{"id":"W4399837348","doi":"10.48550/arxiv.2406.12356","title":"A Gradient Accumulation Method for Dense Retriever under Memory Constraint","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; National Research Foundation of Korea; National Research Foundation","keywords":"Constraint (computer-aided design); Labrador Retriever; Computer science; Mathematical economics; Psychology; Mathematics; Medicine; Geometry","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005606213,0.00037044,0.0003858328,0.0003669881,0.0001371281,0.0001917747,0.001096926,0.0003576907,0.00001443664],"category_scores_gemma":[0.0001121612,0.0004018345,0.0003867697,0.0006900477,0.0001107341,0.0003635057,0.002005761,0.0006599455,0.00003361688],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004184678,"about_ca_system_score_gemma":0.0002845541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000395182,"about_ca_topic_score_gemma":0.00001113472,"domain_scores_codex":[0.9977005,0.0001331256,0.0002770263,0.001383269,0.0001164126,0.0003897302],"domain_scores_gemma":[0.9978579,0.0003639675,0.0002279479,0.001090923,0.000299201,0.0001600129],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001021294,0.00008965297,0.00003358835,0.0003436032,0.0002296642,0.0003508277,0.0003831686,0.04958214,0.0005122679,0.9242368,0.001525832,0.02261031],"study_design_scores_gemma":[0.0002725424,0.00007412049,0.00005027011,0.0001228881,0.000101082,0.00001234904,0.00005613749,0.3855656,0.005042108,0.6071138,0.00118377,0.0004053239],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006235617,0.0002096614,0.9900083,0.0002624055,0.0006836487,0.0008733053,0.0000386488,0.0008126308,0.0008757807],"genre_scores_gemma":[0.803504,0.0001345536,0.1940468,0.0002995375,0.0001003412,0.000005548233,0.00002214,0.00003485493,0.001852237],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7972684,"threshold_uncertainty_score":0.9998434,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1450618318325144,"score_gpt":0.2905016682860898,"score_spread":0.1454398364535754,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}