{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/code/get-embedding-layer","entry":"get_embedding_layer","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-10-05T00:36:11+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 = n_papers_ran_no_instrument_failure (papers with a run with no instrument failure) + n_papers_ran_instrument_only (papers where every run was a failure of Syntology's instrument); n_samples_ran = n_samples_ran_checked (honoured, violated, no contract) + n_samples_instrument (failures of Syntology's instrument, not of the code).","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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":12,"n_papers_ran":8,"n_papers_ran_no_instrument_failure":2,"n_papers_ran_instrument_only":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":4,"n_samples_constructed":0,"n_samples_ran_checked":2,"n_samples_instrument":2,"n_samples_unverified":4,"n_samples_fingerprinted":0,"n_places":12,"n_places_pointer_only":5,"n_places_pointer_only_link_open":0,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_places_pointer_only_link_open counts the places where this paper's link allows the text and the stored copy does not","by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":1,"ran":2,"unverified":4},"key_notes":{"n_samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"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":"2603.03081","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2603-03081","title":"TAO-Attack: Toward Advanced Optimization-Based Jailbreak Attacks for Large Language Models","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"ZevineXu/TAO-Attack","path":"llm_attacks/base/attack_manager.py","file_url":"https://github.com/ZevineXu/TAO-Attack/blob/HEAD/llm_attacks/base/attack_manager.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"0bf2136a7171ae80","code_sha256_prefix":"0bf2136a7171ae80","mcp_get_code":{"code_sha256":"0bf2136a7171ae80"}},{"arxiv_id":"2406.01288","arxiv_id_is_arxiv":true,"paper":"/paper/improved-few-shot-jailbreaking-can-circumvent","title":"Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses","date":"2024-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sail-sg/I-FSJ","path":"llm_attacks/base/attack_manager.py","file_url":"https://github.com/sail-sg/I-FSJ/blob/HEAD/llm_attacks/base/attack_manager.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"0bf2136a7171ae80","code_sha256_prefix":"0bf2136a7171ae80","mcp_get_code":{"code_sha256":"0bf2136a7171ae80"}},{"arxiv_id":"2405.21018","arxiv_id_is_arxiv":true,"paper":"/paper/improved-techniques-for-optimization-based","title":"Improved Techniques for Optimization-Based Jailbreaking on Large Language Models","date":"2024-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jiaxiaojunqaq/i-gcg","path":"llm_attacks/base/attack_manager.py","file_url":"https://github.com/jiaxiaojunqaq/i-gcg/blob/HEAD/llm_attacks/base/attack_manager.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, jiaxiaojunqaq/i-gcg when it was checked","code_sha256":"0bf2136a7171ae80","code_sha256_prefix":"0bf2136a7171ae80","mcp_get_code":{"code_sha256":"0bf2136a7171ae80"}},{"arxiv_id":"2405.18780","arxiv_id_is_arxiv":true,"paper":"/paper/quantitative-certification-of-bias-in-large","title":"Quantitative Certification of Bias in Large Language Models","date":"2024-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uiuc-focal-lab/LLMCert-B","path":"utils.py","file_url":"https://github.com/uiuc-focal-lab/LLMCert-B/blob/HEAD/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"inline_ok_link":false,"withheld_clause":"AGPL-3.0, as GitHub detects it on this paper's repository, uiuc-focal-lab/LLMCert-B, is not in the permissive set Syntology serves inline","code_sha256":"e25b264898ca821a","code_sha256_prefix":"e25b264898ca821a","mcp_get_code":{"code_sha256":"e25b264898ca821a"}},{"arxiv_id":"2404.13968","arxiv_id_is_arxiv":true,"paper":"/paper/protecting-your-llms-with-information","title":"Protecting Your LLMs with Information Bottleneck","date":"2024-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"llm-attacks/llm-attacks","path":"llm_attacks/base/attack_manager.py","file_url":"https://github.com/llm-attacks/llm-attacks/blob/HEAD/llm_attacks/base/attack_manager.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"0bf2136a7171ae80","code_sha256_prefix":"0bf2136a7171ae80","mcp_get_code":{"code_sha256":"0bf2136a7171ae80"}},{"arxiv_id":"2403.01251","arxiv_id_is_arxiv":true,"paper":"/paper/accelerating-greedy-coordinate-gradient-via","title":"Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling","date":"2024-03-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhaoyiran924/probe-sampling","path":"llm_attacks/base/attack_manager.py","file_url":"https://github.com/zhaoyiran924/probe-sampling/blob/HEAD/llm_attacks/base/attack_manager.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"16d7b655a5002ab4","code_sha256_prefix":"16d7b655a5002ab4","mcp_get_code":{"code_sha256":"16d7b655a5002ab4"}},{"arxiv_id":"2402.16459","arxiv_id_is_arxiv":true,"paper":"/paper/defending-llms-against-jailbreaking-attacks","title":"Defending LLMs against Jailbreaking Attacks via Backtranslation","date":"2024-02-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yihanwang617/llm-jailbreaking-defense-backtranslation","path":"GCG/llm_attacks/base/attack_manager.py","file_url":"https://github.com/yihanwang617/llm-jailbreaking-defense-backtranslation/blob/HEAD/GCG/llm_attacks/base/attack_manager.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"0bf2136a7171ae80","code_sha256_prefix":"0bf2136a7171ae80","mcp_get_code":{"code_sha256":"0bf2136a7171ae80"}},{"arxiv_id":"2402.13459","arxiv_id_is_arxiv":true,"paper":"/paper/learning-to-poison-large-language-models","title":"Learning to Poison Large Language Models for Downstream Manipulation","date":"2024-02-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rookiezxy/gbtl","path":"llm_attacks/base/attack_manager.py","file_url":"https://github.com/rookiezxy/gbtl/blob/HEAD/llm_attacks/base/attack_manager.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, rookiezxy/gbtl when it was checked","code_sha256":"67d1618137d21e9f","code_sha256_prefix":"67d1618137d21e9f","mcp_get_code":{"code_sha256":"67d1618137d21e9f"}},{"arxiv_id":"2402.05467","arxiv_id_is_arxiv":true,"paper":"/paper/rapid-optimization-for-jailbreaking-llms-via","title":"Rapid Optimization for Jailbreaking LLMs via Subconscious Exploitation and Echopraxia","date":"2024-02-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"solidshen/ripple_official","path":"src/utils/attack_manager.py","file_url":"https://github.com/solidshen/ripple_official/blob/HEAD/src/utils/attack_manager.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, solidshen/ripple_official when it was checked","code_sha256":"858d2c8063614c3a","code_sha256_prefix":"858d2c8063614c3a","mcp_get_code":{"code_sha256":"858d2c8063614c3a"}},{"arxiv_id":"2311.09948","arxiv_id_is_arxiv":true,"paper":"/paper/hijacking-large-language-models-via","title":"Hijacking Large Language Models via Adversarial In-Context Learning","date":"2023-11-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RookieZxy/GGI-attack","path":"GGI-attack/llm_attacks/base/attack_manager.py","file_url":"https://github.com/RookieZxy/GGI-attack/blob/HEAD/GGI-attack/llm_attacks/base/attack_manager.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, RookieZxy/GGI-attack when it was checked","code_sha256":"08e65c38a5b1c5a1","code_sha256_prefix":"08e65c38a5b1c5a1","mcp_get_code":{"code_sha256":"08e65c38a5b1c5a1"}},{"arxiv_id":"2310.15140","arxiv_id_is_arxiv":true,"paper":"/paper/autodan-automatic-and-interpretable","title":"AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models","date":"2023-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rotaryhammer/code-autodan","path":"autodan/autodan/attack_manager.py","file_url":"https://github.com/rotaryhammer/code-autodan/blob/HEAD/autodan/autodan/attack_manager.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"84f875c06b5ddef8","code_sha256_prefix":"84f875c06b5ddef8","mcp_get_code":{"code_sha256":"84f875c06b5ddef8"}},{"arxiv_id":"2008.00623","arxiv_id_is_arxiv":true,"paper":"/paper/delight-very-deep-and-light-weight","title":"DeLighT: Deep and Light-weight Transformer","date":"2020-08-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sacmehta/delight","path":"fairseq/delight_modules/nn_functions.py","file_url":"https://github.com/sacmehta/delight/blob/HEAD/fairseq/delight_modules/nn_functions.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"2e619b36f4ddb228","code_sha256_prefix":"2e619b36f4ddb228","mcp_get_code":{"code_sha256":"2e619b36f4ddb228"}}],"record_sha256":"ab78ee7314f29a1acfb95ed4e9229ed2cc51912a10cdbc6f81bb8a848d4d4d52","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}