🐦 Twitter Post Details

Viewing enriched Twitter post

@dair_ai

Can coding-agents replicate scientific ML papers? We know this is possible because we can already do this @dair_ai. Still a great read. So they try to replicate an ML paper from its materials alone. They use a coding-agent skill that turns each selected paper claim into a target with recorded evidence. The agent reconstructs the method, runs experiments, links outputs to provenance, compares against the paper's claims, and passes validation checks before completion. Completion depends on workspace evidence, not on the agent's final message. Across twelve runs over four scientific ML papers, all twelve workspaces pass the completion gate and all 158 recorded targets are matched with report coverage. Yet repeated runs still differ in how papers are split into targets, in numerical fidelity, in elapsed time, and in the rules used to accept evidence. Basically the completion becomes reproducible even when the path is not. Paper: https://t.co/IkhknqCUiv Learn to build effective AI agents in our academy: https://t.co/LRnpZN7L4c

Media 1
View on Twitter

📊 Media Metadata

{
  "media": [
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2073065231790809214/media_0.jpg",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2073065231790809214/media_0.jpg",
      "type": "photo",
      "filename": "media_0.jpg"
    }
  ],
  "processed_at": "2026-07-03T16:01:33.785259",
  "pipeline_version": "2.0"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "2073065231790809214",
  "url": "https://x.com/dair_ai/status/2073065231790809214",
  "twitterUrl": "https://twitter.com/dair_ai/status/2073065231790809214",
  "text": "Can coding-agents replicate scientific ML papers?\n\nWe know this is possible because we can already do this @dair_ai.\n\nStill a great read.\n\nSo they try to replicate an ML paper from its materials alone.\n\nThey use a coding-agent skill that turns each selected paper claim into a target with recorded evidence. The agent reconstructs the method, runs experiments, links outputs to provenance, compares against the paper's claims, and passes validation checks before completion.\n\nCompletion depends on workspace evidence, not on the agent's final message.\n\nAcross twelve runs over four scientific ML papers, all twelve workspaces pass the completion gate and all 158 recorded targets are matched with report coverage. Yet repeated runs still differ in how papers are split into targets, in numerical fidelity, in elapsed time, and in the rules used to accept evidence.\n\nBasically the completion becomes reproducible even when the path is not.\n\nPaper: https://t.co/IkhknqCUiv\n\nLearn to build effective AI agents in our academy: https://t.co/LRnpZN7L4c",
  "source": "Twitter for iPhone",
  "retweetCount": 3,
  "replyCount": 1,
  "likeCount": 15,
  "quoteCount": 2,
  "viewCount": 2858,
  "createdAt": "Fri Jul 03 15:24:01 +0000 2026",
  "lang": "en",
  "bookmarkCount": 12,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2073065231790809214",
  "displayTextRange": [
    0,
    276
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "dair_ai",
    "url": "https://x.com/dair_ai",
    "twitterUrl": "https://twitter.com/dair_ai",
    "id": "889050642903293953",
    "name": "DAIR.AI",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/1643277398522187778/31dedbLo_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/889050642903293953/1773242460",
    "description": "",
    "location": "",
    "followers": 127318,
    "following": 1,
    "status": "",
    "canDm": true,
    "canMediaTag": true,
    "createdAt": "Sun Jul 23 09:12:45 +0000 2017",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 4717,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 268,
    "statusesCount": 3409,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "2073065231790809214"
    ],
    "profile_bio": {
      "description": "Democratizing AI research, education, and technologies. Learn about AI Agents for FREE at https://t.co/HHXg8rryu4",
      "entities": {
        "description": {
          "urls": [
            {
              "display_url": "academy.dair.ai/courses/elemen…",
              "expanded_url": "https://academy.dair.ai/courses/elements-of-ai-agents",
              "indices": [
                90,
                113
              ],
              "url": "https://t.co/HHXg8rryu4"
            }
          ]
        },
        "url": {
          "urls": [
            {
              "display_url": "dair.ai",
              "expanded_url": "https://www.dair.ai/",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/lkqPZtMU5s"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "display_url": "pic.twitter.com/qUSYW0TemB",
        "expanded_url": "https://twitter.com/dair_ai/status/2073065231790809214/photo/1",
        "ext_master_playlist_only": [],
        "ext_media_availability": {
          "status": "Available"
        },
        "ext_playlists": [],
        "features": {
          "large": {
            "faces": [
              {
                "h": 105,
                "w": 105,
                "x": 1382,
                "y": 881
              }
            ]
          },
          "orig": {
            "faces": [
              {
                "h": 105,
                "w": 105,
                "x": 1382,
                "y": 881
              }
            ]
          }
        },
        "id_str": "2073065227818815489",
        "indices": [
          277,
          300
        ],
        "media_key": "3_2073065227818815489",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARzFAddUWtABCgACHMUB2EEaoH4AAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABHMUB11Ra0AEKAAIcxQHYQRqgfgAA",
            "media_key": "3_2073065227818815489"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/HMUB11Ra0AElpmC.png",
        "original_info": {
          "focus_rects": [
            {
              "h": 871,
              "w": 1556,
              "x": 0,
              "y": 0
            },
            {
              "h": 1556,
              "w": 1556,
              "x": 0,
              "y": 0
            },
            {
              "h": 1774,
              "w": 1556,
              "x": 0,
              "y": 0
            },
            {
              "h": 1900,
              "w": 950,
              "x": 142,
              "y": 0
            },
            {
              "h": 1900,
              "w": 1556,
              "x": 0,
              "y": 0
            }
          ],
          "height": 1900,
          "width": 1556
        },
        "sizes": {
          "large": {
            "h": 1900,
            "w": 1556
          }
        },
        "type": "photo",
        "url": "https://t.co/qUSYW0TemB"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [
      {
        "display_url": "arxiv.org/abs/2607.02134",
        "expanded_url": "https://arxiv.org/abs/2607.02134",
        "indices": [
          947,
          970
        ],
        "url": "https://t.co/IkhknqCUiv"
      },
      {
        "display_url": "academy.dair.ai",
        "expanded_url": "https://academy.dair.ai/",
        "indices": [
          1023,
          1046
        ],
        "url": "https://t.co/LRnpZN7L4c"
      }
    ],
    "user_mentions": [
      {
        "id_str": "889050642903293953",
        "indices": [
          107,
          115
        ],
        "name": "DAIR.AI",
        "screen_name": "dair_ai"
      }
    ]
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "communityInfo": null,
  "article": null
}