{"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/self-explore-to-avoid-the-pit-improving-the","title":"Self-Explore: Enhancing Mathematical Reasoning in Language Models with Fine-grained Rewards","arxiv_id":"2404.10346","date":"2024-04-16","proceeding":null,"authors":["Hyeonbin Hwang","Doyoung Kim","Seungone Kim","Seonghyeon Ye","Minjoon Seo"],"abstract":"Training on large amounts of rationales (i.e., CoT Fine-tuning) is effective at improving the reasoning capabilities of large language models (LLMs). However, acquiring human-authored rationales or augmenting rationales from proprietary models is costly and not scalable. In this paper, we study the problem of whether LLMs could self-improve their reasoning capabilities. To this end, we propose Self-Explore, where the LLM is tasked to explore the first wrong step (i.e., the first pit) within the rationale and use such signals as fine-grained rewards for further improvement. On the GSM8K and MATH test set, Self-Explore achieves 11.57% and 2.89% improvement on average across three LLMs compared to supervised fine-tuning (SFT). Our code is available at https://github.com/hbin0701/Self-Explore.","url_abs":"https://arxiv.org/abs/2404.10346v4","url_pdf":"https://arxiv.org/pdf/2404.10346v4.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":"self-explore-to-avoid-the-pit-improving-the","repo_url":"https://github.com/hbin0701/Self-Explore","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"gsm8k","task_name":"GSM8K"},{"task_slug":"math","task_name":"Math"},{"task_slug":"mathematical-reasoning","task_name":"Mathematical Reasoning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2404.10346","atlas_url":"https://app.syntology.ai/?focus=2404.10346","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.10346"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2404.10346"},"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":"2404.10346"},"call":"get_harvested_code_for_paper(arxiv_id=\"2404.10346\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2404.10346"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2404.10346\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2404.10346"},"call":"get_concepts_for_paper(arxiv_id=\"2404.10346\")"}],"by_repo":[{"repo":"hbin0701/Self-Explore","kind":"official","samples":8,"ran":7,"instrument":4,"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/2404.10346.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/2404.10346.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/hbin0701/Self-Explore","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":5,"ran_violates":2,"ran":1,"unverified":1},"n_samples":9,"n_ran":8,"n_constructed":0,"n_ran_checked":3,"n_instrument":5,"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":8,"ran":7,"n_ran_checked":3,"n_instrument":4,"repositories":1},"unlocated":{"samples":1,"ran":1,"n_ran_checked":0,"n_instrument":1,"repositories":0,"is":"identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded"}},"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":9,"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":7,"n_ran_without_level_date":1,"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":"66b3b5450182da3a","code_sha256_prefix":"66b3b5450182da3a","entry":"batch_data","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature":"data_list:list/1/Tensor, batch_size:int/0/int","fixture_out_type":"list","retrieve_with":{"tool":"get_code","code_sha256":"66b3b5450182da3a"},"code_page":"/code/batch-data","census":null,"licence":null,"inline_ok":false,"inline_ok_link":false,"withheld_clause":"this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it","mcp_get_code":{"code_sha256":"66b3b5450182da3a"}},{"code_sha256":"771d0d0c6a85a612","code_sha256_prefix":"771d0d0c6a85a612","entry":"check_equation","repo":"hbin0701/Self-Explore","repo_kind":"official","path":"gen/get_rft_data.py","file_url":"https://github.com/hbin0701/Self-Explore/blob/HEAD/gen/get_rft_data.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"eq:str/0/str","fixture_out_type":"bool","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, hbin0701/Self-Explore when it was checked","mcp_get_code":{"code_sha256":"771d0d0c6a85a612"}},{"code_sha256":"50408bcb3e87455b","code_sha256_prefix":"50408bcb3e87455b","entry":"extract_answer","repo":"hbin0701/Self-Explore","repo_kind":"official","path":"gen/utils_others.py","file_url":"https://github.com/hbin0701/Self-Explore/blob/HEAD/gen/utils_others.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"completion: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":"50408bcb3e87455b"},"code_page":"/code/extract-answer","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, hbin0701/Self-Explore when it was checked","mcp_get_code":{"code_sha256":"50408bcb3e87455b"}},{"code_sha256":"fc107f0a7cb2bb77","code_sha256_prefix":"fc107f0a7cb2bb77","entry":"extract_answers","repo":"hbin0701/Self-Explore","repo_kind":"official","path":"gen/utils_others.py","file_url":"https://github.com/hbin0701/Self-Explore/blob/HEAD/gen/utils_others.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"completions:list/1/str","fixture_out_type":"list","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/extract-answers","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, hbin0701/Self-Explore when it was checked","mcp_get_code":{"code_sha256":"fc107f0a7cb2bb77"}},{"code_sha256":"48f4dfa28740b7de","code_sha256_prefix":"48f4dfa28740b7de","entry":"get_dataset","repo":"hbin0701/Self-Explore","repo_kind":"official","path":"dpo/prepare_dataset.py","file_url":"https://github.com/hbin0701/Self-Explore/blob/HEAD/dpo/prepare_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"path_train:str/0/str, path_test:str/0/str","fixture_out_type":"DatasetDict","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/get-dataset","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, hbin0701/Self-Explore when it was checked","mcp_get_code":{"code_sha256":"48f4dfa28740b7de"}},{"code_sha256":"f3a68206b24244ce","code_sha256_prefix":"f3a68206b24244ce","entry":"is_eq_correct","repo":"hbin0701/Self-Explore","repo_kind":"official","path":"gen/get_rft_data.py","file_url":"https://github.com/hbin0701/Self-Explore/blob/HEAD/gen/get_rft_data.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"equations:list/1/str","fixture_out_type":"bool","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, hbin0701/Self-Explore when it was checked","mcp_get_code":{"code_sha256":"f3a68206b24244ce"}},{"code_sha256":"c4783f2528e590ab","code_sha256_prefix":"c4783f2528e590ab","entry":"read_jsonl","repo":"hbin0701/Self-Explore","repo_kind":"official","path":"gen/get_rft_data.py","file_url":"https://github.com/hbin0701/Self-Explore/blob/HEAD/gen/get_rft_data.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"fname:str/0/str","fixture_out_type":"list","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/read-jsonl","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, hbin0701/Self-Explore when it was checked","mcp_get_code":{"code_sha256":"c4783f2528e590ab"}},{"code_sha256":"f5c2fbf1177f0d1f","code_sha256_prefix":"f5c2fbf1177f0d1f","entry":"standardize_value_str","repo":"hbin0701/Self-Explore","repo_kind":"official","path":"gen/utils_others.py","file_url":"https://github.com/hbin0701/Self-Explore/blob/HEAD/gen/utils_others.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"x: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":"f5c2fbf1177f0d1f"},"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, hbin0701/Self-Explore when it was checked","mcp_get_code":{"code_sha256":"f5c2fbf1177f0d1f"}},{"code_sha256":"0ad5c5d201bc2f1e","code_sha256_prefix":"0ad5c5d201bc2f1e","entry":"get_quantization_config","repo":"hbin0701/Self-Explore","repo_kind":"official","path":"dpo/alignment/model_utils.py","file_url":"https://github.com/hbin0701/Self-Explore/blob/HEAD/dpo/alignment/model_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/get-quantization-config","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, hbin0701/Self-Explore when it was checked","mcp_get_code":{"code_sha256":"0ad5c5d201bc2f1e"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"2732789897d920209ef0f7e6dcafc8f0ccca9a62bf5575798e71db8cb2811073","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}