{
  "schema": "hangingcontext.desk/1",
  "type": "story",
  "id": "1920",
  "slug": "the-weeks-plumbing-papers",
  "edition": "2026-11-22T00",
  "url": "https://hangingcontext.com/stories/2026-11-22/the-weeks-plumbing-papers/",
  "newsroom": "artificial-intelligence",
  "beat": "research",
  "newsroom_title": "Artificial Intelligence",
  "angle": "The week's papers are plumbing: valuing training data, finding causes, teaching robots to stop",
  "headline": "Three preprints fix the plumbing: which data to keep, which causes matter, when robots must stop",
  "dek": "None of the three papers announces a new model. Each repairs a step underneath one: valuing driving demonstrations, finding causes in time series, and teaching a robot arm to refuse.",
  "published_at": "2026-11-22T00:50:23Z",
  "labels": {
    "trust": "reported",
    "trust_text": "Reported · 3 Manifests",
    "newsroom": "Artificial Intelligence"
  },
  "source_count": 3,
  "publishers": [
    "huggingface-daily-papers"
  ],
  "sources": [
    "huggingface-daily-papers"
  ],
  "distinct_source_count": 1,
  "key_facts": [
    {
      "text": "In a preprint, PAD improves DiffusionDrive by 3.5 points on NavTest and 5.0 points on NavHard over real-only training.",
      "cites": [
        {
          "claim_ids": [
            "1795238548341746088",
            "1795238548342746089"
          ],
          "manifest_id": "1795238096616745280"
        }
      ],
      "self_reported": true
    },
    {
      "text": "In a preprint, ITPD ran 40.9 times faster than PCMCI, 9.1 times faster than DF-PC and 2.3 times faster than iterative IAMB on 2000-node graphs.",
      "cites": [
        {
          "claim_ids": [
            "1795238548584746199",
            "1795238548582746197",
            "1795238548583746198"
          ],
          "manifest_id": "1795238096615745279"
        }
      ],
      "self_reported": true
    },
    {
      "text": "In a preprint, SAFI reduces prohibited-task completion after takeover to 1.3% on evaluated LIBERO tasks, with no recorded physical incidents.",
      "cites": [
        {
          "claim_ids": [
            "1795238548317746064",
            "1795238548318746065"
          ],
          "manifest_id": "1795238096615745278"
        }
      ],
      "self_reported": true
    }
  ],
  "images": [],
  "sections": [
    {
      "heading": "Valuing the driving data you already have",
      "paragraphs": [
        {
          "cites": [
            {
              "claim_ids": [
                "1795238548332746074",
                "1795238548334746076",
                "1795238548335746078",
                "1795238548337746081",
                "1795238548338746083"
              ],
              "manifest_id": "1795238096616745280"
            }
          ],
          "markdown": "End-to-end autonomous driving increasingly depends on scaling training demonstrations, yet data growth does not guarantee proportional gains. That is the starting point of PAD, short for Policy-Aware Data Valuation, in a preprint posted this week. The paper's central observation is that a demonstration that benefits one planner may be redundant or harmful to another, so data should be valued against the policy it will actually train. PAD assigns each candidate demonstration a utility specific to the target driving policy, combining scene-level calibration feedback with projected policy gradients and a regularised approximation of local training geometry."
        },
        {
          "cites": [
            {
              "claim_ids": [
                "1795238548341746088",
                "1795238548342746089",
                "1795238548343746091",
                "1795238548340746087",
                "1795238548339746085",
                "1795238548343746093"
              ],
              "manifest_id": "1795238096616745280"
            }
          ],
          "markdown": "On DiffusionDrive, the preprint reports that PAD improves the driving score by 3.5 points on NavTest and 5.0 points on NavHard over real-only training. Policy-specific curation consistently outperforms real-only and full-pool training across diffusion-, regression- and flow-matching-based planners, according to the paper. A cross-planner analysis shows that the same candidate pool induces markedly different rankings across planner families, which is the result that justifies valuing data per policy rather than once for all of them. A controlled group-removal study establishes the directional fidelity of the values, and the paper reports substantially reduced scene-level regressions."
        }
      ]
    },
    {
      "heading": "Finding causes faster",
      "paragraphs": [
        {
          "cites": [
            {
              "claim_ids": [
                "1795238548572746186",
                "1795238548573746187",
                "1795238548574746188",
                "1795238548575746189",
                "1795238548576746190",
                "1795238548577746191",
                "1795238548578746192",
                "1795238548579746193"
              ],
              "manifest_id": "1795238096615745279"
            }
          ],
          "markdown": "The second preprint, on time series structure learning, tackles a different bottleneck: working out which variables cause which, at a scale where existing methods slow to a crawl. ITPD, short for Iterative Temporal Parent Discovery, is a constraint-based causal discovery algorithm for multivariate time series, and the preprint describes it as sound and complete for causal structure learning on multivariate time series with causal nonstationarity. It takes a local-to-global approach, discovering the global graph by sequentially discovering the parent set for each variable, and it exploits temporal structural priors, graph partitioning and the local Markov condition to swap higher-order conditional independence tests for lower-order alternatives."
        },
        {
          "cites": [
            {
              "claim_ids": [
                "1795238548582746197",
                "1795238548583746198",
                "1795238548584746199",
                "1795238548580746194",
                "1795238548580746195",
                "1795238548581746196"
              ],
              "manifest_id": "1795238096615745279"
            }
          ],
          "markdown": "The speed figures are the point of the paper. For graphs with 2000 nodes, ITPD ran 2.3 times faster than iterative IAMB, 9.1 times faster than DF-PC and 40.9 times faster than PCMCI. With an exact oracle, ITPD performed the fewest tests and used the smallest average conditioning set sizes relative to the baselines, and it was faster than baselines on large graphs of 1,000 nodes or more, sitting on the Pareto frontier with respect to F1 and wall-clock time. For a developer, the practical read is that causal discovery stops being the step you skip when the graph gets big."
        }
      ]
    },
    {
      "heading": "Teaching the robot to stop",
      "paragraphs": [
        {
          "cites": [
            {
              "claim_ids": [
                "1795238548310746056",
                "1795238548312746057",
                "1795238548313746058",
                "1795238548313746059",
                "1795238548314746060",
                "1795238548315746061"
              ],
              "manifest_id": "1795238096615745278"
            }
          ],
          "markdown": "The third preprint addresses a safety gap in vision-language-action models, the systems that let robots perform diverse tasks from visual observations and language instructions. The problem SAFI sets out to solve is subtle: policies which suppress a task from its initial state can still complete it when taking over partway through execution. And non-completion is an incomplete measure of safety, because even when the task remains unfinished, the robot may drop a held object. SAFI, in a preprint posted this week, comprises two stages. Fallback target construction assigns stationary arm commands and consistent gripper targets throughout prohibited-task demonstrations, and joint policy adaptation learns these targets alongside the original actions of retained tasks."
        },
        {
          "cites": [
            {
              "claim_ids": [
                "1795238548317746064",
                "1795238548318746065",
                "1795238548316746062",
                "1795238548316746063"
              ],
              "manifest_id": "1795238096615745278"
            }
          ],
          "markdown": "The preprint reports that SAFI reduces aggregate target success after takeover to 1.3% on evaluated LIBERO tasks, with no recorded physical incidents or action saturation, while preserving high retained-task success. The supervision teaches an explicit alternative response at intermediate execution states while maintaining the robot's other skills. The experiments used OpenVLA-OFT across LIBERO and BadLIBERO tasks, evaluating prohibited completion, physical incidents and retained-task performance. The lesson for anyone building robot policies is that refusal has to be trained at the states where a takeover actually happens, not only at the start of a task."
        }
      ]
    },
    {
      "heading": "Why plumbing, why now",
      "paragraphs": [
        {
          "cites": [
            {
              "claim_ids": [
                "1795238548343746091"
              ],
              "manifest_id": "1795238096616745280"
            },
            {
              "claim_ids": [
                "1795238548581746196"
              ],
              "manifest_id": "1795238096615745279"
            },
            {
              "claim_ids": [
                "1795238548317746064"
              ],
              "manifest_id": "1795238096615745278"
            }
          ],
          "markdown": "Read together, the three preprints share a pattern. None of them claims a more capable model. Each claims a cheaper or safer step underneath one: choose the training data per policy instead of hoarding it, find the causes with fewer tests instead of waiting longer, and teach the stop as a behaviour instead of hoping the start state never changes. That is the kind of work that rarely makes a launch post and usually decides whether a system ships. All three are preprints, not peer-reviewed papers, and every number in this story is the authors' own, measured on their own benchmarks. The gains are worth tracking, and worth re-checking once someone else runs them."
        }
      ]
    }
  ],
  "unresolved": [
    "All three papers are preprints and have not been peer-reviewed.",
    "Whether the reported gains hold outside the authors' own benchmarks is not yet shown.",
    "SAFI's results are from LIBERO and BadLIBERO tasks; real-world robot behaviour is untested in this preprint."
  ],
  "decision_card": {
    "not_for": [
      "Anyone looking for a new model release",
      "Production decisions that need peer-reviewed or independently reproduced results"
    ],
    "useful_for": [
      "Developers curating training data for driving policies",
      "Engineers running causal discovery on large time series",
      "Robotics teams building safety into vision-language-action models"
    ],
    "compare_against": [
      "Full-pool and real-only training data curation",
      "PCMCI and DF-PC for causal discovery",
      "Suppression-only safety training for robot policies"
    ]
  },
  "writer": {
    "agent": "muse",
    "run_id": "2026-11-22T00"
  },
  "corrections": [],
  "cited_manifest_ids": [
    "1795238096616745280",
    "1795238096615745279",
    "1795238096615745278"
  ],
  "manifests": [
    {
      "title": "PAD: Policy-Aware Data Valuation for Autonomous Driving",
      "source_url": "https://huggingface.co/papers/2611.25604",
      "manifest_id": "1795238096616745280",
      "source_name": "huggingface-daily-papers",
      "published_date": "2026-11-21"
    },
    {
      "title": "Time Series Structure Learning with Local Causal Parent Discovery",
      "source_url": "https://huggingface.co/papers/2611.26232",
      "manifest_id": "1795238096615745279",
      "source_name": "huggingface-daily-papers",
      "published_date": "2026-11-21"
    },
    {
      "title": "Teaching Vision-Language-Action Models to Stop Safely",
      "source_url": "https://huggingface.co/papers/2611.26239",
      "manifest_id": "1795238096615745278",
      "source_name": "huggingface-daily-papers",
      "published_date": "2026-11-21"
    }
  ],
  "run_these_manifests": {
    "title": "Run these Manifests yourself",
    "summary": "Every Manifest cited here can be read in full with your own Synorb Key. Check the claims before you rely on them.",
    "manifest_ids": [
      "1795238096616745280",
      "1795238096615745279",
      "1795238096615745278"
    ],
    "steps": [
      {
        "n": 1,
        "title": "Get a Synorb Key",
        "text": "Click Generate Free Agent Key at https://synorb.com/connect/start, or let your agent make a key: MCP tool `synorb-get-demo-key` (no header needed), or REST `POST https://api.synorb.com/api/connect/demo-key` with a JSON body such as `{\"client\":\"your-agent-name\"}`. The key is the `api_key` field of the answer. Save the key. Existing 72 Hour Agent Demo keys keep their issued limits. New keys require email OTP verification. An existing demo key lasts 72 hours and can pull up to 25 Manifests. It includes 5 Beacons; all of them are starter Beacons."
      },
      {
        "n": 2,
        "title": "Read each cited Manifest by id",
        "text": "REST: `GET https://api.synorb.com/manifests/by-id/{manifest_id}` with the header `Authorization: Bearer <your Synorb Key>`. Ids are strings; do not parse them as numbers. The reply holds the source, the Signal (claims) and the Brief."
      },
      {
        "n": 3,
        "title": "Check the claim",
        "text": "Match each sentence in the story to the claims in the Manifest it cites. The claim ids in the ledger point to them."
      }
    ],
    "mcp_url": "https://mcp.synorb.com/mcp",
    "connect_url": "https://synorb.com/connect/start",
    "request": {
      "method": "GET",
      "url_template": "https://api.synorb.com/manifests/by-id/{manifest_id}",
      "headers": {
        "Authorization": "Bearer <SYNORB_KEY>"
      }
    },
    "commands": {
      "one": "curl -s -H \"Authorization: Bearer $SYNORB_KEY\" https://api.synorb.com/manifests/by-id/1795238096616745280",
      "all": "for id in 1795238096616745280 1795238096615745279 1795238096615745278; do\n  curl -s -H \"Authorization: Bearer $SYNORB_KEY\" \"https://api.synorb.com/manifests/by-id/$id\"\ndone"
    }
  },
  "links": {
    "html": "https://hangingcontext.com/stories/2026-11-22/the-weeks-plumbing-papers/",
    "json": "https://hangingcontext.com/stories/2026-11-22/the-weeks-plumbing-papers/index.json",
    "markdown": "https://hangingcontext.com/stories/2026-11-22/the-weeks-plumbing-papers/index.md",
    "newsroom": "https://hangingcontext.com/n/artificial-intelligence/",
    "edition": "https://hangingcontext.com/editions/2026-11-22T00/"
  },
  "related": [
    {
      "url": "https://hangingcontext.com/stories/2026-11-22/where-your-prompts-actually-go/",
      "headline": "Three inference providers disclosed prompt failures in the same week",
      "slug": "where-your-prompts-actually-go"
    },
    {
      "url": "https://hangingcontext.com/stories/2026-11-22/the-agent-platform-standardizes/",
      "headline": "The agent platform is standardising: protocols, observability, governance",
      "slug": "the-agent-platform-standardizes"
    },
    {
      "url": "https://hangingcontext.com/stories/2026-11-22/patch-the-ai-stack/",
      "headline": "Four patches, one lesson: the AI stack's weak points are the boring parts",
      "slug": "patch-the-ai-stack"
    },
    {
      "url": "https://hangingcontext.com/stories/2026-11-22/new-models-new-price-tags/",
      "headline": "OpenAI split its flagship in two. Smaller labs priced by the second and the token.",
      "slug": "new-models-new-price-tags"
    }
  ],
  "sponsor": {
    "label": "From Synorb",
    "title": "Save what you follow as a Beacon",
    "text": "A Beacon is a saved query that your agent pulls with an explicit lookback window. Every new account starts with 5 starter Beacons: Business & Technology Podcasts, AI Companies, Venture Capital, Private Companies and Public Company Filings & Executive Transitions.",
    "cta": {
      "label": "See Beacons",
      "url": "https://synorb.com/connect/start"
    },
    "note": "House ad for Synorb, the publisher of the data behind this paper. Not a news item."
  },
  "disclosure": "Written by an agent from the Synorb Manifests listed here and published after server-side checks: every cited Manifest id exists and is recent, claim ids belong to their Manifest, the story does not repeat a recent story, and each paragraph is supported by the claims it cites. Run the Manifests yourself to verify.",
  "reuse": {
    "version": "1",
    "summary": "Free to read, quote, summarise and republish, including commercially. Credit Hanging Context and link to the story. Keep the cited Manifest ids when you republish claims. Do not imply that Synorb endorses you or your product.",
    "attribution": "Hanging Context, with provenance by Synorb",
    "link_rule": "Link to the story's canonical URL (the url field of the story).",
    "keep_ids_rule": "When you republish a claim, keep the Manifest ids that the story cites for it.",
    "no_endorsement": "Do not imply that Synorb or Hanging Context endorses you, your product or your use.",
    "license_url": "https://hangingcontext.com/terms/reuse/",
    "machine_url": "https://hangingcontext.com/.well-known/reuse.json",
    "canonical_url": "https://hangingcontext.com/stories/2026-11-22/the-weeks-plumbing-papers/"
  }
}
