{ "schema_version": 2, "generated_from_author_sources": true, "conforms_to": "https://aogavrilov.com/openapi.json#/components/schemas/FullTextCitationContextIndex", "canonical_url": "https://aogavrilov.com/publications/inspectable-control/full-text/citations.json", "source_full_text_url": "https://aogavrilov.com/publications/inspectable-control/full-text/", "source_fragment_sha256": "b0f2ed7a4dfb2815573acf2c19eb5a13b6611a0c2ee44a4ad6cc78c010a77dd7", "section_index_url": "https://aogavrilov.com/publications/inspectable-control/full-text/sections.json", "section_index_sha256": "0ba57ecaea4c1f0004b229c0c0b130bfca10f736b8c0167b9d58de722d6e8ad5", "bibliographic_identity_source_url": "https://aogavrilov.com/publications/inspectable-control/metadata.jsonld", "provenance": { "bibliography_text": "author-provided-camera-ready-tex", "bibliographic_identity": "validated-publication-record-copy-only", "citation_context": "exact-source-block", "identifier_inference": false }, "title": "Inspectable Control for Structure-Preserving Software Regeneration", "language": "en", "granularity": [ "bibliographic-reference", "bibliographic-identity", "citation-occurrence", "source-block" ], "statistics": { "references": 5, "cited_references": 5, "citation_occurrences": 5, "citing_blocks": 2 }, "references": [ { "id": "bib.bib1", "url": "https://aogavrilov.com/publications/inspectable-control/full-text/#bib.bib1", "label": "(1)", "citation_text": "Ali Razavi, Aaron van den Oord, and Oriol Vinyals. 2019. Generating Diverse High-Fidelity Images with VQ-VAE-2. In Advances in Neural Information Processing Systems.", "citation_text_sha256": "ac64261d0c6aba45c88030ba95a4c35571b3bdfb44571727272cbf6d6fb999e8", "occurrence_count": 1, "contexts": [ { "block_id": "S1.p2.text", "block_url": "https://aogavrilov.com/publications/inspectable-control/full-text/#S1.p2.text", "section_id": "S1", "section_url": "https://aogavrilov.com/publications/inspectable-control/full-text/#S1", "section_heading": "1. Problem Setting and Method", "anchor_text": "1", "citation_cluster_text": "(1; 2; 3)", "text": "We therefore study hierarchical discrete latents as an inspectable control layer for software artifacts. Our system combines a hierarchical VQ-VAE with masked discrete regeneration (1; 2; 3). Each 64-token Python function is encoded into 16 top-level codes and 32 lower-level codes. Control is exposed through lock-and-regenerate: selected latent positions are frozen, the rest are regenerated, and the decoder reconstructs the final function. Developers therefore do not edit embeddings directly; they choose which latent positions remain fixed. We intentionally study a narrow setting—short Python functions, argmax decoding, and structural proxies—to isolate controllability before broader evaluations.", "text_sha256": "17d46f791c2fb0d1dafcc5faed65b6f512522ca37958d924baacc20c17e96289" } ], "bibliographic_record": { "id": "https://arxiv.org/abs/1906.00446", "number": 1, "title": "Generating Diverse High-Fidelity Images with VQ-VAE-2", "authors": [ "Ali Razavi", "Aaron van den Oord", "Oriol Vinyals" ], "year": 2019, "venue": "Advances in Neural Information Processing Systems", "url": "https://arxiv.org/abs/1906.00446", "doi": null, "arxiv": "1906.00446", "same_as": [] } }, { "id": "bib.bib2", "url": "https://aogavrilov.com/publications/inspectable-control/full-text/#bib.bib2", "label": "(2)", "citation_text": "Jacob Austin, Daniel D. Johnson, Jonathan Ho, Daniel Tarlow, and Rianne van den Berg. 2021. Structured Denoising Diffusion Models in Discrete State-Spaces. In Advances in Neural Information Processing Systems.", "citation_text_sha256": "aab625464aed60bc46b42f8e4321e4fb688853149cc2f51657ac6fd5418d1031", "occurrence_count": 1, "contexts": [ { "block_id": "S1.p2.text", "block_url": "https://aogavrilov.com/publications/inspectable-control/full-text/#S1.p2.text", "section_id": "S1", "section_url": "https://aogavrilov.com/publications/inspectable-control/full-text/#S1", "section_heading": "1. Problem Setting and Method", "anchor_text": "2", "citation_cluster_text": "(1; 2; 3)", "text": "We therefore study hierarchical discrete latents as an inspectable control layer for software artifacts. Our system combines a hierarchical VQ-VAE with masked discrete regeneration (1; 2; 3). Each 64-token Python function is encoded into 16 top-level codes and 32 lower-level codes. Control is exposed through lock-and-regenerate: selected latent positions are frozen, the rest are regenerated, and the decoder reconstructs the final function. Developers therefore do not edit embeddings directly; they choose which latent positions remain fixed. We intentionally study a narrow setting—short Python functions, argmax decoding, and structural proxies—to isolate controllability before broader evaluations.", "text_sha256": "17d46f791c2fb0d1dafcc5faed65b6f512522ca37958d924baacc20c17e96289" } ], "bibliographic_record": { "id": "https://arxiv.org/abs/2107.03006", "number": 2, "title": "Structured Denoising Diffusion Models in Discrete State-Spaces", "authors": [ "Jacob Austin", "Daniel D. Johnson", "Jonathan Ho", "Daniel Tarlow", "Rianne van den Berg" ], "year": 2021, "venue": "Advances in Neural Information Processing Systems", "url": "https://arxiv.org/abs/2107.03006", "doi": null, "arxiv": "2107.03006", "same_as": [] } }, { "id": "bib.bib3", "url": "https://aogavrilov.com/publications/inspectable-control/full-text/#bib.bib3", "label": "(3)", "citation_text": "Subham Sekhar Sahoo, Marianne Arriola, Aaron Gokaslan, Edgar Mariano Marroquin, Alexander M. Rush, Yair Schiff, Justin T. Chiu, and Volodymyr Kuleshov. 2024. Simple and Effective Masked Diffusion Language Models. In Advances in Neural Information Processing Systems.", "citation_text_sha256": "eb4b3d4e08935b0cd3f702b422e677ac5bf7e906424c659521e68f8b56231696", "occurrence_count": 1, "contexts": [ { "block_id": "S1.p2.text", "block_url": "https://aogavrilov.com/publications/inspectable-control/full-text/#S1.p2.text", "section_id": "S1", "section_url": "https://aogavrilov.com/publications/inspectable-control/full-text/#S1", "section_heading": "1. Problem Setting and Method", "anchor_text": "3", "citation_cluster_text": "(1; 2; 3)", "text": "We therefore study hierarchical discrete latents as an inspectable control layer for software artifacts. Our system combines a hierarchical VQ-VAE with masked discrete regeneration (1; 2; 3). Each 64-token Python function is encoded into 16 top-level codes and 32 lower-level codes. Control is exposed through lock-and-regenerate: selected latent positions are frozen, the rest are regenerated, and the decoder reconstructs the final function. Developers therefore do not edit embeddings directly; they choose which latent positions remain fixed. We intentionally study a narrow setting—short Python functions, argmax decoding, and structural proxies—to isolate controllability before broader evaluations.", "text_sha256": "17d46f791c2fb0d1dafcc5faed65b6f512522ca37958d924baacc20c17e96289" } ], "bibliographic_record": { "id": "https://arxiv.org/abs/2406.07524", "number": 3, "title": "Simple and Effective Masked Diffusion Language Models", "authors": [ "Subham Sekhar Sahoo", "Marianne Arriola", "Yair Schiff", "Aaron Gokaslan", "Edgar Marroquin", "Justin T Chiu", "Alexander Rush", "Volodymyr Kuleshov" ], "year": 2024, "venue": "Advances in Neural Information Processing Systems", "url": "https://arxiv.org/abs/2406.07524", "doi": null, "arxiv": "2406.07524", "same_as": [] } }, { "id": "bib.bib4", "url": "https://aogavrilov.com/publications/inspectable-control/full-text/#bib.bib4", "label": "(4)", "citation_text": "Shraddha Barke, Michael B. James, and Nadia Polikarpova. 2023. Grounded Copilot: How Programmers Interact with Code-Generating Models. Proceedings of the ACM on Human-Computer Interaction 7, CSCW1 (2023), Article 78.", "citation_text_sha256": "01720afb361067bae46517804ad7b72689adec60994ac477528a84f7a7743842", "occurrence_count": 1, "contexts": [ { "block_id": "S1.p1.text", "block_url": "https://aogavrilov.com/publications/inspectable-control/full-text/#S1.p1.text", "section_id": "S1", "section_url": "https://aogavrilov.com/publications/inspectable-control/full-text/#S1", "section_heading": "1. Problem Setting and Method", "anchor_text": "4", "citation_cluster_text": "(4; 5)", "text": "Many software-engineering tasks are better described as controlled modification than as free-form generation: a developer wants to preserve a high-level plan, regenerate only a bounded region, and inspect where change propagates (4; 5). Surface-token interfaces make that awkward because the directly manipulable object is text.", "text_sha256": "562c07d7273821808094fa5fa1ba7b42763b6eaa362edfca64576cac6783735a" } ], "bibliographic_record": { "id": "https://doi.org/10.1145/3586030", "number": 4, "title": "Grounded Copilot: How Programmers Interact with Code-Generating Models", "authors": [ "Shraddha Barke", "Michael B. James", "Nadia Polikarpova" ], "year": 2023, "venue": "Proceedings of the ACM on Programming Languages", "url": "https://doi.org/10.1145/3586030", "doi": "10.1145/3586030", "arxiv": "2206.15000", "same_as": [ "https://arxiv.org/abs/2206.15000" ] } }, { "id": "bib.bib5", "url": "https://aogavrilov.com/publications/inspectable-control/full-text/#bib.bib5", "label": "(5)", "citation_text": "Kechi Zhang, Jia Li, Ge Li, Xianjie Shi, and Zhi Jin. 2023. RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing.", "citation_text_sha256": "5f68bddd2463167e3001827f8c547e56d5fb8efeede9d32b91b660e9e2fccd23", "occurrence_count": 1, "contexts": [ { "block_id": "S1.p1.text", "block_url": "https://aogavrilov.com/publications/inspectable-control/full-text/#S1.p1.text", "section_id": "S1", "section_url": "https://aogavrilov.com/publications/inspectable-control/full-text/#S1", "section_heading": "1. Problem Setting and Method", "anchor_text": "5", "citation_cluster_text": "(4; 5)", "text": "Many software-engineering tasks are better described as controlled modification than as free-form generation: a developer wants to preserve a high-level plan, regenerate only a bounded region, and inspect where change propagates (4; 5). Surface-token interfaces make that awkward because the directly manipulable object is text.", "text_sha256": "562c07d7273821808094fa5fa1ba7b42763b6eaa362edfca64576cac6783735a" } ], "bibliographic_record": { "id": "https://doi.org/10.18653/v1/2023.emnlp-main.151", "number": 5, "title": "RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation", "authors": [ "Fengji Zhang", "Bei Chen", "Yue Zhang", "Jacky Keung", "Jin Liu", "Daoguang Zan", "Yi Mao", "Jian-Guang Lou", "Weizhu Chen" ], "year": 2023, "venue": "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing", "url": "https://doi.org/10.18653/v1/2023.emnlp-main.151", "doi": "10.18653/v1/2023.emnlp-main.151", "arxiv": "2303.12570", "same_as": [ "https://arxiv.org/abs/2303.12570" ] } } ] }