idx=5: freeze (18 records) — THIRD AMENDMENT TO MASTER LEASE, no parser changes#78
idx=5: freeze (18 records) — THIRD AMENDMENT TO MASTER LEASE, no parser changes#78arthrod wants to merge 1 commit into
Conversation
…der existing parser
Round-2/3 subdoc consolidation logic (title L1 + body L2 with +1 penalty)
already handles this idx cleanly without any new parser changes:
- Pre-round-2 survey: 279 records (L1=261, L2=17) — EXHIBIT B legal
descriptions exploded into 200+ L1 LOT/TRACT/PARCEL records.
- Current parser output: 18 records (L0=1, L1=10, L2=7) — EXHIBIT B
header at L1, full body consolidated into one L2 record per subdoc
rubric.
- Reconstruction: word_coverage=99.6%, char_ratio=99.9% (well above
the 90% bar).
Structure produced for idx=5:
L0 "THIRD AMENDMENT TO MASTER LEASE" (title)
L1 preamble + WITNESSETH/WHEREAS recitals
L1 4 Articles (I/II/III/IV) with L2 numbered N.M sections
L1 IN WITNESS WHEREOF signature block (single doc2dict node)
L1 "EXHIBIT B LEGAL DESCRIPTIONS" subdoc header
L2 EXHIBIT B body (242k chars of legal property descriptions)
L1 trailing "Schedule 1.1" bare-identifier subdoc reference
All 6 frozen idxs (0/1/2/3/4/5) pass regression.
|
Mention Blocks like a regular teammate with your question or request: @blocks review this pull request Run |
![sourcery-ai[bot]](https://avatars.githubusercontent.com/in/48477?s=60&v=4){kind=small}
Qodo reviews are paused for this user.Troubleshooting steps vary by plan Learn more → On a Teams plan? Using GitHub Enterprise Server, GitLab Self-Managed, or Bitbucket Data Center? |
|
CodeAnt AI is reviewing your PR. |
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Organization UI Review profile: ASSERTIVE Plan: Pro Run ID: 📒 Files selected for processing (2)
📜 Recent review details🧰 Additional context used🔍 Remote MCPThe repository isn't yet indexed in DeepWiki. Let me search for related documentation using other approaches and gather context about the document being processed.## Summary of Additional Context Found Based on my research, I've gathered the following relevant information to supplement the pull request review: Document DetailsThe THIRD AMENDMENT TO MASTER LEASE is dated March 24, 2017, between Gold Merger Sub, LLC (landlord) and Pinnacle MLS, LLC (tenant), following a merger agreement dated July 20, 2015, between Pinnacle Entertainment, Gaming and Leisure Properties, Inc. (GLPI), and Pinnacle merged into the landlord on April 28, 2016. Real Property Consolidation ContextThe amendment addresses property acquisitions, including quitclaim deeds for Pinnacle Real Property located in Vicksburg, Mississippi, with portions added via additional deeds dated to the amendment's effective date. The "EXHIBIT B LEGAL DESCRIPTIONS" mentioned in the PR—which comprises approximately 242 KB of legal property descriptions and consolidates into a single L2 subdoc—represents these extensive real property scheduling requirements. Historical Transaction ContextIn April 2016, Pinnacle made a strategic sale-leaseback of the majority of its real estate assets to GLPI (a real estate investment trust). This Third Amendment (March 24, 2017) was subsequently referenced in later lease arrangements, including in a Lease Commitment and Rent Allocation Agreement that addressed facility divisions and rent allocation following corporate restructuring. Parsing EfficiencyThe PR's achievement of 99.6% word coverage and 99.9% character reconstruction ratio with only 18 records (down from 279 pre-round-2) reflects the parser's effectiveness in handling complex legal documents with extensive exhibits. The consolidation of EXHIBIT B into a single L2 record is a direct consequence of the real property scheduling density in master lease amendments of this type. [::DeepWiki::]], [::web_search::] 🔇 Additional comments (1)
📝 WalkthroughSummary by CodeRabbit
WalkthroughThis PR updates the auto-parse level freeze state file by expanding the frozen indices array from ChangesLevel freeze state progression
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~2 minutes Possibly related PRs
Suggested labels
Poem
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. Comment |
codeant-ai
Bot
added
the
size:S
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
|
CodeAnt AI finished reviewing your PR. |
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request updates the state.json file to include index 5 in the frozen list and adds a corresponding history entry for the freeze action. Review feedback highlights that the current_idx should be advanced to 6 to maintain state consistency and prevent accidental overwrites. Additionally, there are concerns regarding structural inaccuracies and footer artifacts in the frozen data for index 5 that should be addressed in the parser to ensure a high-quality baseline.
| 3, | ||
| 4 | ||
| 4, | ||
| 5 |
There was a problem hiding this comment.
The current_idx (line 2) remains at 0 despite freezing up to idx=5. In this workflow, it is recommended to advance current_idx to 6 to reflect the progress and ensure that subsequent runs of the loop scripts (like freeze.py or advance.py) default to the correct next document. This prevents accidental overwrites of earlier indices.
| { | ||
| "ts": "2026-05-17T06:18:39", | ||
| "action": "freeze", | ||
| "idx": 5, | ||
| "n_records": 18 | ||
| } |
There was a problem hiding this comment.
The frozen output for idx=5 contains a structural inconsistency where 'TRACT FIFTEEN' (order 5) is assigned to Level 1, despite being content within Section 1.1(a) (Level 2). Additionally, order 17 appears to be a trailing footer artifact ('Ex. B-98') that should ideally be dropped per the rubric. While these are noted as 'quirks' in the PR description, freezing them into the golden baseline reduces the structural accuracy of the regression set. Consider if these can be addressed in the parser to maintain a cleaner baseline.
|
Triage agent — PR #78 comment review (read-only pass, no code changes) 2 inline comments reviewed:
NEED-DISCUSSION (1): idx=5 freeze — TRACT FIFTEEN level assignment and trailing footer in Triage only — no code changes made this round. |
1 participant
User description
Summary
Sixth stacked PR. Adds idx=5 (THIRD AMENDMENT TO MASTER LEASE between Pinnacle Entertainment and Gaming and Leisure Properties, March 24, 2017) as the sixth verified frozen baseline on top of idx=4 (PR #77).
No parser changes needed. The round-2/3 subdoc consolidation logic (title-as-root + +1 subdoc penalty) already handles this agreement type cleanly. This PR is freeze-only.
Verified output for idx=5
{L0:1, L1:10, L2:7}Top-level structure
Why this is significant
idx=5 was the stress test for the round-2 subdoc consolidation logic. The pre-round-2 parser exploded EXHIBIT B's 200+ TRACT/LOT/PARCEL legal property descriptions into separate L1 records, ballooning the freeze to 279 records and burying the main agreement structure. Round-2's
_consolidate_real_subdocs+ sig-page natural grouping correctly identifies EXHIBIT B as a real subdoc with a substantive body, consolidates the body to one L2 record (with +1 subdoc penalty), and preserves the main agreement's 4 Articles + sig area at L1.This validates the round-2 design against a fundamentally different subdoc type (legal property descriptions, not press releases or
[***]redactions).Known minor quirks (non-blocking; inspector concurs)
Test plan
uv run scripts/parse_doc2dict_with_config.py --limit 6 --no-truncate --output-dir data/auto_parseexits 0 withok 6uv run scripts/level_loop/freeze.py 5 --forcereports word_coverage ≥ 90% (99.6%)uv run scripts/level_loop/regress.pyreports all 6 frozen idxs OKSource
http://www.sec.gov/Archives/edgar/data/1656239/000165623917000033/d363017dex101.htm
🤖 Generated with Claude Code
CodeAnt-AI Description
Freeze the idx=5 master lease baseline with verified parser output
What Changed
Impact
✅ More regression coverage for master lease documents✅ Fewer breakages on repeated freeze checks✅ Safer baseline comparisons for frozen documents🔄 Retrigger CodeAnt AI Review
💡 Usage Guide
Checking Your Pull Request
Every time you make a pull request, our system automatically looks through it. We check for security issues, mistakes in how you're setting up your infrastructure, and common code problems. We do this to make sure your changes are solid and won't cause any trouble later.
Talking to CodeAnt AI
Got a question or need a hand with something in your pull request? You can easily get in touch with CodeAnt AI right here. Just type the following in a comment on your pull request, and replace "Your question here" with whatever you want to ask:
This lets you have a chat with CodeAnt AI about your pull request, making it easier to understand and improve your code.
Example
Preserve Org Learnings with CodeAnt
You can record team preferences so CodeAnt AI applies them in future reviews. Reply directly to the specific CodeAnt AI suggestion (in the same thread) and replace "Your feedback here" with your input:
This helps CodeAnt AI learn and adapt to your team's coding style and standards.
Example
Retrigger review
Ask CodeAnt AI to review the PR again, by typing:
Check Your Repository Health
To analyze the health of your code repository, visit our dashboard at https://app.codeant.ai. This tool helps you identify potential issues and areas for improvement in your codebase, ensuring your repository maintains high standards of code health.