{"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/kernelmat","entry":"kernelmat","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":10,"n_papers_ran":6,"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":8,"n_samples_ran":5,"n_samples_fingerprinted":1,"n_places":10,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":1,"ran":2,"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":"2606.19679","paper":"/paper/arxiv-2606-19679","title":"LOKI: Memory-Free Null-Space Constrained Lifelong Knowledge Editing","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"neu-spiral/LOKI","path":"easyeditor/models/loki/loki_main.py","file_url":"https://github.com/neu-spiral/LOKI/blob/HEAD/easyeditor/models/loki/loki_main.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ab2cd20fd45e42c5","mcp_get_code":{"code_sha256":"ab2cd20fd45e42c5"}},{"arxiv_id":"2510.20627","paper":"/paper/arxiv-2510-20627","title":"H-SPLID: HSIC-based Saliency Preserving Latent Information Decomposition","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"neu-spiral/H-SPLID","path":"src/models/split_model.py","file_url":"https://github.com/neu-spiral/H-SPLID/blob/HEAD/src/models/split_model.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b41642f800673cde","mcp_get_code":{"code_sha256":"b41642f800673cde"}},{"arxiv_id":"2411.08460","paper":"/paper/trap-mid-trapdoor-based-defense-against-model","title":"Trap-MID: Trapdoor-based Defense against Model Inversion Attacks","date":"2024-11-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ntuaislab/trap-mid","path":"loss.py","file_url":"https://github.com/ntuaislab/trap-mid/blob/HEAD/loss.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"92265a82f9af90ae","mcp_get_code":{"code_sha256":"92265a82f9af90ae"}},{"arxiv_id":"2402.19465","paper":"/paper/towards-tracing-trustworthiness-dynamics","title":"Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models","date":"2024-02-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chnq/tracingllm","path":"src/mi_estimators.py","file_url":"https://github.com/chnq/tracingllm/blob/HEAD/src/mi_estimators.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":"f3fd137e74d1312c","mcp_get_code":{"code_sha256":"f3fd137e74d1312c"}},{"arxiv_id":"2306.09104","paper":"/paper/on-strengthening-and-defending-graph","title":"On Strengthening and Defending Graph Reconstruction Attack with Markov Chain Approximation","date":"2023-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tmlr-group/MC-GRA","path":"MC-GRA/hsic.py","file_url":"https://github.com/tmlr-group/MC-GRA/blob/HEAD/MC-GRA/hsic.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e3c0f8ba33d86df6","mcp_get_code":{"code_sha256":"e3c0f8ba33d86df6"}},{"arxiv_id":"2210.04311","paper":"/paper/pruning-adversarially-robust-neural-networks","title":"Pruning Adversarially Robust Neural Networks without Adversarial Examples","date":"2022-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"neu-spiral/pwoa","path":"source/hsicbt/math/hsic.py","file_url":"https://github.com/neu-spiral/pwoa/blob/HEAD/source/hsicbt/math/hsic.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"882769c04ee627eb","mcp_get_code":{"code_sha256":"882769c04ee627eb"}},{"arxiv_id":"2106.02734","paper":"/paper/revisiting-hilbert-schmidt-information","title":"Revisiting Hilbert-Schmidt Information Bottleneck for Adversarial Robustness","date":"2021-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"neu-spiral/hbar","path":"source/hbar/math/hsic.py","file_url":"https://github.com/neu-spiral/hbar/blob/HEAD/source/hbar/math/hsic.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"882769c04ee627eb","mcp_get_code":{"code_sha256":"882769c04ee627eb"}},{"arxiv_id":"2106.01939","paper":"/paper/graph-intervention-networks-for-causal-effect","title":"Causal Effect Inference for Structured Treatments","date":"2021-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JeanKaddour/GIN","path":"models/building_blocks/hsic_utils.py","file_url":"https://github.com/JeanKaddour/GIN/blob/HEAD/models/building_blocks/hsic_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f79c5f76af695e65","mcp_get_code":{"code_sha256":"f79c5f76af695e65"}},{"arxiv_id":"1908.01580","paper":"/paper/the-hsic-bottleneck-deep-learning-without","title":"The HSIC Bottleneck: Deep Learning without Back-Propagation","date":"2019-08-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"choasma/HSIC-Bottleneck","path":"source/hsicbt/math/hsic.py","file_url":"https://github.com/choasma/HSIC-Bottleneck/blob/HEAD/source/hsicbt/math/hsic.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"24809ea920bce66a","mcp_get_code":{"code_sha256":"24809ea920bce66a"}},{"arxiv_id":"2024.findings-acl.290","paper":null,"title":"arXiv:2024.findings-acl.290","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"ChnQ/TracingLLM","path":"src/mi_estimators.py","file_url":"https://github.com/ChnQ/TracingLLM/blob/HEAD/src/mi_estimators.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":"f3fd137e74d1312c","mcp_get_code":{"code_sha256":"f3fd137e74d1312c"}}]}