{"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":"/task/open-domain-dialog/papers/ran/1","list_of":"/task/open-domain-dialog","task":"Open-Domain Dialog","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":1,"pages_in_order":1,"rows_per_page":100,"rows":[1,11],"of":11,"counts":{"archive_papers_tagged":60,"with_a_code_link":32,"where_syntology_ran_a_sample":11,"not_listed_spam_title":0,"listed":60,"listed_where_code_ran":11,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":8,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":8,"listed_every_run_a_failure_of_syntologys_instrument":3,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/open-domain-dialog/papers/ran/1","prev":null,"next":null,"papers":[{"url":"/paper/re2g-retrieve-rerank-generate-2","slug":"re2g-retrieve-rerank-generate-2","title":"Re2G: Retrieve, Rerank, Generate","date":"2022-07-13","arxiv_id":"2207.06300","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/re2g-retrieve-rerank-generate-2#ran","syntology_url":"https://syntology.ai/paper/2207.06300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.06300"}},"official":{"repos":["ibm/kgi-slot-filling"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-zero-and-few-shot-generalization-in","slug":"improving-zero-and-few-shot-generalization-in","title":"InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning","date":"2022-05-25","arxiv_id":"2205.12673","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/improving-zero-and-few-shot-generalization-in#ran","syntology_url":"https://syntology.ai/paper/2205.12673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.12673"}},"official":{"repos":["prakharguptaz/Instructdial"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/herald-an-annotation-efficient-method-to","slug":"herald-an-annotation-efficient-method-to","title":"HERALD: An Annotation Efficient Method to Detect User Disengagement in Social Conversations","date":"2021-06-01","arxiv_id":"2106.00162","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/herald-an-annotation-efficient-method-to#ran","syntology_url":"https://syntology.ai/paper/2106.00162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.00162"}},"official":{"repos":["Weixin-Liang/HERALD"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dialogue-response-ranking-training-with-large","slug":"dialogue-response-ranking-training-with-large","title":"Dialogue Response Ranking Training with Large-Scale Human Feedback Data","date":"2020-09-15","arxiv_id":"2009.06978","repositories_listed":2,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/dialogue-response-ranking-training-with-large#ran","syntology_url":"https://syntology.ai/paper/2009.06978","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.06978"}},"official":null}},{"url":"/paper/kilt-a-benchmark-for-knowledge-intensive","slug":"kilt-a-benchmark-for-knowledge-intensive","title":"KILT: a Benchmark for Knowledge Intensive Language Tasks","date":"2020-09-04","arxiv_id":"2009.02252","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/kilt-a-benchmark-for-knowledge-intensive#ran","syntology_url":"https://syntology.ai/paper/2009.02252","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.02252"}},"official":{"repos":["facebookresearch/KILT"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/unsupervised-evaluation-of-interactive-dialog","slug":"unsupervised-evaluation-of-interactive-dialog","title":"Unsupervised Evaluation of Interactive Dialog with DialoGPT","date":"2020-06-23","arxiv_id":"2006.12719","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unsupervised-evaluation-of-interactive-dialog#ran","syntology_url":"https://syntology.ai/paper/2006.12719","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.12719"}},"official":{"repos":["shikib/fed"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/beyond-user-self-reported-likert-scale","slug":"beyond-user-self-reported-likert-scale","title":"Beyond User Self-Reported Likert Scale Ratings: A Comparison Model for Automatic Dialog Evaluation","date":"2020-05-21","arxiv_id":"2005.10716","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/beyond-user-self-reported-likert-scale#ran","syntology_url":"https://syntology.ai/paper/2005.10716","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.10716"}},"official":{"repos":["Weixin-Liang/dialog_evaluation_CMADE"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/investigating-evaluation-of-open-domain","slug":"investigating-evaluation-of-open-domain","title":"Investigating Evaluation of Open-Domain Dialogue Systems With Human Generated Multiple References","date":"2019-07-24","arxiv_id":"1907.10568","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/investigating-evaluation-of-open-domain#ran","syntology_url":"https://syntology.ai/paper/1907.10568","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.10568"}},"official":{"repos":["prakharguptaz/multirefeval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/way-off-policy-batch-deep-reinforcement","slug":"way-off-policy-batch-deep-reinforcement","title":"Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog","date":"2019-06-30","arxiv_id":"1907.00456","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/way-off-policy-batch-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1907.00456","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.00456"}},"official":{"repos":["natashamjaques/neural_chat"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluating-coherence-in-dialogue-systems","slug":"evaluating-coherence-in-dialogue-systems","title":"Evaluating Coherence in Dialogue Systems using Entailment","date":"2019-04-06","arxiv_id":"1904.03371","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/evaluating-coherence-in-dialogue-systems#ran","syntology_url":"https://syntology.ai/paper/1904.03371","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.03371"}},"official":{"repos":["nouhadziri/DialogEntailment"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/augmenting-neural-response-generation-with","slug":"augmenting-neural-response-generation-with","title":"Augmenting Neural Response Generation with Context-Aware Topical Attention","date":"2018-11-02","arxiv_id":"1811.01063","repositories_listed":1,"syntology":{"n":14,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/augmenting-neural-response-generation-with#ran","syntology_url":"https://syntology.ai/paper/1811.01063","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.01063"}},"official":{"repos":["nouhadziri/THRED"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":9,"ran_from_kinds":["official"]}}}],"record_sha256":"b138f38865b86acc95d9b7654722e50c7fec259e6f915b3d12d812783d7908ab","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}