Published timeline
153.33/160 avg NSS
6 episodes from timeline_60069004963d4c3e82610ec4a67d28c4. This score is separate from the fair-comparison agent run below.
Evaluation & Artifact Library
A browsable evidence package for professors and students. It includes the currently published timeline, its evaluations, the shared HBO/Redux comparison, source treatments, and system ablations.
Original HBO Season 8
143.17/160 avg NSS
6 episodes, scored with the shared fair-comparison harness.
GoT Season 8 Redux
119.8/160 avg NSS
10 episodes, scored with the shared fair-comparison harness.
Latest agent GenAI run (timeline_ee8b0736bfce4fe7b4fea0913908025e)
128.0/160 avg NSS
6 episodes, scored with the shared fair-comparison harness.
Important: the fair-comparison agent candidate is a different timeline from the currently published screenplay timeline. Both are included and labeled so the results are not conflated.
Timeline 60069004963d4c3e82610ec4a67d28c4
23 inspectable artifact(s)
- plot_board.jsonJSON artifact
- plot_board.mdMD artifact
- plot_board_graph.jsonJSON artifact
- s8e1.mdMD artifact
- s8e2.mdMD artifact
- s8e3.mdMD artifact
- s8e4.mdMD artifact
- s8e5.mdMD artifact
- s8e6.mdMD artifact
- s8e6_script.jsonJSON artifact
- s8e6_script.txtTXT artifact
- s8e6_script_images.jsonJSON artifact
- s8e6_script_memory_patched.jsonJSON artifact
- s8e6_script_memory_patched.txtTXT artifact
- s8e6_script_memory_patched_images.jsonJSON artifact
- s8e6_script_regenerated.jsonJSON artifact
- s8e6_script_regenerated.txtTXT artifact
- s8e6_script_regenerated_v2.jsonJSON artifact
- s8e6_script_regenerated_v2.txtTXT artifact
- season8_full.mdMD artifact
- season8_nss.jsonJSON artifact
- season8_plan.mdMD artifact
- season8_summary.jsonJSON artifact
Final Presentation Nss Reevaluation
5 inspectable artifact(s)
Original S8 Treatments
14 inspectable artifact(s)
- s8e1.jsonJSON artifact
- s8e1.mdMD artifact
- s8e2.jsonJSON artifact
- s8e2.mdMD artifact
- s8e3.jsonJSON artifact
- s8e3.mdMD artifact
- s8e4.jsonJSON artifact
- s8e4.mdMD artifact
- s8e5.jsonJSON artifact
- s8e5.mdMD artifact
- s8e6.jsonJSON artifact
- s8e6.mdMD artifact
- season8_treatments_full.mdMD artifact
- season8_treatments_summary.jsonJSON artifact
Treatments Fair
22 inspectable artifact(s)
- e01.jsonJSON artifact
- e01.mdMD artifact
- e02.jsonJSON artifact
- e02.mdMD artifact
- e03.jsonJSON artifact
- e03.mdMD artifact
- e04.jsonJSON artifact
- e04.mdMD artifact
- e05.jsonJSON artifact
- e05.mdMD artifact
- e06.jsonJSON artifact
- e06.mdMD artifact
- e07.jsonJSON artifact
- e07.mdMD artifact
- e08.jsonJSON artifact
- e08.mdMD artifact
- e09.jsonJSON artifact
- e09.mdMD artifact
- e10.jsonJSON artifact
- e10.mdMD artifact
- redux_treatments_full.mdMD artifact
- redux_treatments_summary.jsonJSON artifact
Ablation 20260601 050013
64 inspectable artifact(s)
- ablation_plan.jsonJSON artifact
- ablation_results.jsonJSON artifact
- ablation_summary.mdMD artifact
- baseline/llm_only_baseline/s8e1.mdMD artifact
- baseline/llm_only_baseline/s8e2.mdMD artifact
- baseline/llm_only_baseline/s8e3.mdMD artifact
- baseline/llm_only_baseline/s8e4.mdMD artifact
- baseline/llm_only_baseline/s8e5.mdMD artifact
- baseline/llm_only_baseline/s8e6.mdMD artifact
- baseline/llm_only_baseline/season8_full.mdMD artifact
- baseline/llm_only_baseline/season8_nss.jsonJSON artifact
- baseline/llm_only_baseline/season8_summary.jsonJSON artifact
- full_hybrid_graph_memory/timeline_e7afa18865bb4123a22efdfd93667da5/plot_board.jsonJSON artifact
- full_hybrid_graph_memory/timeline_e7afa18865bb4123a22efdfd93667da5/plot_board.mdMD artifact
- full_hybrid_graph_memory/timeline_e7afa18865bb4123a22efdfd93667da5/plot_board_graph.jsonJSON artifact
- full_hybrid_graph_memory/timeline_e7afa18865bb4123a22efdfd93667da5/s8e1.mdMD artifact
- full_hybrid_graph_memory/timeline_e7afa18865bb4123a22efdfd93667da5/s8e2.mdMD artifact
- full_hybrid_graph_memory/timeline_e7afa18865bb4123a22efdfd93667da5/s8e3.mdMD artifact
- full_hybrid_graph_memory/timeline_e7afa18865bb4123a22efdfd93667da5/s8e4.mdMD artifact
- full_hybrid_graph_memory/timeline_e7afa18865bb4123a22efdfd93667da5/s8e5.mdMD artifact
- full_hybrid_graph_memory/timeline_e7afa18865bb4123a22efdfd93667da5/s8e6.mdMD artifact
- full_hybrid_graph_memory/timeline_e7afa18865bb4123a22efdfd93667da5/season8_full.mdMD artifact
- full_hybrid_graph_memory/timeline_e7afa18865bb4123a22efdfd93667da5/season8_nss.jsonJSON artifact
- full_hybrid_graph_memory/timeline_e7afa18865bb4123a22efdfd93667da5/season8_plan.mdMD artifact
- full_hybrid_graph_memory/timeline_e7afa18865bb4123a22efdfd93667da5/season8_summary.jsonJSON artifact
- graphrag_only_memory/timeline_1c53902b36784c4a90dbcb247359c39b/plot_board.jsonJSON artifact
- graphrag_only_memory/timeline_1c53902b36784c4a90dbcb247359c39b/plot_board.mdMD artifact
- graphrag_only_memory/timeline_1c53902b36784c4a90dbcb247359c39b/plot_board_graph.jsonJSON artifact
- graphrag_only_memory/timeline_1c53902b36784c4a90dbcb247359c39b/s8e1.mdMD artifact
- graphrag_only_memory/timeline_1c53902b36784c4a90dbcb247359c39b/s8e2.mdMD artifact
- graphrag_only_memory/timeline_1c53902b36784c4a90dbcb247359c39b/s8e3.mdMD artifact
- graphrag_only_memory/timeline_1c53902b36784c4a90dbcb247359c39b/s8e4.mdMD artifact
- graphrag_only_memory/timeline_1c53902b36784c4a90dbcb247359c39b/s8e5.mdMD artifact
- graphrag_only_memory/timeline_1c53902b36784c4a90dbcb247359c39b/s8e6.mdMD artifact
- graphrag_only_memory/timeline_1c53902b36784c4a90dbcb247359c39b/season8_full.mdMD artifact
- graphrag_only_memory/timeline_1c53902b36784c4a90dbcb247359c39b/season8_nss.jsonJSON artifact
- graphrag_only_memory/timeline_1c53902b36784c4a90dbcb247359c39b/season8_plan.mdMD artifact
- graphrag_only_memory/timeline_1c53902b36784c4a90dbcb247359c39b/season8_summary.jsonJSON artifact
- no_memory/timeline_e45352d4e75a44e598615ff50be1f510/plot_board.jsonJSON artifact
- no_memory/timeline_e45352d4e75a44e598615ff50be1f510/plot_board.mdMD artifact
- no_memory/timeline_e45352d4e75a44e598615ff50be1f510/plot_board_graph.jsonJSON artifact
- no_memory/timeline_e45352d4e75a44e598615ff50be1f510/s8e1.mdMD artifact
- no_memory/timeline_e45352d4e75a44e598615ff50be1f510/s8e2.mdMD artifact
- no_memory/timeline_e45352d4e75a44e598615ff50be1f510/s8e3.mdMD artifact
- no_memory/timeline_e45352d4e75a44e598615ff50be1f510/s8e4.mdMD artifact
- no_memory/timeline_e45352d4e75a44e598615ff50be1f510/s8e5.mdMD artifact
- no_memory/timeline_e45352d4e75a44e598615ff50be1f510/s8e6.mdMD artifact
- no_memory/timeline_e45352d4e75a44e598615ff50be1f510/season8_full.mdMD artifact
- no_memory/timeline_e45352d4e75a44e598615ff50be1f510/season8_nss.jsonJSON artifact
- no_memory/timeline_e45352d4e75a44e598615ff50be1f510/season8_plan.mdMD artifact
- no_memory/timeline_e45352d4e75a44e598615ff50be1f510/season8_summary.jsonJSON artifact
- vector_only_memory/timeline_d87565ff4fcb4a65ab18a6b40ee98465/plot_board.jsonJSON artifact
- vector_only_memory/timeline_d87565ff4fcb4a65ab18a6b40ee98465/plot_board.mdMD artifact
- vector_only_memory/timeline_d87565ff4fcb4a65ab18a6b40ee98465/plot_board_graph.jsonJSON artifact
- vector_only_memory/timeline_d87565ff4fcb4a65ab18a6b40ee98465/s8e1.mdMD artifact
- vector_only_memory/timeline_d87565ff4fcb4a65ab18a6b40ee98465/s8e2.mdMD artifact
- vector_only_memory/timeline_d87565ff4fcb4a65ab18a6b40ee98465/s8e3.mdMD artifact
- vector_only_memory/timeline_d87565ff4fcb4a65ab18a6b40ee98465/s8e4.mdMD artifact
- vector_only_memory/timeline_d87565ff4fcb4a65ab18a6b40ee98465/s8e5.mdMD artifact
- vector_only_memory/timeline_d87565ff4fcb4a65ab18a6b40ee98465/s8e6.mdMD artifact
- vector_only_memory/timeline_d87565ff4fcb4a65ab18a6b40ee98465/season8_full.mdMD artifact
- vector_only_memory/timeline_d87565ff4fcb4a65ab18a6b40ee98465/season8_nss.jsonJSON artifact
- vector_only_memory/timeline_d87565ff4fcb4a65ab18a6b40ee98465/season8_plan.mdMD artifact
- vector_only_memory/timeline_d87565ff4fcb4a65ab18a6b40ee98465/season8_summary.jsonJSON artifact