Round confirm-intent-short-1

Short intent on a fresh specification

Status · DESCRIPTIVEReviewed status is transcribed from rounds/STATUS.md. The original narrative and its qualifications remain below.

Source-reported narrativeRound README and results text are source material. Numeric values that are not tied to a claim ledger record remain source-reported.

Round source README · rounds/confirm-intent-short-1/README.md

A descriptive confirmation screen on one new private specification in Go and Elixir. The round is approximate: Lab verified the code in the builder's workspace, not in a clean copy of the candidate as Kogen now does.

Question and scope

On a fresh specification whose acceptance scenarios cover all requirements checked by hidden tests, is a short intent correct in at least as many paired blocks as full prose, with no more wrong submissions or wrong first-green builds?

The task specifications remain private. This page reports the public task IDs and the per-test outcome IDs exported with them; it does not reproduce the task prose, acceptance scenarios, hidden-test code, or reference implementations.

What each arm received

The full arm received the complete prose specification plus an extended Gherkin acceptance feature and its step definitions. The short arm received an Intent frame containing a title, purpose, command-line synopsis, and option names, plus the same extended feature and steps. The two arms used identical acceptance scenarios for each task, and the feature coverage was checked against every requirement exercised by hidden tests.

A rescue means review changes a tree that failed one or more hidden tests into a tree that passes them all. The reviewer approved all 12 trees unchanged, so each submission was its first green build and no rescue occurred.

Fixed rule

CONFIRMED requires short to be correct in at least as many blocks as full, with no more wrong submissions and no more wrong first-green builds, across at least five usable blocks. REJECTED applies if short is correct in fewer blocks or has more wrong submissions or wrong first-green builds. UNRESOLVED applies when fewer than five usable blocks are available.

Results

A paired block is one task and repetition run with both full and short. A first-green build is the first code snapshot that passed the workflow's verification checks; hidden tests determine whether it was correct.

The run scored 12 of 12 attempts and had six usable pairs of attempts, each comparing full and short on the same task and repetition: two task IDs, three repetitions, and both arms. There were no wrong submissions, builder stops, provider refusals, repairs, or wrong first-green builds.

Arm Correct blocks Wrong submissions Wrong first-green builds Reviewer edits Builder input tokens Reviewer input tokens Total input tokens Sum of review-stage durations (Lab bundle)
Full prose 6 of 6 0 0 0 0.45M 0.61M 1.06M 538.9 s
Short intent 6 of 6 0 0 0 0.39M 0.48M 0.87M 410.4 s

CONFIRMED. Short was correct in as many usable blocks as full (6 of 6), with no more wrong submissions and no more wrong first-green builds; the run had at least five usable blocks.

Task ID Full correct submissions Short correct submissions
subnet-ex 3 of 3 3 of 3
subnet-go 3 of 3 3 of 3

Public test outcomes

The outcomes below list repetitions 0, 1, and 2 in that order. State strings come directly from the exported public ID maps.

Task ID Public test ID Full outcomes Short outcomes
subnet-ex test_hidden:test_address_lexical_and_range_errors_are_exact passed / passed / passed passed / passed / passed
subnet-ex test_hidden:test_address_validation_precedes_prefix_validation passed / passed / passed passed / passed / passed
subnet-ex test_hidden:test_argument_errors_and_precedence passed / passed / passed passed / passed / passed
subnet-ex test_hidden:test_ascii_check_precedes_all_row_parsing passed / passed / passed passed / passed / passed
subnet-ex test_hidden:test_cidr_shape_error_is_exact passed / passed / passed passed / passed / passed
subnet-ex test_hidden:test_comments_must_start_in_first_column passed / passed / passed passed / passed / passed
subnet-ex test_hidden:test_crlf_final_cr_and_physical_line_numbers passed / passed / passed passed / passed / passed
subnet-ex test_hidden:test_default_retains_duplicate_canonical_subnets passed / passed / passed passed / passed / passed
subnet-ex test_hidden:test_default_text_empty_and_dash_json passed / passed / passed passed / passed / passed
subnet-ex test_hidden:test_file_path_uses_same_output_as_stdin passed / passed / passed passed / passed / passed
subnet-ex test_hidden:test_first_bad_physical_line_wins_without_partial_output passed / passed / passed passed / passed / passed
subnet-ex test_hidden:test_format_text_and_unique_work_in_either_order passed / passed / passed passed / passed / passed
subnet-ex test_hidden:test_help_exact_and_does_not_read_input passed / passed / passed passed / passed / passed
subnet-ex test_hidden:test_json_has_exact_key_order_and_aggregate_values passed / passed / passed passed / passed / passed
subnet-ex test_hidden:test_missing_file_reports_exact_read_error passed / passed / passed passed / passed / passed
subnet-ex test_hidden:test_prefix_lexical_and_range_errors_are_exact passed / passed / passed passed / passed / passed
subnet-ex test_hidden:test_text_sorts_and_canonicalizes_host_bits passed / passed / passed passed / passed / passed
subnet-ex test_hidden:test_thirty_one_and_thirty_two_prefix_hosts_are_usable passed / passed / passed passed / passed / passed
subnet-ex test_hidden:test_thirty_prefix_hosts_exclude_network_and_broadcast passed / passed / passed passed / passed / passed
subnet-ex test_hidden:test_unique_keeps_one_canonical_network_prefix_pair passed / passed / passed passed / passed / passed
subnet-ex test_hidden:test_unique_still_validates_later_duplicate_lines passed / passed / passed passed / passed / passed
subnet-ex test_hidden:test_unknown_options_and_help_with_extra_argument passed / passed / passed passed / passed / passed
subnet-ex test_hidden:test_unrecognized_option_is_checked_before_later_path_count passed / passed / passed passed / passed / passed
subnet-ex test_hidden:test_value_option_consumes_flag_like_token passed / passed / passed passed / passed / passed
subnet-ex test_hidden:test_zero_prefix_and_decimal_output_bounds passed / passed / passed passed / passed / passed
subnet-go test_hidden:test_address_lexical_and_range_errors_are_exact passed / passed / passed passed / passed / passed
subnet-go test_hidden:test_address_validation_precedes_prefix_validation passed / passed / passed passed / passed / passed
subnet-go test_hidden:test_argument_errors_and_precedence passed / passed / passed passed / passed / passed
subnet-go test_hidden:test_ascii_check_precedes_all_row_parsing passed / passed / passed passed / passed / passed
subnet-go test_hidden:test_cidr_shape_error_is_exact passed / passed / passed passed / passed / passed
subnet-go test_hidden:test_comments_must_start_in_first_column passed / passed / passed passed / passed / passed
subnet-go test_hidden:test_crlf_final_cr_and_physical_line_numbers passed / passed / passed passed / passed / passed
subnet-go test_hidden:test_default_retains_duplicate_canonical_subnets passed / passed / passed passed / passed / passed
subnet-go test_hidden:test_default_text_empty_and_dash_json passed / passed / passed passed / passed / passed
subnet-go test_hidden:test_file_path_uses_same_output_as_stdin passed / passed / passed passed / passed / passed
subnet-go test_hidden:test_first_bad_physical_line_wins_without_partial_output passed / passed / passed passed / passed / passed
subnet-go test_hidden:test_format_text_and_unique_work_in_either_order passed / passed / passed passed / passed / passed
subnet-go test_hidden:test_help_exact_and_does_not_read_input passed / passed / passed passed / passed / passed
subnet-go test_hidden:test_json_has_exact_key_order_and_aggregate_values passed / passed / passed passed / passed / passed
subnet-go test_hidden:test_missing_file_reports_exact_read_error passed / passed / passed passed / passed / passed
subnet-go test_hidden:test_prefix_lexical_and_range_errors_are_exact passed / passed / passed passed / passed / passed
subnet-go test_hidden:test_text_sorts_and_canonicalizes_host_bits passed / passed / passed passed / passed / passed
subnet-go test_hidden:test_thirty_one_and_thirty_two_prefix_hosts_are_usable passed / passed / passed passed / passed / passed
subnet-go test_hidden:test_thirty_prefix_hosts_exclude_network_and_broadcast passed / passed / passed passed / passed / passed
subnet-go test_hidden:test_unique_keeps_one_canonical_network_prefix_pair passed / passed / passed passed / passed / passed
subnet-go test_hidden:test_unique_still_validates_later_duplicate_lines passed / passed / passed passed / passed / passed
subnet-go test_hidden:test_unknown_options_and_help_with_extra_argument passed / passed / passed passed / passed / passed
subnet-go test_hidden:test_unrecognized_option_is_checked_before_later_path_count passed / passed / passed passed / passed / passed
subnet-go test_hidden:test_value_option_consumes_flag_like_token passed / passed / passed passed / passed / passed
subnet-go test_hidden:test_zero_prefix_and_decimal_output_bounds passed / passed / passed passed / passed / passed

All 12 exported attempts were correct, with every listed public ID in the passed state for all three repetitions in each arm. The short arm used 18% less input (0.87M versus 1.06M). Together with the development screen, the short arm was correct in 14 of 14 attempts against 14 of 14 for full, across six task IDs and two languages, at 18–19% lower input.

Limits

This is one fresh specification represented in two languages and six paired blocks. It supports the fixed comparison on this sample and did not test weaker builders or less fully specified work. The extended feature needed 24 more scenarios than the standard one (41 in total), so shorter prose moved detail into the scenarios.

Required reproduction metadata

The frozen settings, resolved configurations, attempt records, and exported public ID states are in the public bundle. The task materials remain private. Lab outcomes are descriptive; no official benchmark grade was assigned. Standard 1.2 records, measured fields, declared gaps, and missing-field data are included with the round.

Metadata

Round date: 2026-10-21 Label: DESCRIPTIVE Publication badge: DESCRIPTIVE; KEPT FOR AUDIT Recomputation status: OBSERVED SOURCE ONLY Why not VALID: DESCRIPTIVE_ONLY, PROTOCOL_DEVIATION, INCOMPLETE_CAPTURE — fresh-task confirmation, approximate execution, no official grades, and missing Standard capture fields declared below. STATUS: DESCRIPTIVE

Execution record

Lab build: 3bf295ef Kogen commit: b45ba32bacf26e2b17cb0bb81015ba56d27a4b0b Model and effort: the default builder and reviewer settings. Task IDs: subnet-ex and subnet-go. Harness commit: not recorded as a public Git commit; the execution build is identified above. Command: the experiment was run and exported in Lab before publication. Raw records: records.jsonl and the public bundle preserve attempt outcomes and configuration. The run scored 12 of 12 attempts, with six usable pairs of attempts, each comparing full and short on the same task and repetition, and used 1.93M input tokens of the 5M budget. All 12 review trees were approved unchanged and were the first green builds. The public bundle retains the frozen configuration, attempt outcomes, and public ID states.

What's missing and why

  • circumstances.cap_end (12 missing): The Lab export does not carry this Standard field. Boundary telemetry not retained. Reason: Boundary telemetry not retained (m08).
  • circumstances.cap_start (12 missing): The Lab export does not carry this Standard field. Boundary telemetry not retained. Reason: Boundary telemetry not retained (m08).
  • circumstances.concurrent_cells_end (12 missing): The Lab export does not carry this Standard field. Host-wide concurrent cell count was not captured. Reason: Host-wide concurrent cell count was not captured (m66).
  • circumstances.concurrent_cells_start (12 missing): The Lab export does not carry this Standard field. Host-wide concurrent cell count was not captured. Reason: Host-wide concurrent cell count was not captured (m66).
  • circumstances.dispatcher_id (12 missing): The Lab export does not carry this Standard field. Exact dispatcher revision is not present in the public receipt extract. Reason: Exact dispatcher revision is not present in the public receipt extract (m63).
  • circumstances.incidents (12 missing): The Lab export does not carry this Standard field. Per-cell incident receipt was not captured. Reason: Per-cell incident receipt was not captured (m78).
  • circumstances.load1_end (12 missing): The Lab export does not carry this Standard field. Host boundary load was not captured in the public round data. Reason: Host boundary load was not captured in the public round data (m65).
  • circumstances.load1_start (12 missing): The Lab export does not carry this Standard field. Host boundary load was not captured in the public round data. Reason: Host boundary load was not captured in the public round data (m65).
  • circumstances.load_samples (12 missing): The Lab export does not carry this Standard field. Timestamped host-wide load samples were not captured. Reason: Timestamped host-wide load samples were not captured (m93).
  • circumstances.queue (12 missing): The Lab export does not carry this Standard field. Queue receipt was not captured. Reason: Queue receipt was not captured (m91).
  • cost.accounting (12 missing): The Lab export does not carry this Standard field. Per-cell cost and pricing inputs are not present in the public round data. Reason: Per-cell cost and pricing inputs are not present in the public round data (m70).
  • cost.calculator_version (12 missing): The Lab export does not carry this Standard field. Cost calculator version not recorded. Reason: Cost calculator version not recorded (m61).
  • cost.long_context_reconciled (12 missing): The Lab export does not carry this Standard field. Boolean receipt not recorded. Reason: Boolean receipt not recorded (m07).
  • cost.price_table_version (12 missing): The Lab export does not carry this Standard field. Price table version not recorded. Reason: Price table version not recorded (m89).
  • cost.usd (12 missing): The Lab export does not carry this Standard field. Per-cell cost and pricing inputs are not present in the public round data. Reason: Per-cell cost and pricing inputs are not present in the public round data (m70).
  • effort.effective (12 missing): The Lab export does not carry this Standard field. Per-cell effective-effort receipt not published. Reason: Per-cell effective-effort receipt not published (m73).
  • effort.requested (12 missing): The Lab export does not carry this Standard field. Not recorded in available public metadata. Reason: Not recorded in available public metadata (m39).
  • effort.runner_requested (12 missing): The Lab export does not carry this Standard field. Not recorded in available public metadata. Reason: Not recorded in available public metadata (m39).
  • environment.account_class (12 missing): The Lab export does not carry this Standard field. No owner-approved class-only account receipt is available for the cell. Reason: No owner-approved class-only account receipt is available for the cell (m100).
  • environment.network.allowlist_hosts (12 missing): The Lab export does not carry this Standard field. Per-cell network allowlist not present in the public round data. Reason: Per-cell network allowlist not present in the public round data (m79).
  • environment.network.profile (12 missing): The Lab export does not carry this Standard field. Per-cell network profile not present in the public round data. Reason: Per-cell network profile not present in the public round data (m80).
  • environment.toolchains.erlang (12 missing): The Lab export does not carry this Standard field. Toolchain version not recorded. Reason: Toolchain version not recorded (m95).
  • environment.toolchains.other_inventory (12 missing): The Lab export does not carry this Standard field. Full per-cell toolchain inventory not recorded. Reason: Full per-cell toolchain inventory not recorded (m64).
  • environment.toolchains.ruby (12 missing): The Lab export does not carry this Standard field. Toolchain version not recorded. Reason: Toolchain version not recorded (m95).
  • environment.toolchains.rust (12 missing): The Lab export does not carry this Standard field. Toolchain version not recorded. Reason: Toolchain version not recorded (m95).
  • grade.grader (12 missing): The Lab export does not carry this Standard field. Per-cell grader software version is not in the public data. Reason: Per-cell grader software version is not in the public data (m77).
  • grade.timestamp (12 missing): The Lab export does not carry this Standard field. No official grade in the public snapshot. Reason: No official grade in the public snapshot (m32).
  • host.id (12 missing): The Lab export does not carry this Standard field. Not recorded in available public metadata. Reason: Not recorded in available public metadata (m39).
  • itt.class (12 missing): The Lab export does not carry this Standard field. No evidence-backed ITT classification. Reason: No evidence-backed ITT classification (m28).
  • itt.cohort (12 missing): The Lab export does not carry this Standard field. No evidence-backed ITT classification. Reason: No evidence-backed ITT classification (m28).
  • outcome (12 missing): The Lab export does not carry this Standard field. Not available for ungraded delivery. Reason: Not available for ungraded delivery (m38).
  • provenance.ledger_sha256 (12 missing): The Lab export does not carry this Standard field. Not recorded in available public metadata. Reason: Not recorded in available public metadata (m39).
  • sandbox.egress_allow (12 missing): The Lab export does not carry this Standard field. Per-cell egress allowlist is not present in the public round data. Reason: Per-cell egress allowlist is not present in the public round data (m75).
  • sandbox.egress_profile (12 missing): The Lab export does not carry this Standard field. Per-cell egress profile is not present in the public round data. Reason: Per-cell egress profile is not present in the public round data (m76).
  • sandbox.profile (12 missing): The Lab export does not carry this Standard field. Per-cell sandbox profile is not present in the public round data. Reason: Per-cell sandbox profile is not present in the public round data (m87).
  • sandbox.profile_sha256 (12 missing): The Lab export does not carry this Standard field. Per-cell sandbox profile fingerprint is not present in the public round data. Reason: Per-cell sandbox profile fingerprint is not present in the public round data (m86).
  • setup.adapter_harness_sha (12 missing): The Lab export does not carry this Standard field. Not recorded in available public metadata. Reason: Not recorded in available public metadata (m39).
  • setup.deps_source (12 missing): The Lab export does not carry this Standard field. Per-cell dependency source is not recorded. Reason: Per-cell dependency source is not recorded (m71).
  • setup.sandbox_mode (12 missing): The Lab export does not carry this Standard field. Per-cell sandbox mode is not present in the public round data. Reason: Per-cell sandbox mode is not present in the public round data (m85).
  • setup.sandbox_profile_sha256 (12 missing): The Lab export does not carry this Standard field. Per-cell sandbox fingerprint is not present in the public round data. Reason: Per-cell sandbox fingerprint is not present in the public round data (m84).
  • setup.task_base.hash (12 missing): The Lab export does not carry this Standard field. Original base commit/tree hash absent; fresh_base_commit is not a base hash. Reason: Original base commit/tree hash absent; fresh_base_commit is not a base hash (m42).
  • setup.task_base.kind (12 missing): The Lab export does not carry this Standard field. Original base revision type not recorded per cell. Reason: Original base revision type not recorded per cell (m43).
  • task.base_repo (12 missing): The Lab export does not carry this Standard field. Not recorded in available public metadata. Reason: Not recorded in available public metadata (m39).
  • task.base_revision.hash (12 missing): The Lab export does not carry this Standard field. Original base commit/tree hash absent; fresh_base_commit is not a base hash. Reason: Original base commit/tree hash absent; fresh_base_commit is not a base hash (m42).
  • task.base_revision.kind (12 missing): The Lab export does not carry this Standard field. Original base revision type not recorded per cell. Reason: Original base revision type not recorded per cell (m43).
  • timestamps.phases.develop.end_utc (12 missing): The Lab export does not carry this Standard field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (m88).
  • timestamps.phases.develop.start_utc (12 missing): The Lab export does not carry this Standard field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (m88).
  • timestamps.phases.gate.end_utc (12 missing): The Lab export does not carry this Standard field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (m88).
  • timestamps.phases.gate.start_utc (12 missing): The Lab export does not carry this Standard field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (m88).
  • timestamps.phases.grade.end_utc (12 missing): The Lab export does not carry this Standard field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (m88).
  • timestamps.phases.grade.start_utc (12 missing): The Lab export does not carry this Standard field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (m88).
  • timestamps.phases.plan.end_utc (12 missing): The Lab export does not carry this Standard field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (m88).
  • timestamps.phases.plan.start_utc (12 missing): The Lab export does not carry this Standard field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (m88).
  • timestamps.phases.review.end_utc (12 missing): The Lab export does not carry this Standard field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (m88).
  • timestamps.phases.review.start_utc (12 missing): The Lab export does not carry this Standard field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (m88).
  • timestamps.phases.setup.end_utc (12 missing): The Lab export does not carry this Standard field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (m88).
  • timestamps.phases.setup.start_utc (12 missing): The Lab export does not carry this Standard field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (m88).
  • timestamps.phases.shape.end_utc (12 missing): The Lab export does not carry this Standard field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (m88).
  • timestamps.phases.shape.start_utc (12 missing): The Lab export does not carry this Standard field. Phase timestamp not present in the public per-cell data. Reason: Phase timestamp not present in the public per-cell data (m88).
  • timing.phases_s.gate (12 missing): The Lab export does not carry this Standard field. Phase wall not emitted or not separable. Reason: Phase wall not emitted or not separable (m45).
  • timing.phases_s.setup (12 missing): The Lab export does not carry this Standard field. Phase wall not emitted or not separable. Reason: Phase wall not emitted or not separable (m45).
  • timing.timeout_cap_s (12 missing): The Lab export does not carry this Standard field. Timeout receipt unavailable. Reason: Timeout receipt unavailable (m53).
  • tools.grader (12 missing): The Lab export does not carry this Standard field. Per-cell grader software version is not in the public data. Reason: Per-cell grader software version is not in the public data (m77).
  • tools.runner (12 missing): The Lab export does not carry this Standard field. Per-cell runner version not recorded in the public round data. Reason: Per-cell runner version not recorded in the public round data (m83).
  • tools.toolchains.erlang (12 missing): The Lab export does not carry this Standard field. Toolchain version not recorded. Reason: Toolchain version not recorded (m95).
  • tools.toolchains.other_inventory (12 missing): The Lab export does not carry this Standard field. Full per-cell toolchain inventory not recorded. Reason: Full per-cell toolchain inventory not recorded (m64).
  • tools.toolchains.ruby (12 missing): The Lab export does not carry this Standard field. Toolchain version not recorded. Reason: Toolchain version not recorded (m95).
  • tools.toolchains.rust (12 missing): The Lab export does not carry this Standard field. Toolchain version not recorded. Reason: Toolchain version not recorded (m95).

Captured run records

Standard-schema records assigned to this round in the indexed snapshot.

No per-round file is listed. Check the run-record index for the complete partition list.

Reproduction inventory

Published analysis replay and full experiment replay are reported separately.

Replay type
analysis-only
Script
No per-round analysis script is published.
Inputs
Full execution replay
Unavailable
Scope
Public bundles and records preserve observed Lab outcomes and configuration; model execution cannot be replayed from this repository snapshot.

View the complete per-round reproduction inventory · Repository reproduction guide