{"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/understanding-in-context-learning-from","title":"Understanding In-Context Learning from Repetitions","arxiv_id":"2310.00297","date":"2023-09-30","proceeding":null,"authors":["Jianhao Yan","Jin Xu","Chiyu Song","Chenming Wu","Yafu Li","Yue Zhang"],"abstract":"This paper explores the elusive mechanism underpinning in-context learning in Large Language Models (LLMs). Our work provides a novel perspective by examining in-context learning via the lens of surface repetitions. We quantitatively investigate the role of surface features in text generation, and empirically establish the existence of \\emph{token co-occurrence reinforcement}, a principle that strengthens the relationship between two tokens based on their contextual co-occurrences. By investigating the dual impacts of these features, our research illuminates the internal workings of in-context learning and expounds on the reasons for its failures. This paper provides an essential contribution to the understanding of in-context learning and its potential limitations, providing a fresh perspective on this exciting capability.","url_abs":"https://arxiv.org/abs/2310.00297v3","url_pdf":"https://arxiv.org/pdf/2310.00297v3.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":"understanding-in-context-learning-from","repo_url":"https://github.com/elliottyan/understand-icl-from-repetition","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"in-context-learning","task_name":"In-Context Learning"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2310.00297","atlas_url":"https://app.syntology.ai/?focus=2310.00297","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.00297"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2310.00297"},"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":"2310.00297"},"call":"get_harvested_code_for_paper(arxiv_id=\"2310.00297\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2310.00297"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2310.00297\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2310.00297"},"call":"get_concepts_for_paper(arxiv_id=\"2310.00297\")"}],"by_repo":[{"repo":"elliottyan/understand-icl-from-repetition","kind":"official","samples":16,"ran":4,"instrument":0,"unverified":12}],"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/2310.00297.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/2310.00297.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/elliottyan/understand-icl-from-repetition","reach":{"status":"ok"}}],"summary":{"ran":4,"unverified":12},"n_samples":16,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":12,"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":16,"ran":4,"n_ran_checked":4,"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":16,"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":4,"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":"29f5d4f54911d0c4","code_sha256_prefix":"29f5d4f54911d0c4","entry":"build_custom_parser","repo":"elliottyan/understand-icl-from-repetition","repo_kind":"official","path":"analyze_icl_rep/analyze_icl_random_2_tokens.py","file_url":"https://github.com/elliottyan/understand-icl-from-repetition/blob/HEAD/analyze_icl_rep/analyze_icl_random_2_tokens.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"parser:ArgumentParser/0/?","fixture_out_type":"ArgumentParser","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, elliottyan/understand-icl-from-repetition when it was checked","mcp_get_code":{"code_sha256":"29f5d4f54911d0c4"}},{"code_sha256":"c027fc249dfe28e3","code_sha256_prefix":"c027fc249dfe28e3","entry":"build_custom_parser","repo":"elliottyan/understand-icl-from-repetition","repo_kind":"official","path":"analyze_icl_rep/analyze_icl_semantic_2_phrase.py","file_url":"https://github.com/elliottyan/understand-icl-from-repetition/blob/HEAD/analyze_icl_rep/analyze_icl_semantic_2_phrase.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"parser:ArgumentParser/0/?","fixture_out_type":"ArgumentParser","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, elliottyan/understand-icl-from-repetition when it was checked","mcp_get_code":{"code_sha256":"c027fc249dfe28e3"}},{"code_sha256":"da9a2d07dd8aa31a","code_sha256_prefix":"da9a2d07dd8aa31a","entry":"format_subject","repo":"elliottyan/understand-icl-from-repetition","repo_kind":"official","path":"analyze_icl_rep/analyze_mmlu_label_space.py","file_url":"https://github.com/elliottyan/understand-icl-from-repetition/blob/HEAD/analyze_icl_rep/analyze_mmlu_label_space.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"subject:str/0/str","fixture_out_type":"str","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","retrieve_with":{"tool":"get_code","code_sha256":"da9a2d07dd8aa31a"},"code_page":"/code/format-subject","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, elliottyan/understand-icl-from-repetition when it was checked","mcp_get_code":{"code_sha256":"da9a2d07dd8aa31a"}},{"code_sha256":"cc095a6dcfbe16c4","code_sha256_prefix":"cc095a6dcfbe16c4","entry":"replace_idx_with_random_tokens","repo":"elliottyan/understand-icl-from-repetition","repo_kind":"official","path":"analyze_icl_rep/analyze_gsm8k_cot.py","file_url":"https://github.com/elliottyan/understand-icl-from-repetition/blob/HEAD/analyze_icl_rep/analyze_gsm8k_cot.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"tokenizer:MockTokenizer/0/?, tensor:Tensor/2/int, args:MockArgs/0/?","fixture_out_type":"str","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, elliottyan/understand-icl-from-repetition when it was checked","mcp_get_code":{"code_sha256":"cc095a6dcfbe16c4"}},{"code_sha256":"127d4c9d3dee7015","code_sha256_prefix":"127d4c9d3dee7015","entry":"build_custom_parser","repo":"elliottyan/understand-icl-from-repetition","repo_kind":"official","path":"analyze_icl_rep/analyze_gsm8k_cot.py","file_url":"https://github.com/elliottyan/understand-icl-from-repetition/blob/HEAD/analyze_icl_rep/analyze_gsm8k_cot.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, elliottyan/understand-icl-from-repetition when it was checked","mcp_get_code":{"code_sha256":"127d4c9d3dee7015"}},{"code_sha256":"4e66424c29ed15de","code_sha256_prefix":"4e66424c29ed15de","entry":"compute_stats_dict","repo":"elliottyan/understand-icl-from-repetition","repo_kind":"official","path":"analyze_icl_rep/analyze_icl_random_mask.py","file_url":"https://github.com/elliottyan/understand-icl-from-repetition/blob/HEAD/analyze_icl_rep/analyze_icl_random_mask.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, elliottyan/understand-icl-from-repetition when it was checked","mcp_get_code":{"code_sha256":"4e66424c29ed15de"}},{"code_sha256":"94272d35afe37f93","code_sha256_prefix":"94272d35afe37f93","entry":"replace_text_with_random_tokens","repo":"elliottyan/understand-icl-from-repetition","repo_kind":"official","path":"analyze_icl_rep/analyze_gsm8k_cot.py","file_url":"https://github.com/elliottyan/understand-icl-from-repetition/blob/HEAD/analyze_icl_rep/analyze_gsm8k_cot.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, elliottyan/understand-icl-from-repetition when it was checked","mcp_get_code":{"code_sha256":"94272d35afe37f93"}},{"code_sha256":"e1b97bfe6a33ee26","code_sha256_prefix":"e1b97bfe6a33ee26","entry":"single_sentence_eval","repo":"elliottyan/understand-icl-from-repetition","repo_kind":"official","path":"analyze_icl_rep/analyze_self_reinforce.py","file_url":"https://github.com/elliottyan/understand-icl-from-repetition/blob/HEAD/analyze_icl_rep/analyze_self_reinforce.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, elliottyan/understand-icl-from-repetition when it was checked","mcp_get_code":{"code_sha256":"e1b97bfe6a33ee26"}},{"code_sha256":"c39bbde81028ab56","code_sha256_prefix":"c39bbde81028ab56","entry":"single_sentence_eval_2_phrase","repo":"elliottyan/understand-icl-from-repetition","repo_kind":"official","path":"analyze_icl_rep/analyze_icl_random_2_phrase.py","file_url":"https://github.com/elliottyan/understand-icl-from-repetition/blob/HEAD/analyze_icl_rep/analyze_icl_random_2_phrase.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, elliottyan/understand-icl-from-repetition when it was checked","mcp_get_code":{"code_sha256":"c39bbde81028ab56"}},{"code_sha256":"e4546e761c326e3e","code_sha256_prefix":"e4546e761c326e3e","entry":"single_sentence_eval_2_phrase","repo":"elliottyan/understand-icl-from-repetition","repo_kind":"official","path":"analyze_icl_rep/analyze_icl_random_2_phrase_control_distance.py","file_url":"https://github.com/elliottyan/understand-icl-from-repetition/blob/HEAD/analyze_icl_rep/analyze_icl_random_2_phrase_control_distance.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, elliottyan/understand-icl-from-repetition when it was checked","mcp_get_code":{"code_sha256":"e4546e761c326e3e"}},{"code_sha256":"a215a17f8a43dd5b","code_sha256_prefix":"a215a17f8a43dd5b","entry":"single_sentence_eval_2_phrase","repo":"elliottyan/understand-icl-from-repetition","repo_kind":"official","path":"analyze_icl_rep/analyze_icl_random_2_phrase_stop_words.py","file_url":"https://github.com/elliottyan/understand-icl-from-repetition/blob/HEAD/analyze_icl_rep/analyze_icl_random_2_phrase_stop_words.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, elliottyan/understand-icl-from-repetition when it was checked","mcp_get_code":{"code_sha256":"a215a17f8a43dd5b"}},{"code_sha256":"405e51c0abc050da","code_sha256_prefix":"405e51c0abc050da","entry":"single_sentence_eval_2_phrase","repo":"elliottyan/understand-icl-from-repetition","repo_kind":"official","path":"analyze_icl_rep/analyze_icl_semantic_2_phrase.py","file_url":"https://github.com/elliottyan/understand-icl-from-repetition/blob/HEAD/analyze_icl_rep/analyze_icl_semantic_2_phrase.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, elliottyan/understand-icl-from-repetition when it was checked","mcp_get_code":{"code_sha256":"405e51c0abc050da"}},{"code_sha256":"5ee4fd4e2eaab0d2","code_sha256_prefix":"5ee4fd4e2eaab0d2","entry":"single_sentence_eval_2_phrase_neighbour","repo":"elliottyan/understand-icl-from-repetition","repo_kind":"official","path":"analyze_icl_rep/analyze_icl_random_2_phrase_control_distance_embed_neighbour.py","file_url":"https://github.com/elliottyan/understand-icl-from-repetition/blob/HEAD/analyze_icl_rep/analyze_icl_random_2_phrase_control_distance_embed_neighbour.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, elliottyan/understand-icl-from-repetition when it was checked","mcp_get_code":{"code_sha256":"5ee4fd4e2eaab0d2"}},{"code_sha256":"562a31edcf54442e","code_sha256_prefix":"562a31edcf54442e","entry":"single_sentence_eval_icl","repo":"elliottyan/understand-icl-from-repetition","repo_kind":"official","path":"analyze_icl_rep/analyze_icl_random_mask.py","file_url":"https://github.com/elliottyan/understand-icl-from-repetition/blob/HEAD/analyze_icl_rep/analyze_icl_random_mask.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, elliottyan/understand-icl-from-repetition when it was checked","mcp_get_code":{"code_sha256":"562a31edcf54442e"}},{"code_sha256":"1300344adb669654","code_sha256_prefix":"1300344adb669654","entry":"single_sentence_eval_phrase","repo":"elliottyan/understand-icl-from-repetition","repo_kind":"official","path":"analyze_icl_rep/analyze_icl_suffix.py","file_url":"https://github.com/elliottyan/understand-icl-from-repetition/blob/HEAD/analyze_icl_rep/analyze_icl_suffix.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, elliottyan/understand-icl-from-repetition when it was checked","mcp_get_code":{"code_sha256":"1300344adb669654"}},{"code_sha256":"ada2836a4626ca22","code_sha256_prefix":"ada2836a4626ca22","entry":"single_sentence_eval_token_dependency","repo":"elliottyan/understand-icl-from-repetition","repo_kind":"official","path":"analyze_icl_rep/analyze_icl_random_2_tokens.py","file_url":"https://github.com/elliottyan/understand-icl-from-repetition/blob/HEAD/analyze_icl_rep/analyze_icl_random_2_tokens.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, elliottyan/understand-icl-from-repetition when it was checked","mcp_get_code":{"code_sha256":"ada2836a4626ca22"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"564070c8a782098d393c1dc5a32f76e1fa9514f07d0dcfefa4a1dfe5224b76ba","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}