{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/init-model-from-pretrained","entry":"init_model_from_pretrained","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":28,"n_papers_ran":16,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":7,"n_samples_ran":4,"n_samples_fingerprinted":0,"n_places":29,"n_places_pointer_only":9,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":4,"unverified":3},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2606.14259","paper":"/paper/arxiv-2606-14259","title":"Beyond a Single Explanation of the Adam-SGD Gap","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"LiamMa/GRIT","path":"grit/finetuning.py","file_url":"https://github.com/LiamMa/GRIT/blob/HEAD/grit/finetuning.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9e4db46ba20af98e","mcp_get_code":{"code_sha256":"9e4db46ba20af98e"}},{"arxiv_id":"2510.21267","paper":"/paper/arxiv-2510-21267","title":"Relieving the Over-Aggregating Effect in Graph Transformers","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"sunjss/over-aggregating","path":"graphgps/finetuning.py","file_url":"https://github.com/sunjss/over-aggregating/blob/HEAD/graphgps/finetuning.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9e4db46ba20af98e","mcp_get_code":{"code_sha256":"9e4db46ba20af98e"}},{"arxiv_id":"2502.09263","paper":"/paper/unlocking-the-potential-of-classic-gnns-for","title":"Unlocking the Potential of Classic GNNs for Graph-level Tasks: Simple Architectures Meet Excellence","date":"2025-02-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LUOyk1999/GNNPlus","path":"GNNPlus/finetuning.py","file_url":"https://github.com/LUOyk1999/GNNPlus/blob/HEAD/GNNPlus/finetuning.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3db4474abe13fdee","mcp_get_code":{"code_sha256":"3db4474abe13fdee"}},{"arxiv_id":"2411.12732","paper":"/paper/benchmarking-positional-encodings-for-gnns","title":"Benchmarking Positional Encodings for GNNs and Graph Transformers","date":"2024-11-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ETH-DISCO/Benchmarking-PEs","path":"grit/finetuning.py","file_url":"https://github.com/ETH-DISCO/Benchmarking-PEs/blob/HEAD/grit/finetuning.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9e4db46ba20af98e","mcp_get_code":{"code_sha256":"9e4db46ba20af98e"}},{"arxiv_id":"2406.15852","paper":"/paper/next-level-message-passing-with-hierarchical","title":"Next Level Message-Passing with Hierarchical Support Graphs","date":"2024-06-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"carlosinator/support-graphs","path":"graphgps/finetuning.py","file_url":"https://github.com/carlosinator/support-graphs/blob/HEAD/graphgps/finetuning.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3db4474abe13fdee","mcp_get_code":{"code_sha256":"3db4474abe13fdee"}},{"arxiv_id":"2406.05815","paper":"/paper/what-can-we-learn-from-state-space-models-for","title":"What Can We Learn from State Space Models for Machine Learning on Graphs?","date":"2024-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"graph-com/gssc","path":"gssc/finetuning.py","file_url":"https://github.com/graph-com/gssc/blob/HEAD/gssc/finetuning.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9e4db46ba20af98e","mcp_get_code":{"code_sha256":"9e4db46ba20af98e"}},{"arxiv_id":"2405.21061","paper":"/paper/graph-external-attention-enhanced-transformer","title":"Graph External Attention Enhanced Transformer","date":"2024-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"icm1018/GEAET","path":"GEAET/finetuning.py","file_url":"https://github.com/icm1018/GEAET/blob/HEAD/GEAET/finetuning.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3db4474abe13fdee","mcp_get_code":{"code_sha256":"3db4474abe13fdee"}},{"arxiv_id":"2405.20543","paper":"/paper/towards-a-general-gnn-framework-for","title":"Towards a General Recipe for Combinatorial Optimization with Multi-Filter GNNs","date":"2024-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wenkelf/copt","path":"graphgym/finetuning.py","file_url":"https://github.com/wenkelf/copt/blob/HEAD/graphgym/finetuning.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9a4410b8a6c0cc47","mcp_get_code":{"code_sha256":"9a4410b8a6c0cc47"}},{"arxiv_id":"2405.19121","paper":"/paper/spatio-spectral-graph-neural-networks","title":"Spatio-Spectral Graph Neural Networks","date":"2024-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sigeisler/s2gnn","path":"graphgps/finetuning.py","file_url":"https://github.com/sigeisler/s2gnn/blob/HEAD/graphgps/finetuning.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"897f9d9194e1b336","mcp_get_code":{"code_sha256":"897f9d9194e1b336"}},{"arxiv_id":"2405.16435","paper":"/paper/structure-aware-semantic-node-identifiers-for","title":"Node Identifiers: Compact, Discrete Representations for Efficient Graph Learning","date":"2024-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LUOyk1999/NodeID","path":"SL/Graph_Classification/graphgps/finetuning.py","file_url":"https://github.com/LUOyk1999/NodeID/blob/HEAD/SL/Graph_Classification/graphgps/finetuning.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3db4474abe13fdee","mcp_get_code":{"code_sha256":"3db4474abe13fdee"}},{"arxiv_id":"2405.13806","paper":"/paper/advancing-graph-convolutional-networks-via","title":"A General Graph Spectral Wavelet Convolution via Chebyshev Order Decomposition","date":"2024-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liun-online/WaveGC","path":"WaveGC_graph/graphgps/finetuning.py","file_url":"https://github.com/liun-online/WaveGC/blob/HEAD/WaveGC_graph/graphgps/finetuning.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3db4474abe13fdee","mcp_get_code":{"code_sha256":"3db4474abe13fdee"}},{"arxiv_id":"2405.11951","paper":"/paper/distinguished-in-uniform-self-attention-vs","title":"Distinguished In Uniform: Self Attention Vs. Virtual Nodes","date":"2024-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"toenshoff/vn-vs-gt","path":"graphgps/finetuning.py","file_url":"https://github.com/toenshoff/vn-vs-gt/blob/HEAD/graphgps/finetuning.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3db4474abe13fdee","mcp_get_code":{"code_sha256":"3db4474abe13fdee"}},{"arxiv_id":"2404.13604","paper":"/paper/ckgconv-general-graph-convolution-with","title":"CKGConv: General Graph Convolution with Continuous Kernels","date":"2024-04-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"networkslab/CKGConv","path":"ckgconv/finetuning.py","file_url":"https://github.com/networkslab/CKGConv/blob/HEAD/ckgconv/finetuning.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"309b367fdc9f4994","mcp_get_code":{"code_sha256":"309b367fdc9f4994"}},{"arxiv_id":"2404.03380","paper":"/paper/on-the-theoretical-expressive-power-and-the","title":"On the Theoretical Expressive Power and the Design Space of Higher-Order Graph Transformers","date":"2024-04-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhouc20/k-transformer","path":"graphgps/finetuning.py","file_url":"https://github.com/zhouc20/k-transformer/blob/HEAD/graphgps/finetuning.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9a4410b8a6c0cc47","mcp_get_code":{"code_sha256":"9a4410b8a6c0cc47"}},{"arxiv_id":"2402.14202","paper":"/paper/comparing-graph-transformers-via-positional","title":"Comparing Graph Transformers via Positional Encodings","date":"2024-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"blackmit/comparing_graph_transformers_via_positional_encodings","path":"graphgps/finetuning.py","file_url":"https://github.com/blackmit/comparing_graph_transformers_via_positional_encodings/blob/HEAD/graphgps/finetuning.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3db4474abe13fdee","mcp_get_code":{"code_sha256":"3db4474abe13fdee"}},{"arxiv_id":"2402.02518","paper":"/paper/latent-graph-diffusion-a-unified-framework","title":"Unifying Generation and Prediction on Graphs with Latent Graph Diffusion","date":"2024-02-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhouc20/latentgraphdiffusion","path":"lgd/finetuning.py","file_url":"https://github.com/zhouc20/latentgraphdiffusion/blob/HEAD/lgd/finetuning.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b8ea7231e959f164","mcp_get_code":{"code_sha256":"b8ea7231e959f164"}},{"arxiv_id":"2402.02005","paper":"/paper/topology-informed-graph-transformer","title":"Topology-Informed Graph Transformer","date":"2024-02-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leemingo/tigt","path":"graphgps/finetuning.py","file_url":"https://github.com/leemingo/tigt/blob/HEAD/graphgps/finetuning.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3db4474abe13fdee","mcp_get_code":{"code_sha256":"3db4474abe13fdee"}},{"arxiv_id":"2312.04234","paper":"/paper/graph-convolutions-enrich-the-self-attention","title":"Graph Convolutions Enrich the Self-Attention in Transformers!","date":"2023-12-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rampasek/GraphGPS","path":"graphgps/finetuning.py","file_url":"https://github.com/rampasek/GraphGPS/blob/HEAD/graphgps/finetuning.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3db4474abe13fdee","mcp_get_code":{"code_sha256":"3db4474abe13fdee"}},{"arxiv_id":"2311.01276","paper":"/paper/long-range-neural-atom-learning-for-molecular","title":"Neural Atoms: Propagating Long-range Interaction in Molecular Graphs through Efficient Communication Channel","date":"2023-11-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tmlr-group/neuralatom","path":"2D_Molecule/graphgps/finetuning.py","file_url":"https://github.com/tmlr-group/neuralatom/blob/HEAD/2D_Molecule/graphgps/finetuning.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8653a762bb268420","mcp_get_code":{"code_sha256":"8653a762bb268420"}},{"arxiv_id":"2310.19285","paper":"/paper/facilitating-graph-neural-networks-with","title":"Facilitating Graph Neural Networks with Random Walk on Simplicial Complexes","date":"2023-10-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhouc20/HodgeRandomWalk","path":"graphgps/finetuning.py","file_url":"https://github.com/zhouc20/HodgeRandomWalk/blob/HEAD/graphgps/finetuning.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9a4410b8a6c0cc47","mcp_get_code":{"code_sha256":"9a4410b8a6c0cc47"}},{"arxiv_id":"2310.07430","paper":"/paper/non-backtracking-graph-neural-networks","title":"Non-backtracking Graph Neural Networks","date":"2023-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"seonghyun26/nba-gnn","path":"lrgb/graphgps/finetuning.py","file_url":"https://github.com/seonghyun26/nba-gnn/blob/HEAD/lrgb/graphgps/finetuning.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8653a762bb268420","mcp_get_code":{"code_sha256":"8653a762bb268420"}},{"arxiv_id":"2309.00367","paper":"/paper/where-did-the-gap-go-reassessing-the-long","title":"Where Did the Gap Go? Reassessing the Long-Range Graph Benchmark","date":"2023-09-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Fedzbar/laser-release","path":"laser/finetuning.py","file_url":"https://github.com/Fedzbar/laser-release/blob/HEAD/laser/finetuning.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8653a762bb268420","mcp_get_code":{"code_sha256":"8653a762bb268420"}},{"arxiv_id":"2309.00367","paper":"/paper/where-did-the-gap-go-reassessing-the-long","title":"Where Did the Gap Go? Reassessing the Long-Range Graph Benchmark","date":"2023-09-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"toenshoff/lrgb","path":"graphgps/finetuning.py","file_url":"https://github.com/toenshoff/lrgb/blob/HEAD/graphgps/finetuning.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3db4474abe13fdee","mcp_get_code":{"code_sha256":"3db4474abe13fdee"}},{"arxiv_id":"2306.07812","paper":"/paper/automated-3d-pre-training-for-molecular","title":"Automated 3D Pre-Training for Molecular Property Prediction","date":"2023-06-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lars-research/3d-pgt","path":"graphgps/finetuning.py","file_url":"https://github.com/lars-research/3d-pgt/blob/HEAD/graphgps/finetuning.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9e4db46ba20af98e","mcp_get_code":{"code_sha256":"9e4db46ba20af98e"}},{"arxiv_id":"2305.17589","paper":"/paper/graph-inductive-biases-in-transformers","title":"Graph Inductive Biases in Transformers without Message Passing","date":"2023-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liamma/grit","path":"grit/finetuning.py","file_url":"https://github.com/liamma/grit/blob/HEAD/grit/finetuning.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9e4db46ba20af98e","mcp_get_code":{"code_sha256":"9e4db46ba20af98e"}},{"arxiv_id":"2305.12322","paper":"/paper/learning-large-graph-property-prediction-via","title":"Learning Large Graph Property Prediction via Graph Segment Training","date":"2023-05-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kaidic/gst","path":"graphgps/finetuning.py","file_url":"https://github.com/kaidic/gst/blob/HEAD/graphgps/finetuning.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9e4db46ba20af98e","mcp_get_code":{"code_sha256":"9e4db46ba20af98e"}},{"arxiv_id":"2305.08018","paper":"/paper/drew-dynamically-rewired-message-passing-with","title":"DRew: Dynamically Rewired Message Passing with Delay","date":"2023-05-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bengutteridge/drew","path":"lrgb/graphgps/finetuning.py","file_url":"https://github.com/bengutteridge/drew/blob/HEAD/lrgb/graphgps/finetuning.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8653a762bb268420","mcp_get_code":{"code_sha256":"8653a762bb268420"}},{"arxiv_id":"2302.08647","paper":"/paper/multiresolution-graph-transformers-and","title":"Multiresolution Graph Transformers and Wavelet Positional Encoding for Learning Hierarchical Structures","date":"2023-02-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vijaydwivedi75/lrgb","path":"graphgps/finetuning.py","file_url":"https://github.com/vijaydwivedi75/lrgb/blob/HEAD/graphgps/finetuning.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8653a762bb268420","mcp_get_code":{"code_sha256":"8653a762bb268420"}},{"arxiv_id":"2302.04181","paper":"/paper/attending-to-graph-transformers","title":"Attending to Graph Transformers","date":"2023-02-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"luis-mueller/probing-graph-transformers","path":"graphgps/finetuning.py","file_url":"https://github.com/luis-mueller/probing-graph-transformers/blob/HEAD/graphgps/finetuning.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3db4474abe13fdee","mcp_get_code":{"code_sha256":"3db4474abe13fdee"}}]}