Current deep specialist encoder leaderboard
This repository contains the complete, checksum-bound JAX checkpoint set
referenced by the canonical configs/train_leaderboard.json snapshot.
- Source code Git commit:
1d9319dcd7ee2154ec239f74c12cfba1e4f68c75 - Packaged worktree board Git blob:
40c01441600baaedc909affc8a88f8b10d40c128 - Board blob at source commit:
40c01441600baaedc909affc8a88f8b10d40c128 - Packaged board matches source commit:
true - Source board SHA-256:
e48b67dbc74216a1b8f401f5ddced303f1828f1f0b0c2d46d33ad4e0e69fe822 - Board members / unique deck hashes: 26 / 26
- Unique checkpoint directories: 26
- Direct deck-trained members: 26
Every payload is a complete entity_interaction_deep or
entity_interaction_deep_v2 stateless_mlp,
specialist_rule_state_v1, public-event-window-0 checkpoint. The archive
retains every file in each referenced checkpoint directory and deduplicates
directories reused by more than one board member.
Download, verify, and extract
hf download TCGBaselines/deep_encoders \
deep_encoders_train_leaderboard_current.tar.gz deep_encoders_train_leaderboard_current.tar.gz.sha256 --local-dir .
sha256sum -c deep_encoders_train_leaderboard_current.tar.gz.sha256
tar -xzf deep_encoders_train_leaderboard_current.tar.gz
sha256sum -c deep_encoders_bundle_checksums.sha256
Extract at the ladderboard_elo repository root. This creates the exact
checkpoints/<id>/ paths plus configs/train_leaderboard.json,
MODELS.json, DEEP_ENCODERS_BUNDLE_README.md, and the internal checksum
manifest. Existing files at those paths are replaced by normal tar extraction,
so use a clean checkout or back up local changes first.
Cross-deck actor reuse
board_deck_hash and checkpoint_trained_deck_hash are separate fields in
MODELS.json. The following entries intentionally run an actor on a target
deck other than the deck recorded by its immutable checkpoint manifest:
| Member | Board deck | Checkpoint-trained deck | Relation |
|---|
These are valid frozen actor opponents, but their stored critics are not declared compatible with the retargeted deck. Use actor-only initialization and a fresh/warm-started target-deck critic unless newer deck-specific evidence explicitly says otherwise. The immutable checkpoint manifests are preserved rather than rewritten to conceal training provenance.
Current board members
| Rank | Elo | Member | Board deck | Checkpoint relation |
|---|---|---|---|---|
| 1 | 1048.6 | lopbunny_dudunsparce_phase2_u000443_43b70a |
04689d80f09215b6 |
direct |
| 2 | 999.9 | cornerstone_ogerpon_crustle_mega_kangaskhan_manual_v2opp_even_u000100_7046cc |
e2194d835b594811 |
direct |
| 3 | 959.1 | mega_lucario_phase3_best_u000200_c57fbe |
2796018749350c2b |
direct |
| 4 | 946.2 | deep_mega_starmie_cinderace_phase2_u000196_db88e4 |
00bbd953f688a18b |
direct |
| 5 | 945.2 | mega_lopunny_froslass_phase3_best_u000240_e66e1f |
07818719c2c434ef |
direct |
| 6 | 942.7 | blaziken_dragapult_deep_vrpo_latest_u000420_966f71 |
362eca0b8a31393e |
direct |
| 7 | 942.0 | archaludon_cinderace_phase3_best_u000240_107c09 |
82ce67869190aefd |
direct |
| 8 | 940.7 | festival_lead_manual_v2opp_even_u000200_0afdbe |
07d4c9cb1496190b |
direct |
| 9 | 940.3 | hop_trevenant_dudunsparce_deep_vrpo_final_u000740 |
850f423d1fe52b95 |
direct |
| 10 | 938.9 | tr_honchkrow_porygon2_phase3_best_u000280_427778 |
d71c667d3ed25c89 |
direct |
| 11 | 937.3 | alakazam_dudunsparce_phase3_best_u000160_96ab07 |
01dc0c8ee2afb65c |
direct |
| 12 | 927.3 | starmie_froslass_phase2_u000925_efff34 |
0e6ead751f2c6e11 |
direct |
| 13 | 927.0 | tr_mewtwo_spidops_deep_vrpo_u000480_620d59 |
ec38a9f1af1ad0f3 |
direct |
| 14 | 919.9 | dragapult_dusknoir_phase1_u000220_8e22f9 |
f9f5dc7482675db1 |
direct |
| 15 | 916.8 | lucario_dunsparce_deep_vrpo_continuation_u000760_1c1db6 |
8e33dea1649f0c39 |
direct |
| 16 | 913.2 | crustle_kangaskhan_deep_ppo_phase2_u000121_b43489 |
2959276a9ee66220 |
direct |
| 17 | 893.4 | prague_dragapult_exact_cont_u000190_15a109 |
079d6dfeb312242b |
direct |
| 18 | 877.1 | grimmsnarl_froslass_phase3_best_u000280_c63b55 |
2a9b67c9561fbdd4 |
direct |
| 19 | 876.1 | clefairy_hammer_dragapult_manual_v2opp_u000310_faa5aa |
c63916cd72ec8788 |
direct |
| 20 | 865.4 | festival_lead_arian_improved_manual_v2opp_u000210_b67ce8 |
eb27f50f2a0327ea |
direct |
| 21 | 862.3 | cynthia_garchomp_phase2_u000200_bbbade |
7218e9812dd0ef05 |
direct |
| 22 | 853.1 | dragapult_dusknoir_cont_u000130_ccff55 |
a9358b44a6c7aa2e |
direct |
| 23 | 816.2 | mega_abomasnow_kyogre_deep_vrpo_u000400_774a80 |
b5a0ec95d155c444 |
direct |
| 24 | 800.0 | raging_bolt_ba07_phase1_best_u000300_e5f767 |
ba07b48dc438899f |
direct |
| 25 | 742.5 | hydrapple_ogerpon_phase3_best_u000280_726cff |
efe238b2a77e2d1f |
direct |
| 26 | 0.0 | okidogi_barbaracle_deep_vrpo_latest_u000280_d7bc4d |
b15fcfd19acc20ed |
direct |
These are game-playing specialist policies, not Transformers models or a
hosted inference endpoint. Elo calibration and provenance remain in the
shipped board and MODELS.json.