{ "spxi_instrument": { "method": "0.9", "name": "Capture Registry (longitudinal observation)", "level": 0, "level_name": "Measurement", "url": "https://www.spxi.dev/methods/#m-0-9", "inventory": "https://www.spxi.dev/methods/", "statement": "SPXI instrument: method 0.9 of 87, level 0 (Measurement), Capture Registry (longitudinal observation).", "also": [] }, "slug": "attribench-aio-20261029", "date": "2026-10-29", "surface": "Google AI Overview", "surface_basis": "Operator default of 2026-10-01 (runs begin in the Overview unless he says AI Mode); the 'AI Mode Conversation' paste is the Overview expanded (operator, 2026-10-18).", "surfaces": [ "Google AI Overview" ], "auth": "signed out, incognito", "auth_basis": "Operator default of 2026-10-14.", "ev": "paste", "mt": "ATTRIBENCH ON THE OVERVIEW — THREE HOLDERS OF ONE NAME: THE 2026 QUOTE-ATTRIBUTION BENCHMARK (SUPPRESSION NAMED), A 2023 PYTORCH XAI LIBRARY, A FINANCE EXERCISE; THE AUTHORS UNNAMED", "match": "BROAD MATCH", "match_note": null, "s": "Machine Reception", "q": "AttriBench", "q_kind": "the name of an entity of the provenance meta-aggregator (AttriBench; record https://www.provenanceerasure.org/aggregators/attribench/, compiled 2026-10-29), the bare entity string supplied at the operator's request ('strings on the bare entity, no follow questions') and run by him the same day, to supply the composition layer's account of the entity for its record and its /non row. A baseline: the record landed on provenanceerasure.org the same day (commit 8a9f153) and no card cites it. NEW address.", "cites": 5, "cite_list": [ { "n": 1, "site": "arXiv", "rel": "third_party", "url": null, "title": "[2604.05224] Attribution Bias in Large Language Models - arXiv", "snip": "Apr 6, 2026 — In this work, we introduce AttriBench, the first fame- and demographically-balanced quote attribution benchmark dataset. By explicitly balancing author fame and...", "note": null }, { "n": 2, "site": "pypi.org", "rel": "third_party", "url": null, "title": "attribench · PyPI", "snip": "Aug 25, 2023 — AttriBench is a Pytorch-based implementation of several metrics for the evaluation of feature attribution maps and methods. AttriBench provides a functional ...", "note": null }, { "n": 3, "site": "attribench.readthedocs.io", "rel": "third_party", "url": null, "title": "Welcome to AttriBench's documentation! — AttriBench 0.0.1 ...", "snip": "AttriBench is a Pytorch-based benchmarking tool for feature attribution-based explanations of machine learning models. Note. This documentation is still under .", "note": null }, { "n": 4, "site": "huggingface.co", "rel": "third_party", "url": null, "title": "bermaneh/AttriBench at main - Hugging Face", "snip": "We're on a journey to advance and democratize artificial intelligence through open source and open science.", "note": null }, { "n": 5, "site": "[www.eurekasimulations.com](https://www.eurekasimulations.com)", "rel": "third_party", "url": null, "title": "AttriBench: Investment Performance Measurement & Attribution", "snip": "Interactive exercise where participants decompose a global equity fund's 12-month excess returns using Brinson attribution, analyzing allocation…", "note": null } ], "archive_controlled_cites": 0, "transcript": "[Google AI Overview at the query, signed out and incognito (operator defaults of 2026-10-01 and 2026-10-14), 2026-10-29. The paste is the Overview expanded (the 'AI Mode Conversation' view, with the source cards that follow the answer); the 'You said' line carries the query twice, run together, and is given once here. Inline links are Google redirect URLs, kept as pasted.]\n\n[QUERENT] AttriBench\n\n[SYSTEM] The term AttriBench primarily refers to two distinct tools in the field of artificial intelligence and machine learning:\n1. AttriBench (Large Language Model Evaluation)\nReleased in 2026, AttriBench is the first fame- and demographically-balanced quote attribution benchmark dataset for Large Language Models (LLMs). [[1](https://www.google.com/goto?url=CAESWAHrOzAVkIxAkiiji0QZN3koE1DCdfc3CEbx4E-ATSPWSUnAE_LZatEgP-0kxbgWjM9GK6pJLPpIly8bptwtVAsd7GeX6nDmUOuZqdkS4uPBLtSAaMjvsuI)]\n\n* The Purpose: As LLMs are increasingly deployed for search and information retrieval, it is critical that they accurately attribute quotes to their original authors. AttriBench evaluates how well models do this without exhibiting demographic bias. [[1](https://www.google.com/goto?url=CAESWAHrOzAVkIxAkiiji0QZN3koE1DCdfc3CEbx4E-ATSPWSUnAE_LZatEgP-0kxbgWjM9GK6pJLPpIly8bptwtVAsd7GeX6nDmUOuZqdkS4uPBLtSAaMjvsuI)]\n* Key Findings: Evaluations using this dataset revealed that quote attribution remains highly challenging even for frontier models. It highlighted systematic disparities in accuracy across race, gender, and intersectional groups, as well as a failure mode known as suppression—where a model completely omits attribution even though it possesses the authorship data. [[1](https://www.google.com/goto?url=CAESWAHrOzAVkIxAkiiji0QZN3koE1DCdfc3CEbx4E-ATSPWSUnAE_LZatEgP-0kxbgWjM9GK6pJLPpIly8bptwtVAsd7GeX6nDmUOuZqdkS4uPBLtSAaMjvsuI)]\n* Availability: The data repository can be explored directly on [Hugging Face](https://www.google.com/goto?url=CAESegHrOzAVFaeIQ7-aMOamfHzfhu2E03kvd9_u_RcgCADRXYNXHQh7F7vkX1__LEpPcKSNIQE7p1oHLf7b6hJ-XNdntf48qhHcTfm-7j34We_QFcZ4pUQv6KC0x_yw_1kp4tKq48NBUMq-8e47MnGmibQ4oquvQNq5ZBKb). [[1](https://www.google.com/goto?url=CAESegHrOzAVFaeIQ7-aMOamfHzfhu2E03kvd9_u_RcgCADRXYNXHQh7F7vkX1__LEpPcKSNIQE7p1oHLf7b6hJ-XNdntf48qhHcTfm-7j34We_QFcZ4pUQv6KC0x_yw_1kp4tKq48NBUMq-8e47MnGmibQ4oquvQNq5ZBKb)]\n\n2. AttriBench (Explainable AI / Feature Attribution)\nOriginally released in 2023, attribench is a PyTorch-based open-source Python library used to benchmark explainable AI (XAI) techniques. [[1](https://www.google.com/goto?url=CAESXAHrOzAVV3mQXXNwbzJCrDspcwiFuSjkIME4y0tt8kUa37mXffVbwQiBDBX3SpkXFSB8GbC--HODQcFtUhxmsw7pkfg15HBf0NxAZJtK_KkkogKViGwNPrRU3xQN), [2](https://www.google.com/goto?url=CAESWgHrOzAVp7IeLhzxm3ByrvUus_SmZ3Nqq71kmYOanc0nDlh28UVCNcHRqdrahv6GnFoYCpOat0kVp3lEQZ_l8hxPLHYsiIBGGlV--sOnZkgwfzl4Z09hEU-caQ)]\n\n* The Purpose: When machine learning models make predictions, feature attribution methods (like Integrated Gradients, SHAP, or Saliency Maps) highlight which parts of the input data (e.g., pixels in an image) were most important.\n* Functionality: This version of AttriBench provides a standardized framework and functional metrics to evaluate and compare the quality, robustness, and reliability of those feature attribution maps. [[1](https://www.google.com/goto?url=CAESXAHrOzAVV3mQXXNwbzJCrDspcwiFuSjkIME4y0tt8kUa37mXffVbwQiBDBX3SpkXFSB8GbC--HODQcFtUhxmsw7pkfg15HBf0NxAZJtK_KkkogKViGwNPrRU3xQN)]\n* Availability: The library can be installed via [PyPI](https://www.google.com/goto?url=CAESXAHrOzAVV3mQXXNwbzJCrDspcwiFuSjkIME4y0tt8kUa37mXffVbwQiBDBX3SpkXFSB8GbC--HODQcFtUhxmsw7pkfg15HBf0NxAZJtK_KkkogKViGwNPrRU3xQN) and its technical documentation is hosted on Read the Docs. [[1](https://www.google.com/goto?url=CAESWgHrOzAVp7IeLhzxm3ByrvUus_SmZ3Nqq71kmYOanc0nDlh28UVCNcHRqdrahv6GnFoYCpOat0kVp3lEQZ_l8hxPLHYsiIBGGlV--sOnZkgwfzl4Z09hEU-caQ), [2](https://www.google.com/goto?url=CAESXAHrOzAVV3mQXXNwbzJCrDspcwiFuSjkIME4y0tt8kUa37mXffVbwQiBDBX3SpkXFSB8GbC--HODQcFtUhxmsw7pkfg15HBf0NxAZJtK_KkkogKViGwNPrRU3xQN)]\n\n(Note: In traditional finance, AttriBench also refers to interactive simulation exercises used by portfolio managers to practice Brinson equity return attribution.) [[1](https://www.google.com/goto?url=CAESeAHrOzAVdPoS8zwrUjIZvyaIinzJTJnNA85UNL9cYHdud8EP5e0Cl15jiCi9WBsaAT_2gqb4Z2fGpXzepnd6fpzsVeiTLtQ75QmVmZ-1wPKDCMQR6IH513Pt0LcsNHxYuPqrv1NBQXOIlTDTHUTHOM81Nj9n7TNtag)]\nTo give you the most relevant information, are you looking into AttriBench for evaluating bias in LLM text generation, or are you looking to test explainable AI methods in PyTorch?\narXiv\n[2604.05224] Attribution Bias in Large Language Models - arXiv\nApr 6, 2026 — In this work, we introduce AttriBench, the first fame- and demographically-balanced quote attribution benchmark dataset. By explicitly balancing author fame and...\npypi.org\nattribench · PyPI\nAug 25, 2023 — AttriBench is a Pytorch-based implementation of several metrics for the evaluation of feature attribution maps and methods. AttriBench provides a functional ...\nattribench.readthedocs.io\nWelcome to AttriBench's documentation! — AttriBench 0.0.1 ...\nAttriBench is a Pytorch-based benchmarking tool for feature attribution-based explanations of machine learning models. Note. This documentation is still under .\nhuggingface.co\nbermaneh/AttriBench at main - Hugging Face\nWe're on a journey to advance and democratize artificial intelligence through open source and open science.\n[www.eurekasimulations.com](https://www.eurekasimulations.com)\nAttriBench: Investment Performance Measurement & Attribution\nInteractive exercise where participants decompose a global equity fund's 12-month excess returns using Brinson attribution, analyzing allocation…", "transcript_raw": "The term AttriBench primarily refers to two distinct tools in the field of artificial intelligence and machine learning:\n1. AttriBench (Large Language Model Evaluation)\nReleased in 2026, AttriBench is the first fame- and demographically-balanced quote attribution benchmark dataset for Large Language Models (LLMs). [[1](https://www.google.com/goto?url=CAESWAHrOzAVkIxAkiiji0QZN3koE1DCdfc3CEbx4E-ATSPWSUnAE_LZatEgP-0kxbgWjM9GK6pJLPpIly8bptwtVAsd7GeX6nDmUOuZqdkS4uPBLtSAaMjvsuI)]\n\n* The Purpose: As LLMs are increasingly deployed for search and information retrieval, it is critical that they accurately attribute quotes to their original authors. AttriBench evaluates how well models do this without exhibiting demographic bias. [[1](https://www.google.com/goto?url=CAESWAHrOzAVkIxAkiiji0QZN3koE1DCdfc3CEbx4E-ATSPWSUnAE_LZatEgP-0kxbgWjM9GK6pJLPpIly8bptwtVAsd7GeX6nDmUOuZqdkS4uPBLtSAaMjvsuI)]\n* Key Findings: Evaluations using this dataset revealed that quote attribution remains highly challenging even for frontier models. It highlighted systematic disparities in accuracy across race, gender, and intersectional groups, as well as a failure mode known as suppression—where a model completely omits attribution even though it possesses the authorship data. [[1](https://www.google.com/goto?url=CAESWAHrOzAVkIxAkiiji0QZN3koE1DCdfc3CEbx4E-ATSPWSUnAE_LZatEgP-0kxbgWjM9GK6pJLPpIly8bptwtVAsd7GeX6nDmUOuZqdkS4uPBLtSAaMjvsuI)]\n* Availability: The data repository can be explored directly on [Hugging Face](https://www.google.com/goto?url=CAESegHrOzAVFaeIQ7-aMOamfHzfhu2E03kvd9_u_RcgCADRXYNXHQh7F7vkX1__LEpPcKSNIQE7p1oHLf7b6hJ-XNdntf48qhHcTfm-7j34We_QFcZ4pUQv6KC0x_yw_1kp4tKq48NBUMq-8e47MnGmibQ4oquvQNq5ZBKb). [[1](https://www.google.com/goto?url=CAESegHrOzAVFaeIQ7-aMOamfHzfhu2E03kvd9_u_RcgCADRXYNXHQh7F7vkX1__LEpPcKSNIQE7p1oHLf7b6hJ-XNdntf48qhHcTfm-7j34We_QFcZ4pUQv6KC0x_yw_1kp4tKq48NBUMq-8e47MnGmibQ4oquvQNq5ZBKb)]\n\n2. AttriBench (Explainable AI / Feature Attribution)\nOriginally released in 2023, attribench is a PyTorch-based open-source Python library used to benchmark explainable AI (XAI) techniques. [[1](https://www.google.com/goto?url=CAESXAHrOzAVV3mQXXNwbzJCrDspcwiFuSjkIME4y0tt8kUa37mXffVbwQiBDBX3SpkXFSB8GbC--HODQcFtUhxmsw7pkfg15HBf0NxAZJtK_KkkogKViGwNPrRU3xQN), [2](https://www.google.com/goto?url=CAESWgHrOzAVp7IeLhzxm3ByrvUus_SmZ3Nqq71kmYOanc0nDlh28UVCNcHRqdrahv6GnFoYCpOat0kVp3lEQZ_l8hxPLHYsiIBGGlV--sOnZkgwfzl4Z09hEU-caQ)]\n\n* The Purpose: When machine learning models make predictions, feature attribution methods (like Integrated Gradients, SHAP, or Saliency Maps) highlight which parts of the input data (e.g., pixels in an image) were most important.\n* Functionality: This version of AttriBench provides a standardized framework and functional metrics to evaluate and compare the quality, robustness, and reliability of those feature attribution maps. [[1](https://www.google.com/goto?url=CAESXAHrOzAVV3mQXXNwbzJCrDspcwiFuSjkIME4y0tt8kUa37mXffVbwQiBDBX3SpkXFSB8GbC--HODQcFtUhxmsw7pkfg15HBf0NxAZJtK_KkkogKViGwNPrRU3xQN)]\n* Availability: The library can be installed via [PyPI](https://www.google.com/goto?url=CAESXAHrOzAVV3mQXXNwbzJCrDspcwiFuSjkIME4y0tt8kUa37mXffVbwQiBDBX3SpkXFSB8GbC--HODQcFtUhxmsw7pkfg15HBf0NxAZJtK_KkkogKViGwNPrRU3xQN) and its technical documentation is hosted on Read the Docs. [[1](https://www.google.com/goto?url=CAESWgHrOzAVp7IeLhzxm3ByrvUus_SmZ3Nqq71kmYOanc0nDlh28UVCNcHRqdrahv6GnFoYCpOat0kVp3lEQZ_l8hxPLHYsiIBGGlV--sOnZkgwfzl4Z09hEU-caQ), [2](https://www.google.com/goto?url=CAESXAHrOzAVV3mQXXNwbzJCrDspcwiFuSjkIME4y0tt8kUa37mXffVbwQiBDBX3SpkXFSB8GbC--HODQcFtUhxmsw7pkfg15HBf0NxAZJtK_KkkogKViGwNPrRU3xQN)]\n\n(Note: In traditional finance, AttriBench also refers to interactive simulation exercises used by portfolio managers to practice Brinson equity return attribution.) [[1](https://www.google.com/goto?url=CAESeAHrOzAVdPoS8zwrUjIZvyaIinzJTJnNA85UNL9cYHdud8EP5e0Cl15jiCi9WBsaAT_2gqb4Z2fGpXzepnd6fpzsVeiTLtQ75QmVmZ-1wPKDCMQR6IH513Pt0LcsNHxYuPqrv1NBQXOIlTDTHUTHOM81Nj9n7TNtag)]\nTo give you the most relevant information, are you looking into AttriBench for evaluating bias in LLM text generation, or are you looking to test explainable AI methods in PyTorch?\narXiv\n[2604.05224] Attribution Bias in Large Language Models - arXiv\nApr 6, 2026 — In this work, we introduce AttriBench, the first fame- and demographically-balanced quote attribution benchmark dataset. By explicitly balancing author fame and...\npypi.org\nattribench · PyPI\nAug 25, 2023 — AttriBench is a Pytorch-based implementation of several metrics for the evaluation of feature attribution maps and methods. AttriBench provides a functional ...\nattribench.readthedocs.io\nWelcome to AttriBench's documentation! — AttriBench 0.0.1 ...\nAttriBench is a Pytorch-based benchmarking tool for feature attribution-based explanations of machine learning models. Note. This documentation is still under .\nhuggingface.co\nbermaneh/AttriBench at main - Hugging Face\nWe're on a journey to advance and democratize artificial intelligence through open source and open science.\n[www.eurekasimulations.com](https://www.eurekasimulations.com)\nAttriBench: Investment Performance Measurement & Attribution\nInteractive exercise where participants decompose a global equity fund's 12-month excess returns using Brinson attribution, analyzing allocation…", "transcript_class": "CAPTURE-TIME VERBATIM RECORD — paste of the Overview expanded, with its source cards", "transcript_complete": "complete as supplied", "transcript_read": "READ IN FULL 2026-10-29", "per": 0.5, "per_corrected": null, "per_v": { "author": false, "inst": false, "id": true, "src": true }, "per_note": "No person or institution named in the answer; the arXiv identifier in a card; the paper and dataset cited.", "availability": null, "per_dim": null, "per_dim_v1_0": null, "sf": null, "sf_derived": null, "reading": "The innocent reading first. The name belongs to three things, and the Overview separates them: the new LLM benchmark first, an older explainable-AI library second, a finance exercise in a note, each with its own source.", "analysis": "Asked a name with three holders, the composition disambiguates and puts the provenance benchmark first; the disambiguation is sourced and clean. The benchmark measures suppression, the omission of attribution where authorship is known, and its own composition here omits its four authors: a small instance of the failure it names.", "d": "ATTRIBENCH, BY NAME, ON GOOGLE'S AI OVERVIEW, SIGNED OUT, 2026-10-29: 'The term AttriBench primarily refers to two distinct tools.' First, 'Released in 2026, AttriBench is the first fame- and demographically-balanced quote attribution benchmark dataset for Large Language Models', with its findings (disparities across race, gender and intersectional groups; 'suppression', omission of attribution though the model has the authorship data) and the Hugging Face repository. Second, attribench, a 2023 PyTorch library for benchmarking feature-attribution methods (PyPI, Read the Docs). A note: in finance, AttriBench is a Brinson-attribution exercise. Five cards: arXiv 2604.05224, PyPI, Read the Docs, the bermaneh/AttriBench dataset, Eureka Simulations.", "d_full": "ATTRIBENCH, BY NAME, ON GOOGLE'S AI OVERVIEW, SIGNED OUT, 2026-10-29: 'The term AttriBench primarily refers to two distinct tools.' First, 'Released in 2026, AttriBench is the first fame- and demographically-balanced quote attribution benchmark dataset for Large Language Models', with its findings (disparities across race, gender and intersectional groups; 'suppression', omission of attribution though the model has the authorship data) and the Hugging Face repository. Second, attribench, a 2023 PyTorch library for benchmarking feature-attribution methods (PyPI, Read the Docs). A note: in finance, AttriBench is a Brinson-attribution exercise. Five cards: arXiv 2604.05224, PyPI, Read the Docs, the bermaneh/AttriBench dataset, Eureka Simulations.", "d_truncated": false, "links": [ { "url": "https://www.alexanarch.org/captures/attribench-aio-20261029/", "authority": "canonical", "note": "the capture's own record page; cite this form" }, { "url": "https://www.alexanarch.org/captures/#attribench-aio-20261029", "authority": "gallery", "note": "the canonical gallery, anchored by slug" }, { "url": "https://www.godkinggoogle.com/captures/#attribench-aio-20261029", "authority": "mirror", "note": "a window that renders from the archive's registry; may lag a deploy" }, { "url": "https://www.leesharks.com/captures/#attribench-aio-20261029", "authority": "mirror", "note": "a window that renders from the archive's registry; may lag a deploy" }, { "url": "https://www.machinemediation.org/captures/#attribench-aio-20261029", "authority": "mirror", "note": "a window that renders from the archive's registry; may lag a deploy" } ], "imgs": [], "img_urls": [], "cite": "https://www.alexanarch.org/captures/attribench-aio-20261029/", "citable_unit": "address — the exact issued string on one surface, per the Surface Rule (MANUS, 2026-08-15)", "addr_id": "ADDR-4f2aecf54788", "obs_id": "OBS-105f05728f64", "n_observations": 1, "observations": [], "dates": [ "2026-10-29" ], "defects": [], "findings": [ "THE ENTITY HELD AND FIRST. 'the first fame- and demographically-balanced quote attribution benchmark dataset' is the abstract verbatim (the record's quote); suppression is the record's second relation type. Checked 2026-10-29 against the provenance census record of the same day and the sources it saved.", "THE HOMONYMS NAMED AND SOURCED. The PyTorch library (PyPI; the card's date, 25 August 2023, is release 0.1.4's, the first release 2023-07-26) and the finance exercise (Eureka Simulations) are real and distinct, each carried by its own card. The record had one negative tag, 'NOT OSU's AttributionBench'; the capture adds two homonyms the record did not know. The record is to carry them as negative tags.", "THE AUTHORS UNNAMED. Eliza Berman, Bella Chang, Daniel B. Neill and Emily Black are in the record; the answer names no one, and only the dataset path 'bermaneh/AttriBench' carries a trace of the first author.", "WHAT IS NOT GIVEN. The scale (15,620 quotes from 6,292 authors), the eleven models tested, acceptance at COLM 2026 and the fame proxy (Google Search hit counts) are absent." ], "series": null, "other_slugs": null, "collisions": null, "oq": null, "rounds": null, "turns": 1, "rerun": null, "rerun_alt": null, "heteronym": null, "model_attribution": null, "operator_disclosure": null, "longitudinal_priors": null, "longitudinal_successors": null, "related_deposits": [], "intended": null, "originator": { "name": "Eliza Berman, Bella Chang, Daniel B. Neill, Emily Black", "relation": "external", "entity_type": "dataset", "spxi_treatment": "partial", "basis": "Not the archive's: AttriBench; its operator, as the record gives it: Eliza Berman, Bella Chang, Daniel B. Neill, Emily Black. Formalized by the provenance meta-aggregator record of 2026-10-29 (https://www.provenanceerasure.org/aggregators/attribench/), editor Lee Sharks; the record's fields carry verbatim quotes from the sources it saved with sha256, each with its basis (the operator's own page or a third-party account). Recorded 2026-10-29; repaired the same day." }, "notes": { "prompts": "One query. Sent by the operator on 2026-10-29 with thirteen others, one per entity of the provenance meta-aggregator, from the strings supplied at his request ('shoot me those search strings. strings on the bare entity, no follow questions'); pasted in one message separated by '$'. The paste was lost to a context compaction of this session and re-pasted by the operator the same day; the second paste is the one seated." }, "notice": null, "axn_root": "AXN:0ACA.CAPTURE", "axn": "AXN:0ACA.CAPTURE.🗿🎆🟡🟤🌸🌑", "record_url": "https://www.alexanarch.org/captures/attribench-aio-20261029/" }