{ "source_file": "0930", "source_platform": "研究机构", "author": "Meta AI Research", "title_listed": "Segment Anything (SAM)", "keywords": "SAM,图像分割,CV", "domain": "图像处理", "content_type": "深度技术解析", "is_paid_flag": "否", "url": "https://ai.meta.com/research/publications/segment-anything/", "publish_date": "2023-04", "corpus_stage": "预训练/SFT", "notes": "SAM通用图像分割模型", "id": "f71cc9b9a899", "collected_at": "2026-10-02T15:46:20", "title": "Segment Anything | Research - AI at Meta", "body_markdown": "Products\nAI Research\nResources\nAbout\nAI Developers\nTry Muse\nCOMPUTER VISION\nSegment Anything\nApril 05, 2023\nAbstract\nWe introduce the Segment Anything (SA) project: a new task, model, and dataset for image segmentation. Using our efficient model in a data collection loop, we built the largest segmentation dataset to date (by far), with over 1 billion masks on 11M licensed and privacy respecting images. The model is designed and trained to be promptable, so it can transfer zero-shot to new image distributions and tasks. We evaluate its capabilities on numerous tasks and find that its zero-shot performance is impressive -- often competitive with or even superior to prior fully supervised results. We are releasing the Segment Anything Model (SAM) and corresponding dataset (SA-1B) of 1B masks and 11M images at \\href{https://segment-anything.com}{https://segment-anything.com} to foster research into foundation models for computer vision.\nDownload the Paper\nAUTHORS\nWritten by\nAlexander Kirillov\nAlex Berg\nChloe Rolland\nEric Mintun\nHanzi Mao\nLaura Gustafson\nNikhila Ravi\nPiotr Dollar\nRoss Girshick\nSpencer Whitehead\nWan-Yen Lo\nTete Xiao\nPublisher\nArXiv\nResearch Topics\nComputer Vision\nRelated Publications\nAugust 04, 2026\nCOMPUTER VISION\nWaiT for the Signal: Simple Frequency-Aware Flow-Matching\nKrunoslav Lehman Pavasovic\n,\nTheophane Vallaeys\n,\nStéphane Mallat\n,\nGiulio Biroli\n,\nLuke Zettlemoyer\n,\nBrian Karrer\n,\nJakob Verbeek\nAugust 04, 2026\nRead the Paper\nJuly 13, 2026\nAR/VR\nRESEARCH\nS-EMBER: A Large-Scale Benchmark for Streaming Egocentric Memory Retrieval\nXiaodong Wang\n,\nXuanyi Zhao\n,\nPedro Rodriguez\n,\nDevendra Singh Sachan\n,\nBarlas Oguz\n,\nSeungwhan Moon\n,\nShang-Wen Li\n,\nGargi Ghosh\n,\nXin Dong\n,\nWen-Tau Yih\nJuly 13, 2026\nRead the Paper\nJuly 03, 2026\nHUMAN & MACHINE INTELLIGENCE\nROBOTICS\nInterpreting Physics in Video World Models\nSonia Joseph\n,\nQuentin Garrido\n,\nRandall Balestriero\n,\nMatthew Kowal\n,\nThomas Fel\n,\nShahab Bakhtiari\n,\nBlake Richards\n,\nMike Rabbat\nJuly 03, 2026\nRead the Paper\nMay 26, 2026\nHUMAN & MACHINE INTELLIGENCE\nTHEORY\nMisalignment Between Backpropagation and the Hierarchy of Brain Responses to Images\nJosephine Raugel\n,\nMax Seitzer\n,\nMarc Szafraniec\n,\nHuy V. Vo\n,\nJérémy Rapin\n,\nPatrick Labatut\n,\nPiotr Bojanowski\n,\nValentin Wyart\n,\nJean Remi King\nMay 26, 2026\nRead the Paper\nSee All Papers\nHelp Us Pioneer The Future of AI\nWe share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.\nJoin our Team\nMeta AI\nAssistant\nMedia Generation\nVibes\nMuse\nAgent\nAI agents explained\nWhat is agentic AI\nAgentic AI examples\nAI Research\nOverview\nProjects\nResources & tools\nPublications\nGitHub\nResources\nBlog\nLearning Hub\nDemos\nAbout\nOverview\nOpen Source\nCareers\nMeta AI\nMeta AI\nAssistant\nMedia Generation\nVibes\nMuse\nMuse\nAgent\nAI agents explained\nWhat is agentic AI\nAgentic AI examples\nAI Research\nAI Research\nOverview\nProjects\nResources & tools\nPublications\nGitHub\nResources\nBlog\nLearning Hub\nDemos\nAbout\nAbout\nOverview\nOpen Source\nCareers\nPrivacy Policy\nTerms\nCookies\nMeta © 2026", "metadata": { "title": "Segment Anything | Research - AI at Meta", "description": "We introduce the Segment Anything (SA) project: a new task, model, and dataset for image segmentation. Using our efficient model in a data collection...", "keywords": null, "author": null }, "paywall": { "listed_paid": false, "detected": false, "marker": "", "public_only": false, "policy": "付费/会员内容只保留页面公开可见部分，不绕过付费墙" }, "crawl": { "success": true, "status_code": 200, "error": "" }, "code_blocks": [], "images": [ { "status": "ok", "url": "https://scontent-dfw6-2.xx.fbcdn.net/v/t39.8562-6/252294889_575082167077436_6034106545912333281_n.svg/meta-logo-primary_standardsize.svg?_nc_cat=108&ccb=1-7&_nc_sid=e280be&_nc_ohc=hAHazKbORSwQ7kNvwFs3s3h&_nc_oc=AdpT8oey1lBbgzpbV7ZyVqYXvdIcHIx66czv3z4_y4D5VbmT8-LcxGwGhf3nCEqCFAg&_nc_zt=14&_nc_ht=scontent-dfw6-2.xx&_nc_gid=m7PPfUjC4xRcB8XaBotPGg&_nc_ss=7820f&oh=00_AQNrux8znbGlvHULjy5CcgWrzAwsaXsa6gcKpQFUb-fqKQ&oe=6AD530B9", "bytes": 13990, "reused": false, "local_path": "attachments/f71cc9b9a899/images/body-f860a5c4d95b0db30839.svg", "src": "https://scontent-dfw6-2.xx.fbcdn.net/v/t39.8562-6/252294889_575082167077436_6034106545912333281_n.svg/meta-logo-primary_standardsize.svg?_nc_cat=108&ccb=1-7&_nc_sid=e280be&_nc_ohc=hAHazKbORSwQ7kNvwFs3s3h&_nc_oc=AdpT8oey1lBbgzpbV7ZyVqYXvdIcHIx66czv3z4_y4D5VbmT8-LcxGwGhf3nCEqCFAg&_nc_zt=14&_nc_ht=scontent-dfw6-2.xx&_nc_gid=m7PPfUjC4xRcB8XaBotPGg&_nc_ss=7820f&oh=00_AQNrux8znbGlvHULjy5CcgWrzAwsaXsa6gcKpQFUb-fqKQ&oe=6AD530B9", "alt": "Meta", "downloaded": true }, { "status": "ok", "url": "https://scontent-dfw5-2.xx.fbcdn.net/v/t39.2365-6/90971213_248000486247635_8189447952712859648_n.jpg?_nc_cat=104&ccb=1-7&_nc_sid=e280be&_nc_ohc=54NmkRNvFEoQ7kNvwGOSvsh&_nc_oc=AdqKW5TQ_AvRltHCoTyvTJXJUOA-Jpuk8fodrH2dv88kvQItDNEEf0IcyCEOG86Qezw&_nc_zt=14&_nc_ht=scontent-dfw5-2.xx&_nc_gid=m7PPfUjC4xRcB8XaBotPGg&_nc_ss=7820f&oh=00_AQPLZ2S71rOO_0wb-HK-v-U-RAqN7rQIw5B_jnWHbg-4MA&oe=6AE99497", "bytes": 351299, "reused": false, "local_path": "attachments/f71cc9b9a899/images/body-e5361584cd666f464b32.jpg", "src": "https://scontent-dfw5-2.xx.fbcdn.net/v/t39.2365-6/90971213_248000486247635_8189447952712859648_n.jpg?_nc_cat=104&ccb=1-7&_nc_sid=e280be&_nc_ohc=54NmkRNvFEoQ7kNvwGOSvsh&_nc_oc=AdqKW5TQ_AvRltHCoTyvTJXJUOA-Jpuk8fodrH2dv88kvQItDNEEf0IcyCEOG86Qezw&_nc_zt=14&_nc_ht=scontent-dfw5-2.xx&_nc_gid=m7PPfUjC4xRcB8XaBotPGg&_nc_ss=7820f&oh=00_AQPLZ2S71rOO_0wb-HK-v-U-RAqN7rQIw5B_jnWHbg-4MA&oe=6AE99497", "alt": "", "downloaded": true }, { "status": "ok", "url": "https://scontent-dfw6-1.xx.fbcdn.net/v/t39.2365-6/87524316_2677189655726266_6338721200264445952_n.svg?_nc_cat=103&ccb=1-7&_nc_sid=e280be&_nc_ohc=fVw4LJojBokQ7kNvwGoeBzo&_nc_oc=AdrkP6I-04u6p4Jook2sPg73GEI1IfiIRn2GycI6WgIkObCoxv9tkmBFc09yToCgBiA&_nc_zt=14&_nc_ht=scontent-dfw6-1.xx&_nc_gid=m7PPfUjC4xRcB8XaBotPGg&_nc_ss=7820f&oh=00_AQMrcgbr8HJWjKsPkOgq6sx83IlUoBXZBJpy5wxFbwz87Q&oe=6AE99A78", "bytes": 768, "reused": false, "local_path": "attachments/f71cc9b9a899/images/body-bd580075c6bbcc551d21.svg", "src": "https://scontent-dfw6-1.xx.fbcdn.net/v/t39.2365-6/87524316_2677189655726266_6338721200264445952_n.svg?_nc_cat=103&ccb=1-7&_nc_sid=e280be&_nc_ohc=fVw4LJojBokQ7kNvwGoeBzo&_nc_oc=AdrkP6I-04u6p4Jook2sPg73GEI1IfiIRn2GycI6WgIkObCoxv9tkmBFc09yToCgBiA&_nc_zt=14&_nc_ht=scontent-dfw6-1.xx&_nc_gid=m7PPfUjC4xRcB8XaBotPGg&_nc_ss=7820f&oh=00_AQMrcgbr8HJWjKsPkOgq6sx83IlUoBXZBJpy5wxFbwz87Q&oe=6AE99A78", "alt": "", "downloaded": true }, { "status": "ok", "url": "https://scontent-dfw5-2.xx.fbcdn.net/v/t39.8562-6/335682312_964107378293184_3093631164486164913_n.svg?_nc_cat=100&ccb=1-7&_nc_sid=e280be&_nc_ohc=fYUd8cfKa3cQ7kNvwHzxyUo&_nc_oc=AdqO5CXvI_Ry9-R7gLxXAricVHfV9jgZI4bhWqxGsfabwKdJ_6gU1IS1JNw7Yk5A8rI&_nc_zt=14&_nc_ht=scontent-dfw5-2.xx&_nc_gid=m7PPfUjC4xRcB8XaBotPGg&_nc_ss=7820f&oh=00_AQOH8rthUbd281H2jgfaFZEq0BPevaijuQ2pL-jp-8U2hw&oe=6AD520E7", "bytes": 536, "reused": false, "local_path": "attachments/f71cc9b9a899/images/body-c6a5c226c8a4a96214ea.svg", "src": "https://scontent-dfw5-2.xx.fbcdn.net/v/t39.8562-6/335682312_964107378293184_3093631164486164913_n.svg?_nc_cat=100&ccb=1-7&_nc_sid=e280be&_nc_ohc=fYUd8cfKa3cQ7kNvwHzxyUo&_nc_oc=AdqO5CXvI_Ry9-R7gLxXAricVHfV9jgZI4bhWqxGsfabwKdJ_6gU1IS1JNw7Yk5A8rI&_nc_zt=14&_nc_ht=scontent-dfw5-2.xx&_nc_gid=m7PPfUjC4xRcB8XaBotPGg&_nc_ss=7820f&oh=00_AQOH8rthUbd281H2jgfaFZEq0BPevaijuQ2pL-jp-8U2hw&oe=6AD520E7", "alt": "", "downloaded": true }, { "status": "ok", "url": "https://scontent-dfw6-1.xx.fbcdn.net/v/t39.8562-6/336009607_1870102080040414_6753977241281150924_n.svg?_nc_cat=103&ccb=1-7&_nc_sid=e280be&_nc_ohc=EOxnus0Vys8Q7kNvwFGrms5&_nc_oc=AdodxvUHQnETZW32TOMmP5S_noQxTy-8rzUluvcvOmKo3rO2-NuuXTQLrgMGVVO-y84&_nc_zt=14&_nc_ht=scontent-dfw6-1.xx&_nc_gid=m7PPfUjC4xRcB8XaBotPGg&_nc_ss=7820f&oh=00_AQNvij0FTI-gxveJfak0lH0s0AEmiKiy53K5hCAvHo4P2w&oe=6AD51922", "bytes": 1126, "reused": false, "local_path": "attachments/f71cc9b9a899/images/body-03dc1c50fc9929676c8e.svg", "src": "https://scontent-dfw6-1.xx.fbcdn.net/v/t39.8562-6/336009607_1870102080040414_6753977241281150924_n.svg?_nc_cat=103&ccb=1-7&_nc_sid=e280be&_nc_ohc=EOxnus0Vys8Q7kNvwFGrms5&_nc_oc=AdodxvUHQnETZW32TOMmP5S_noQxTy-8rzUluvcvOmKo3rO2-NuuXTQLrgMGVVO-y84&_nc_zt=14&_nc_ht=scontent-dfw6-1.xx&_nc_gid=m7PPfUjC4xRcB8XaBotPGg&_nc_ss=7820f&oh=00_AQNvij0FTI-gxveJfak0lH0s0AEmiKiy53K5hCAvHo4P2w&oe=6AD51922", "alt": "", "downloaded": true }, { "status": "ok", "url": "https://scontent-dfw6-2.xx.fbcdn.net/v/t39.8562-6/336289415_1541032296405649_2165099305308791297_n.svg?_nc_cat=109&ccb=1-7&_nc_sid=e280be&_nc_ohc=szNSkRClPB8Q7kNvwG_QuzC&_nc_oc=AdrwcmNZ6VBPiUuOKpS80tKMlMpN-566glDgJUkbOeVxfK_YcxcnHGmQXAT2VLrdJy4&_nc_zt=14&_nc_ht=scontent-dfw6-2.xx&_nc_gid=m7PPfUjC4xRcB8XaBotPGg&_nc_ss=7820f&oh=00_AQNiOQSVa8OCJxgfczNecXhGxF5dk4ODhqiAapQL37vxRA&oe=6AD544FB", "bytes": 806, "reused": false, "local_path": "attachments/f71cc9b9a899/images/body-8a1278754b1fe0171412.svg", "src": "https://scontent-dfw6-2.xx.fbcdn.net/v/t39.8562-6/336289415_1541032296405649_2165099305308791297_n.svg?_nc_cat=109&ccb=1-7&_nc_sid=e280be&_nc_ohc=szNSkRClPB8Q7kNvwG_QuzC&_nc_oc=AdrwcmNZ6VBPiUuOKpS80tKMlMpN-566glDgJUkbOeVxfK_YcxcnHGmQXAT2VLrdJy4&_nc_zt=14&_nc_ht=scontent-dfw6-2.xx&_nc_gid=m7PPfUjC4xRcB8XaBotPGg&_nc_ss=7820f&oh=00_AQNiOQSVa8OCJxgfczNecXhGxF5dk4ODhqiAapQL37vxRA&oe=6AD544FB", "alt": "", "downloaded": true }, { "status": "ok", "url": "https://scontent-dfw6-2.xx.fbcdn.net/v/t39.8562-6/335648731_142576991793348_7786819189843639239_n.svg?_nc_cat=108&ccb=1-7&_nc_sid=e280be&_nc_ohc=kR8jmDz5Tu8Q7kNvwFsKqaM&_nc_oc=AdqrOm2ElI15Ej13sM8SirbTVZiUpR5DMxc4KAJkrz9qH4EpZnouLCCNEJvPdLyTI_o&_nc_zt=14&_nc_ht=scontent-dfw6-2.xx&_nc_gid=m7PPfUjC4xRcB8XaBotPGg&_nc_ss=7820f&oh=00_AQN5UWKJMFSJ_gSSOvPRDifSHwXg-BhOSnI68mMapi1o1Q&oe=6AD5262E", "bytes": 771, "reused": false, "local_path": "attachments/f71cc9b9a899/images/body-814d23de80196ccadb47.svg", "src": "https://scontent-dfw6-2.xx.fbcdn.net/v/t39.8562-6/335648731_142576991793348_7786819189843639239_n.svg?_nc_cat=108&ccb=1-7&_nc_sid=e280be&_nc_ohc=kR8jmDz5Tu8Q7kNvwFsKqaM&_nc_oc=AdqrOm2ElI15Ej13sM8SirbTVZiUpR5DMxc4KAJkrz9qH4EpZnouLCCNEJvPdLyTI_o&_nc_zt=14&_nc_ht=scontent-dfw6-2.xx&_nc_gid=m7PPfUjC4xRcB8XaBotPGg&_nc_ss=7820f&oh=00_AQN5UWKJMFSJ_gSSOvPRDifSHwXg-BhOSnI68mMapi1o1Q&oe=6AD5262E", "alt": "", "downloaded": true } ], "audio": [], "videos": [ { "url": "https://www.youtube.com/@aiatmeta", "src": "https://www.youtube.com/@aiatmeta", "status": "reference_only", "kind": "channel_reference" } ], "links": [ { "href": "https://developer.meta.com/ai/?utm_source=ai_meta_site&utm_medium=web&utm_campaign=nav_AI-developers_07242026&utm_content=nav_AI-developers", "label": "AI Developers", "type": "a" }, { "href": "https://applink.muse.ai/?pt=10684&pid=ai_meta_site&utm_source=ai_meta_site&utm_medium=web&utm_campaign=nav_try-muse_09082026&utm_content=nav_try-muse_09082026&ct=nav_try-muse_09082026&referrer=utm_source%3Dai_meta_site%26utm_medium%3Dweb%26utm_campaign%3Dnav_try-muse_09082026%26utm_content%3Dnav_try-muse_09082026", "label": "Try Muse", "type": "a" }, { "href": "https://ai.meta.com/", "label": "", "type": "a" }, { "href": "https://scontent-dfw5-2.xx.fbcdn.net/v/t39.2365-6/10000000_900554171201033_1602411987825904100_n.pdf?_nc_cat=100&ccb=1-7&_nc_sid=3c67a6&_nc_ohc=oWkBo-uCU5YQ7kNvwGgdUpG&_nc_oc=AdpgQBzHXPmHDliQ6wJZHlcKV9O6yQHTaJNDzYjdV9e1t7SqEZJuKepDLGIL8UcyYSg&_nc_zt=14&_nc_ht=scontent-dfw5-2.xx&_nc_gid=m7PPfUjC4xRcB8XaBotPGg&_nc_ss=7820f&oh=00_AQM1B-LoITK8t3N1BF_wpSaQE0KK13Y-aDTwexhF9vMQlA&oe=6AD54AE7", "label": "Download the Paper", "type": "a" }, { "href": "https://ai.meta.com/people/376342865239921/nikhila-ravi/", "label": "Nikhila Ravi", "type": "a" }, { "href": "https://ai.meta.com/people/1101307851116193/piotr-dollar/", "label": "Piotr Dollar", "type": "a" }, { "href": "https://ai.meta.com/research/computer-vision/", "label": "Computer Vision", "type": "a" }, { "href": "https://ai.meta.com/people/1450721039196474/luke-zettlemoyer/", "label": "Luke Zettlemoyer", "type": "a" }, { "href": "https://ai.meta.com/research/publications/wait-for-the-signal-simple-frequency-aware-flow-matching/", "label": "Read the Paper", "type": "a" }, { "href": "https://ai.meta.com/people/1456066821689392/pedro-rodriguez/", "label": "Pedro Rodriguez", "type": "a" }, { "href": "https://ai.meta.com/people/1474004249915770/barlas-oguz/", "label": "Barlas Oguz", "type": "a" }, { "href": "https://ai.meta.com/people/1630642931666147/shang-wen-daniel-li/", "label": "Shang-Wen Li", "type": "a" }, { "href": "https://ai.meta.com/people/706397891415751/scott-wen-tau-yih/", "label": "Wen-Tau Yih", "type": "a" }, { "href": "https://ai.meta.com/research/publications/s-ember-a-large-scale-benchmark-for-streaming-egocentric-memory-retrieval/", "label": "Read the Paper", "type": "a" }, { "href": "https://ai.meta.com/research/publications/interpreting-physics-in-video-world-models/", "label": "Read the Paper", "type": "a" }, { "href": "https://ai.meta.com/research/publications/misalignment-between-backpropagation-and-the-hierarchy-of-brain-responses-to-images/", "label": "Read the Paper", "type": "a" }, { "href": "https://ai.meta.com/global_search/?content_types%5B0%5D=publication&page=1", "label": "See All Papers", "type": "a" }, { "href": "https://ai.meta.com/join-us/", "label": "Join our Team", "type": "a" }, { "href": "https://ai.meta.com/meta-ai/assistant/", "label": "Meta AI", "type": "a" }, { "href": "https://ai.meta.com/meta-ai/media-generation/", "label": "Media Generation", "type": "a" }, { "href": "https://ai.meta.com/meta-ai/vibes/", "label": "Vibes", "type": "a" }, { "href": "https://ai.meta.com/muse/", "label": "Muse", "type": "a" }, { "href": "https://ai.meta.com/learn/agentic-ai/what-are-ai-agents/", "label": "AI agents explained", "type": "a" }, { "href": "https://ai.meta.com/learn/agentic-ai/what-is-agentic-ai/", "label": "What is agentic AI", "type": "a" }, { "href": "https://ai.meta.com/learn/agentic-ai/agentic-ai-examples/", "label": "Agentic AI examples", "type": "a" }, { "href": "https://ai.meta.com/research", "label": "AI Research", "type": "a" }, { "href": "https://ai.meta.com/research/", "label": "Overview", "type": "a" }, { "href": "https://ai.meta.com/resources/", "label": "Resources & tools", "type": "a" }, { "href": "https://ai.meta.com/results/?content_types%5B0%5D=publication", "label": "Publications", "type": "a" }, { "href": "https://github.com/facebookresearch/", "label": "GitHub", "type": "a" }, { "href": "https://ai.meta.com/blog/", "label": "Blog", "type": "a" }, { "href": "https://ai.meta.com/learn/", "label": "Learning Hub", "type": "a" }, { "href": "https://aidemos.meta.com/", "label": "Demos", "type": "a" }, { "href": "https://ai.meta.com/about", "label": "About", "type": "a" }, { "href": "https://ai.meta.com/about/", "label": "Overview", "type": "a" }, { "href": "https://ai.meta.com/opensourceai/", "label": "Open Source", "type": "a" }, { "href": "https://www.metacareers.com/jobs/?is_leadership=0&sub_teams[0]=Artificial%20Intelligence&is_in_page=0", "label": "Careers", "type": "a" }, { "href": "https://www.facebook.com/aiatmeta/", "label": "", "type": "a" }, { "href": "https://twitter.com/aiatmeta/", "label": "", "type": "a" }, { "href": "https://www.linkedin.com/showcase/aiatmeta", "label": "", "type": "a" }, { "href": "https://www.youtube.com/@aiatmeta", "label": "", "type": "a" }, { "href": "https://www.facebook.com/about/privacy/", "label": "Privacy Policy", "type": "a" }, { "href": "https://www.facebook.com/policies/", "label": "Terms", "type": "a" }, { "href": "https://www.facebook.com/policies/cookies/", "label": "Cookies", "type": "a" } ], "repair_version": 2, "repaired_at": "2026-10-14T10:53:39Z", "source_url": "https://ai.meta.com/research/publications/segment-anything/", "papers": [ { "status": "ok", "url": "https://scontent-dfw5-2.xx.fbcdn.net/v/t39.2365-6/10000000_900554171201033_1602411987825904100_n.pdf?_nc_cat=100&ccb=1-7&_nc_sid=3c67a6&_nc_ohc=oWkBo-uCU5YQ7kNvwGgdUpG&_nc_oc=AdpgQBzHXPmHDliQ6wJZHlcKV9O6yQHTaJNDzYjdV9e1t7SqEZJuKepDLGIL8UcyYSg&_nc_zt=14&_nc_ht=scontent-dfw5-2.xx&_nc_gid=m7PPfUjC4xRcB8XaBotPGg&_nc_ss=7820f&oh=00_AQM1B-LoITK8t3N1BF_wpSaQE0KK13Y-aDTwexhF9vMQlA&oe=6AD54AE7", "bytes": 15382912, "reused": false, "local_path": "papers/repair/84d44e8ed5380163cd16.pdf" } ], "actual_video_files": [], "body_chars": 3093, "expected_body_images": 7, "discovery_status": "ok", "delivery_status": "ok", "missing_reason": "", "raw_html": "attachments/f71cc9b9a899/pages/source.html", "local_html": "attachments/f71cc9b9a899/pages/article.html", "body_base_path": "attachments/f71cc9b9a899/pages/", "body_markdown_path": "attachments/f71cc9b9a899/pages/article.md" }