect:int/0/int, pad_fraction:float/0/float","fixture_out_type":"Colorbar","level_recorded_at":"2026-09-24T21:23:57.672461+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"4f1b09f46b03c233"}},{"code_sha256":"2ed8cd5f08e8e626","code_sha256_prefix":"2ed8cd5f08e8e626","entry":"create_tokenizer_cl","repo":"andreacossu/continual-pretraining-nlp-vision","repo_kind":"official","path":"utils.py","file_url":"https://github.com/andreacossu/continual-pretraining-nlp-vision/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"tokenizer_name:str/0/str, exp_id:int/0/int, add_tokens:bool/0/bool","fixture_out_type":"Mock","level_recorded_at":"2026-09-24T21:23:57.672461+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"2ed8cd5f08e8e626"}},{"code_sha256":"249e014939153c23","code_sha256_prefix":"249e014939153c23","entry":"mean_pooling","repo":"andreacossu/continual-pretraining-nlp-vision","repo_kind":"official","path":"senteval.py","file_url":"https://github.com/andreacossu/continual-pretraining-nlp-vision/blob/HEAD/senteval.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"model_output:Tensor/3/float, attention_mask:Tensor/2/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T21:23:57.672461+00:00","retrieve_with":{"tool":"get_code","code_sha256":"249e014939153c23"},"code_page":"/code/mean-pooling","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"249e014939153c23"}},{"code_sha256":"5a1f7cf9990b1ac9","code_sha256_prefix":"5a1f7cf9990b1ac9","entry":"mycollate","repo":"andreacossu/continual-pretraining-nlp-vision","repo_kind":"official","path":"continual-pretraining-cv-unsupervised.py","file_url":"https://github.com/andreacossu/continual-pretraining-nlp-vision/blob/HEAD/continual-pretraining-cv-unsupervised.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"batch:list/1/tuple","fixture_out_type":"list","level_recorded_at":"2026-09-24T21:23:57.672461+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"5a1f7cf9990b1ac9"}},{"code_sha256":"c7fe1178d14f6de8","code_sha256_prefix":"c7fe1178d14f6de8","entry":"mycollate_mbatches","repo":"andreacossu/continual-pretraining-nlp-vision","repo_kind":"official","path":"continual-pretraining-cv-unsupervised.py","file_url":"https://github.com/andreacossu/continual-pretraining-nlp-vision/blob/HEAD/continual-pretraining-cv-unsupervised.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"mbatches:list/1/list","fixture_out_type":"list","level_recorded_at":"2026-09-24T21:54:21.362907+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"c7fe1178d14f6de8"}},{"code_sha256":"c734372fb6ca5cba","code_sha256_prefix":"c734372fb6ca5cba","entry":"remap_classes","repo":"andreacossu/continual-pretraining-nlp-vision","repo_kind":"official","path":"utils.py","file_url":"https://github.com/andreacossu/continual-pretraining-nlp-vision/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"example:dict/0/?","fixture_out_type":"dict","level_recorded_at":"2026-09-24T21:54:21.362907+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"c734372fb6ca5cba"}},{"code_sha256":"219b7aaf978adc4f","code_sha256_prefix":"219b7aaf978adc4f","entry":"create_tokenizer","repo":"andreacossu/continual-pretraining-nlp-vision","repo_kind":"official","path":"utils.py","file_url":"https://github.com/andreacossu/continual-pretraining-nlp-vision/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/create-tokenizer","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"219b7aaf978adc4f"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"49a13a83eb433f4559b51c72a977f97e52825768caf6d40a6cfee14d5dd2dbe7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}