{
  "version": 2,
  "generated": "2026-07-31",
  "owner": {
    "name": "Aaryan Patel",
    "email": "aaryansp26@gmail.com",
    "github": "https://github.com/asp53826",
    "linkedin": "https://www.linkedin.com/in/aaryanpatelsystems/",
    "site": "https://asp53826.github.io",
    "role": "Systems and ML Infrastructure Engineer",
    "education": "Computer Science undergraduate at the University of Georgia",
    "work": "Automation and analytics at MP Equipment"
  },
  "thesis": "I build systems that survive faults, bad data, and dishonest benchmarks.",
  "contract": "Build the mechanism. Attack the assumptions. Measure against a real baseline. Publish where it loses.",
  "health": {
    "measuredSystems": 23,
    "publicRepositories": 25,
    "testFunctions": 806,
    "sourceFiles": 485,
    "languages": 8,
    "liveLabs": 4,
    "trackedWorkflows": 11,
    "lastVerified": "2026-07-31"
  },
  "current": {
    "title": "Evidence infrastructure for technical portfolios",
    "repo": "asp53826.github.io",
    "status": "active",
    "summary": "A single source of truth that generates the recruiter site, GitHub profile surfaces, proof cards, social artwork, and resume.",
    "proof": "Every public claim resolves to a command, source, oracle, and limitation."
  },
  "experience": {
    "verifiedOn": "2026-07-31",
    "disclosure": "Interactive replays are deterministic narrative checkpoints derived from published tests and benchmark tables. They are not live production telemetry.",
    "flagships": [
      {
        "projectId": "raft-mvcc",
        "commit": "dbd5398",
        "benchmarkCommand": "make clean test benchmark",
        "sourceFiles": [
          "tests/test_raft_mvcc.cpp",
          "bench/benchmark.cpp",
          "src/raft.cpp",
          "src/linearizability.cpp"
        ],
        "scenarioLabel": "Leader isolation and log repair",
        "scenarioSummary": "Isolate the leader, allow an unsafe proposal on the minority side, elect a majority leader, then heal the partition.",
        "invariant": "A minority leader may append locally but cannot advance the committed index.",
        "result": "The majority fails over in 11 logical ticks and the old leader's conflicting suffix is repaired after healing.",
        "events": [
          {
            "time": "T+00",
            "label": "Five nodes agree",
            "detail": "Node 1 leads a healthy five-node cluster; the committed prefix matches on every node.",
            "state": "healthy"
          },
          {
            "time": "T+01",
            "label": "Partition injected",
            "detail": "Node 1 is isolated from the four-node majority. Messages crossing the cut are deterministically dropped.",
            "state": "fault"
          },
          {
            "time": "T+03",
            "label": "Minority proposal",
            "detail": "The isolated leader accepts an uncommitted local proposal but cannot obtain a quorum.",
            "state": "contained"
          },
          {
            "time": "T+07",
            "label": "Fresh candidate wins",
            "detail": "The majority elects a leader using the term and last-log freshness checks.",
            "state": "recovering"
          },
          {
            "time": "T+11",
            "label": "Majority commits",
            "detail": "The new leader commits on the majority while the isolated leader remains unable to commit.",
            "state": "verified"
          },
          {
            "time": "HEAL",
            "label": "Conflict repaired",
            "detail": "Healing exposes the stale suffix; nextIndex backtracking truncates and replaces it.",
            "state": "verified"
          }
        ],
        "history": [
          {
            "label": "Mechanism release",
            "commit": "dbd5398",
            "metric": "598 assertions",
            "note": "Targeted invariants plus a seeded failover campaign."
          },
          {
            "label": "Published failover",
            "commit": "dbd5398",
            "metric": "11 logical ticks",
            "note": "Five-node leader isolation and majority re-election."
          },
          {
            "label": "Verification surface",
            "commit": "b4eef31",
            "metric": "CI badge added",
            "note": "Repository metadata now exposes the same correctness path."
          }
        ],
        "postmortem": {
          "failure": "An isolated leader can still accept a local append, which looks successful if commit state is ignored.",
          "signal": "The test tracks commit advancement separately from proposal acceptance.",
          "correction": "Only a current-term entry replicated to a majority can advance the leader's commit index.",
          "lesson": "Availability-looking behavior is not safety evidence; the invariant must be observed at the commit boundary."
        }
      },
      {
        "projectId": "edgar-mcp",
        "commit": "825052d",
        "benchmarkCommand": "make test && make bench",
        "sourceFiles": [
          "src/edgar_mcp/client.py",
          "tests/test_client.py",
          "tests/test_tools.py",
          "README.md"
        ],
        "scenarioLabel": "Burst control and truthful cache hits",
        "scenarioSummary": "Drive concurrent EDGAR reads through the original burst-prone design, then replay the strict pacer and host-aware cache correction.",
        "invariant": "Request grants stay paced below the SEC ceiling, and a cache hit transfers no response body.",
        "result": "The corrected client sustains 9.2 requests per second and serves a warm 10-K in 1.1 ms with zero downloaded megabytes.",
        "events": [
          {
            "time": "T+00",
            "label": "Cold filing read",
            "detail": "The client fetches a 1.52 MB 10-K and stores the immutable archive document.",
            "state": "healthy"
          },
          {
            "time": "T+01",
            "label": "Burst model challenged",
            "detail": "The original full token bucket places 19 grants inside a one-second window.",
            "state": "fault"
          },
          {
            "time": "T+02",
            "label": "Strict pacing enabled",
            "detail": "A global monotonic pacer spaces grants and removes startup burst capacity.",
            "state": "contained"
          },
          {
            "time": "T+03",
            "label": "False cache hit exposed",
            "detail": "A reported hit still transfers 3.75 MB because the host cannot validate it as assumed.",
            "state": "fault"
          },
          {
            "time": "T+04",
            "label": "Freshness split by host",
            "detail": "Immutable archives cache forever; data APIs use TTL or validators that the host actually provides.",
            "state": "recovering"
          },
          {
            "time": "T+05",
            "label": "Warm read verified",
            "detail": "The 10-K returns in 1.1 ms with 0.00 MB downloaded, a measured 138x improvement.",
            "state": "verified"
          }
        ],
        "history": [
          {
            "label": "First rate benchmark",
            "commit": "pre-fix",
            "metric": "19 req / 1 s",
            "note": "A full token bucket nearly doubled the intended ceiling."
          },
          {
            "label": "Strict pacer",
            "commit": "current",
            "metric": "9.2 req / s",
            "note": "Grants are globally spaced with no initial burst."
          },
          {
            "label": "First cache benchmark",
            "commit": "pre-fix",
            "metric": "3.75 MB warm",
            "note": "The hit counter hid a complete re-download."
          },
          {
            "label": "Host-aware cache",
            "commit": "current",
            "metric": "0.00 MB warm",
            "note": "Warm 10-K read measures 1.1 ms and 138x speedup."
          }
        ],
        "postmortem": {
          "failure": "The first implementation looked compliant and cached because its abstractions reported tokens and hits.",
          "signal": "Wire-level one-second request windows and transferred-byte counters contradicted the abstraction-level metrics.",
          "correction": "Replace burst capacity with strict pacing and assign cache freshness rules per EDGAR host.",
          "lesson": "Measure the wire, not the class name: a RateLimiter and Cache do not prove rate limiting or caching."
        }
      },
      {
        "projectId": "track-fusion",
        "commit": "099601b",
        "benchmarkCommand": "python -m pytest -q && python bench/benchmark.py --quick",
        "sourceFiles": [
          "tf/imm.py",
          "tf/assoc/jpda.py",
          "tf/metrics.py",
          "bench/benchmark.py"
        ],
        "scenarioLabel": "Maneuver, crossing, and cardinality failure",
        "scenarioSummary": "Track a maneuvering target, introduce a crossing under clutter, then compare localization accuracy with full OSPA cost.",
        "invariant": "Association comparisons hold the tracker constant, and evaluation charges for both localization and target-count errors.",
        "result": "IMM lowers localization error 47% inside its useful turn-rate band; JPDA improves crossing localization but sustains 2.7x the false tracks.",
        "events": [
          {
            "time": "T+00",
            "label": "Straight leg",
            "detail": "The CV and IMM estimators agree while motion remains close to constant velocity.",
            "state": "healthy"
          },
          {
            "time": "T+01",
            "label": "Turn begins",
            "detail": "Measurements shift probability toward the coordinated-turn modes in the IMM bank.",
            "state": "recovering"
          },
          {
            "time": "T+02",
            "label": "Localization measured",
            "detail": "OSPA localization falls from 26.92 for the single CV filter to 14.40 for IMM.",
            "state": "verified"
          },
          {
            "time": "T+03",
            "label": "Tracks cross",
            "detail": "Two measurements become plausible for both targets under light clutter.",
            "state": "fault"
          },
          {
            "time": "T+04",
            "label": "Soft association wins locally",
            "detail": "JPDA localization reaches 13.76 versus 14.70 for GNN across the crossing.",
            "state": "contained"
          },
          {
            "time": "T+05",
            "label": "Cardinality exposes the loss",
            "detail": "JPDA keeps 2.7x the false tracks; total OSPA is 39.55 versus 28.73 for GNN.",
            "state": "verified"
          }
        ],
        "history": [
          {
            "label": "Single CV baseline",
            "commit": "099601b",
            "metric": "26.92 OSPA loc",
            "note": "Coverage is 0.893 through the maneuver."
          },
          {
            "label": "IMM bank",
            "commit": "099601b",
            "metric": "14.40 OSPA loc",
            "note": "Coverage rises to 0.960 inside the 3-6 degree/s useful band."
          },
          {
            "label": "Crossing GNN",
            "commit": "099601b",
            "metric": "28.73 total OSPA",
            "note": "Hard association has slightly worse localization and much lower cardinality error."
          },
          {
            "label": "Crossing JPDA",
            "commit": "099601b",
            "metric": "39.55 total OSPA",
            "note": "Localization improves while false tracks rise from 0.21 to 0.56 per scan."
          }
        ],
        "postmortem": {
          "failure": "RMSE and localization-only views make JPDA look like the better crossing strategy.",
          "signal": "OSPA cardinality cost reveals marginal clutter tracks that soft association keeps alive.",
          "correction": "Publish localization and cardinality separately, then compare the total under paired seeds.",
          "lesson": "A better estimator can be a worse tracking system when the metric ignores existence errors."
        }
      }
    ]
  },
  "routes": [
    {
      "id": "systems",
      "label": "Systems",
      "short": "SYS",
      "summary": "Storage, execution, consensus, and fault discovery.",
      "projects": [
        "raft-mvcc",
        "columnar-engine",
        "dst-harness"
      ]
    },
    {
      "id": "quant",
      "label": "Quant / Finance",
      "short": "QNT",
      "summary": "Financial data, market structure, and differentiable pricing.",
      "projects": [
        "edgar-mcp",
        "aad-greeks",
        "lob-market-making"
      ]
    },
    {
      "id": "defense",
      "label": "Defense / Autonomy",
      "short": "DEF",
      "summary": "Tracking, radar image formation, and GPS-denied navigation.",
      "projects": [
        "track-fusion",
        "sar-focus",
        "vio-nav"
      ]
    },
    {
      "id": "ml-infrastructure",
      "label": "ML Infrastructure",
      "short": "MLI",
      "summary": "Retrieval, inference serving, and distributed training.",
      "projects": [
        "annlite",
        "vllm-lite",
        "dist-train"
      ]
    }
  ],
  "projects": [
    {
      "id": "raft-mvcc",
      "name": "raft-mvcc",
      "track": "systems",
      "language": "C++17",
      "tagline": "Consensus, serializable snapshots, and machine-checkable histories.",
      "problem": "A replicated database can acknowledge writes while violating safety under partitions, leader changes, or transaction conflicts.",
      "mechanism": "Raft elections and conflict repair combined with MVCC snapshots, serializable OCC, safe-point GC, and P-compositional linearizability checking.",
      "attack": "Seeded partitions, stale candidates, minority leaders, conflicting transactions, tombstones, and invalid histories.",
      "metric": "598",
      "metricLabel": "assertions across seeded faults",
      "proof": "Five-node failover completes in 11 simulator ticks while minority leaders cannot commit.",
      "limitation": "An in-process simulator: no sockets, fsync, snapshots, membership changes, or multi-range transactions.",
      "command": "git clone https://github.com/asp53826/raft-mvcc && cd raft-mvcc && make test",
      "repo": "https://github.com/asp53826/raft-mvcc",
      "methods": [
        "linearizability",
        "fault injection",
        "differential invariants"
      ]
    },
    {
      "id": "columnar-engine",
      "name": "columnar-engine",
      "track": "systems",
      "language": "C++17",
      "tagline": "Vector-at-a-time analytical execution checked against scalar oracles.",
      "problem": "Analytical operators can be fast while silently mishandling nulls, selections, joins, or aggregation.",
      "mechanism": "Null bitmaps, selection vectors, vectorized filters, joins, aggregation, and TPC-H Q1.",
      "attack": "Every vectorized operator is differentially checked against a scalar reference.",
      "metric": "53.1M",
      "metricLabel": "TPC-H Q1 rows per second",
      "proof": "6,288 assertions; batched filters are 1.94x the scalar implementation.",
      "limitation": "In-memory engine without persistence, distributed execution, or a SQL frontend.",
      "command": "git clone https://github.com/asp53826/columnar-engine && cd columnar-engine && make test",
      "repo": "https://github.com/asp53826/columnar-engine",
      "methods": [
        "scalar oracle",
        "differential testing",
        "benchmark"
      ]
    },
    {
      "id": "dst-harness",
      "name": "dst-harness",
      "track": "systems",
      "language": "Python",
      "tagline": "Deterministic simulation testing scored by seeds-to-first-catch.",
      "problem": "Distributed failures are hard to reproduce when time, network, disk, and scheduling remain nondeterministic.",
      "mechanism": "Virtual clock, network and disk, seeded fault injection, Raft safety properties, and a Wing-Gong checker.",
      "attack": "Twelve planted Raft defects plus 2,000 clean control seeds.",
      "metric": "12 / 12",
      "metricLabel": "planted defects caught",
      "proof": "Seeds-to-first-catch range from 1 to 485; the harness also found two real bugs with reproducing seeds.",
      "limitation": "The target protocol model is deliberately smaller than a production Raft implementation.",
      "command": "git clone https://github.com/asp53826/dst-harness && cd dst-harness && python3 -m venv .venv && .venv/bin/pip install -e '.[dev]' && .venv/bin/python -m pytest -q",
      "repo": "https://github.com/asp53826/dst-harness",
      "methods": [
        "deterministic simulation",
        "mutation testing",
        "linearizability"
      ]
    },
    {
      "id": "edgar-mcp",
      "name": "edgar-mcp",
      "track": "quant",
      "language": "Python",
      "tagline": "SEC EDGAR tools with bounded context, caching, and global pacing.",
      "problem": "Filings are large, issuer identities are ambiguous, and naive concurrent clients can violate the SEC request ceiling.",
      "mechanism": "Identity resolution, filing history, bounded text windows, XBRL discovery, per-host cache validation, and a global request pacer.",
      "attack": "Cold and warm reads, burst traffic, identity collisions, overflow history, and malformed iXBRL.",
      "metric": "138x",
      "metricLabel": "warm 10-K read vs cold fetch",
      "proof": "32 offline tests; peak request windows stay at the SEC 10 requests-per-second ceiling.",
      "limitation": "Public EDGAR data only; it is not an investment recommendation or a complete accounting model.",
      "command": "git clone https://github.com/asp53826/edgar-mcp && cd edgar-mcp && make test",
      "repo": "https://github.com/asp53826/edgar-mcp",
      "live": "https://asp53826.github.io/edgar-mcp/",
      "methods": [
        "rate-limit enforcement",
        "cache benchmark",
        "fixture tests"
      ]
    },
    {
      "id": "aad-greeks",
      "name": "aad-greeks",
      "track": "quant",
      "language": "Python",
      "tagline": "Reverse-mode automatic differentiation over Monte Carlo paths.",
      "problem": "Bumping every pricing input scales linearly and finite differences collapse near discontinuous payoffs.",
      "mechanism": "A tape-based reverse-mode AD engine with pricers written once and differentiated instead of hand-derived.",
      "attack": "Analytic Black-Scholes formulas, central differences across bump sizes, and discontinuous-payoff failure cases.",
      "metric": "5.6e-16",
      "metricLabel": "maximum analytic error",
      "proof": "19 tests; all Greeks cost 1.7-2.4x the price across a 50x change in input count.",
      "limitation": "Pathwise derivatives return a wrong zero delta for an unsmoothed digital payoff; the live lab exposes it.",
      "command": "git clone https://github.com/asp53826/aad-greeks && cd aad-greeks && make test",
      "repo": "https://github.com/asp53826/aad-greeks",
      "live": "https://asp53826.github.io/aad-greeks/",
      "methods": [
        "analytic oracle",
        "finite differences",
        "complexity benchmark"
      ]
    },
    {
      "id": "lob-market-making",
      "name": "lob-market-making",
      "track": "quant",
      "language": "Python",
      "tagline": "Price-time matching and market making under toxic flow.",
      "problem": "Raw PnL can make a strategy look strong while inventory exposure and adverse selection carry the risk.",
      "mechanism": "Limit order book, post-only orders, informed flow, three quoting strategies, and exact PnL decomposition.",
      "attack": "Paired 12-seed strategy comparison with spread, inventory, and toxicity held explicit.",
      "metric": "7x",
      "metricLabel": "naive inventory deviation",
      "proof": "36 tests; naive quoting wins raw PnL and loses every risk-adjusted metric.",
      "limitation": "Synthetic order flow without exchange latency, queue-position uncertainty, or real fees.",
      "command": "git clone https://github.com/asp53826/lob-market-making && cd lob-market-making && make test",
      "repo": "https://github.com/asp53826/lob-market-making",
      "live": "https://asp53826.github.io/lob-market-making/",
      "methods": [
        "paired seeds",
        "PnL attribution",
        "regime sweep"
      ]
    },
    {
      "id": "track-fusion",
      "name": "track-fusion",
      "track": "defense",
      "language": "Python",
      "tagline": "IMM, JPDA, track scoring, and OSPA from the filter up.",
      "problem": "Tracking fails across estimation, association, and track existence; RMSE alone hides cardinality failure.",
      "mechanism": "IMM motion bank, exact JPDA enumeration with bounded fallback, Wald track scoring, and OSPA decomposition.",
      "attack": "Turn-rate sweeps, crossing targets, clutter, and paired association comparisons.",
      "metric": "47%",
      "metricLabel": "localization error reduction",
      "proof": "67 tests; IMM coverage rises from 0.893 to 0.960, while the published sweep shows where the bank loses.",
      "limitation": "The useful IMM band is 3-6 degrees per second; at 0 and 12 degrees per second the configured bank loses.",
      "command": "git clone https://github.com/asp53826/track-fusion && cd track-fusion && python -m pip install -e '.[dev]' && python -m pytest -q",
      "repo": "https://github.com/asp53826/track-fusion",
      "methods": [
        "OSPA",
        "paired seeds",
        "parameter sweep"
      ]
    },
    {
      "id": "sar-focus",
      "name": "sar-focus",
      "track": "defense",
      "language": "Python",
      "tagline": "Image formation checked against analytic resolution and sidelobe theory.",
      "problem": "A plausible radar image can still have the wrong resolution or impossible sidelobes.",
      "mechanism": "LFM pulse compression, time-domain backprojection, phase-gradient autofocus, and impulse-response analysis.",
      "attack": "Independent bandwidth/aperture sweeps and theory checks for resolution and PSLR.",
      "metric": "<0.5%",
      "metricLabel": "resolution error vs theory",
      "proof": "27 tests; the theory oracle exposed interpolation that produced physically impossible sidelobes.",
      "limitation": "Synthetic phase history with idealized propagation and no measured sensor calibration errors.",
      "command": "git clone https://github.com/asp53826/sar-focus && cd sar-focus && python -m pip install -e '.[dev]' && python -m pytest -q",
      "repo": "https://github.com/asp53826/sar-focus",
      "methods": [
        "analytic theory",
        "double dissociation",
        "impulse response"
      ]
    },
    {
      "id": "vio-nav",
      "name": "vio-nav",
      "track": "defense",
      "language": "Python",
      "tagline": "MSCKF visual-inertial odometry built from the Lie algebra up.",
      "problem": "IMU bias integrates into unbounded position drift while a monocular camera cannot observe scale alone.",
      "mechanism": "SO(3) preintegration, sliding camera-state window, null-space feature marginalization, and ATE/RPE evaluation.",
      "attack": "Duration sweeps, hover/circle/figure-eight motion, parallax rejection, and dead-reckoning baseline.",
      "metric": "51.9x",
      "metricLabel": "lower drift at 40 seconds",
      "proof": "37 tests; MSCKF stays near four centimeters while dead reckoning reaches 2.106 meters.",
      "limitation": "At five seconds VIO is worse than inertial-only, and hover makes it 13x worse because depth is unobservable.",
      "command": "git clone https://github.com/asp53826/vio-nav && cd vio-nav && python -m pip install -e '.[dev]' && python -m pytest -q",
      "repo": "https://github.com/asp53826/vio-nav",
      "methods": [
        "ground-truth trajectory",
        "motion sweep",
        "ATE and RPE"
      ]
    },
    {
      "id": "annlite",
      "name": "annlite",
      "track": "ml-infrastructure",
      "language": "C++17 + Python",
      "tagline": "HNSW with SIMD kernels, Python bindings, and FAISS comparison.",
      "problem": "Approximate retrieval claims are meaningless without the full recall-versus-latency curve.",
      "mechanism": "Layered HNSW graph, diversity-aware neighbor selection, SIMD distance kernels, and GIL-free search.",
      "attack": "Exact ground truth, recall-matched FAISS comparison, and thread-count invariance.",
      "metric": "1.83x",
      "metricLabel": "FAISS QPS at 0.999 recall",
      "proof": "51 tests; at 98.5% recall it performs 26x fewer distance computations than exact scan.",
      "limitation": "FAISS remains 10-20% faster in the low-recall regime; the crossover appears only at high recall.",
      "command": "git clone https://github.com/asp53826/annlite && cd annlite && pip install -r requirements-dev.txt && make test",
      "repo": "https://github.com/asp53826/annlite",
      "methods": [
        "exact recall",
        "FAISS baseline",
        "concurrency invariants"
      ]
    },
    {
      "id": "vllm-lite",
      "name": "vllm-lite",
      "track": "ml-infrastructure",
      "language": "Python",
      "tagline": "Paged KV cache and continuous batching around a small model.",
      "problem": "Static batching strands KV memory and creates head-of-line blocking under variable request lengths.",
      "mechanism": "Paged cache, continuous batching, chunked prefill, prefix caching, and speculative decoding.",
      "attack": "Same weights, sampling, traffic distribution, and memory budget across sequential, static, and paged schedulers.",
      "metric": "94%",
      "metricLabel": "KV slot utilization vs 21%",
      "proof": "90 tests; paged scheduling reaches 2.9x sequential throughput and 5.5x better median TTFT.",
      "limitation": "CPU-scale simulator with a small model; it does not claim production GPU kernel performance.",
      "command": "git clone https://github.com/asp53826/vllm-lite && cd vllm-lite && pip install -r requirements.txt && pytest",
      "repo": "https://github.com/asp53826/vllm-lite",
      "methods": [
        "scheduler benchmark",
        "memory accounting",
        "token invariance"
      ]
    },
    {
      "id": "dist-train",
      "name": "dist-train",
      "track": "ml-infrastructure",
      "language": "Python",
      "tagline": "Ring all-reduce built from send/recv, then measured where it loses.",
      "problem": "A one-line collective hides the communication cost and the scale at which latency dominates bandwidth efficiency.",
      "mechanism": "Ring all-reduce, data parallelism, tensor parallelism, pipeline parallelism, and explicit cost models.",
      "attack": "Every collective is checked against torch.distributed across worker counts and tensor sizes.",
      "metric": "58.7 MB",
      "metricLabel": "per worker at eight workers",
      "proof": "57 tests; the naive baseline sends 234.9 MB per worker under the same eight-worker case.",
      "limitation": "Loopback gloo on a 10-core machine; efficiency falls past four workers and small tensors favor naive collectives.",
      "command": "git clone https://github.com/asp53826/dist-train && cd dist-train && pip install -r requirements.txt && pytest",
      "repo": "https://github.com/asp53826/dist-train",
      "methods": [
        "torch.distributed oracle",
        "cost model",
        "scaling sweep"
      ]
    }
  ]
}