Ultralow sub-500nA operating current high-performance TiN\Al2O3\HfO2\Hf\TiN bipolar RRAM achieved through understanding-based stack-engineering
The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.
Abstract
We demonstrate sub-500nA switching and tunable set voltage by inserting thin Al2O3layer in TiN\HfO2\Hf\TiN RRAM cell. Stack engineering clearly led to novel insights into the switching phenomenology: (i) O-scavenging is key in the forming process and stack-asymmetry management; (ii) dielectric-stack thinning allows lower forming current; (iii) `natural' (asymmetry-induced) reset switching takes place close to the TiN anode; (iv) reset resistance is limited by material-barrier properties at TiN interface.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“a low-energy consumption for switching (~10fJ per state transition with zero-static consumption when idle50)”
From Hardware implementation of memristor-based artificial neural networks (2024) · cites this paper as [50]
Citations
Cites
Influence of Al2O3 crystallization on band offsets at interfaces with Si and TiNx
Afanas'ev, V. V., Houssa, M., Stesmans, A. L., Merckling, C., Schram, T., & Kittl, J. A. (2011) · Applied Physics Letters · doi:10.1063/1.3623439 · Cited by 61
Self-citationPantisano, L., Afanas'ev, V. V., Cimino, S., Adelmann, C., Goux, L., Chen, Y. Y., Kittl, J. A., Wouters, D. J., & Jurczak, M. (2011) · Microelectronic Engineering · doi:10.1016/j.mee.2011.03.057 · Cited by 42
Self-citation
Research works printed but not linked: 4
- lee, 2010, IEDM
- wang, 2010, IEDM
- govoreanu, 2011, IEDM
- degraeve, 2010, IEDM
Cited by
Overview of emerging nonvolatile memory technologies
Meena, J. S., Sze, S. M., Chand, U., & Tseng, T.-Y. (2014) · Nanoscale Research Letters · doi:10.1186/1556-276x-9-526 · Cited by 801
“have explained that using a stacked RRAM structure has been shown to be one of the most promising methods to improve the memory characteristics [124].”
MethodHardware implementation of memristor-based artificial neural networks
Aguirre, F., Sebastian, A., Le Gallo, M., Song, W., Wang, T., Yang, J. J., Lu, W., Chang, M.-F., Ielmini, D., Yang, Y., et al. (2024) · Nature Communications · doi:10.1038/s41467-024-45670-9 · Cited by 564
“…non-volatile states (up to ~100 47,48 , and even ~1000 49 ), ii) a low-energy consumption for switching(~10fJperstatetransitionwithzero-staticconsumptionwhen idle 50 ), and iii) a scalable structure appropriate for matrix integration (often referred to as crossbar 51 ) and even 3D stacking 52 .”
Power-efficient neural network with artificial dendrites
Li, X., Tang, J., Zhang, Q., Gao, B., Yang, J. J., Song, S., Wu, W., Zhang, W., Yao, P., Deng, N., et al. (2020) · Nature Nanotechnology · doi:10.1038/s41565-020-0722-5 · Cited by 255
Nanoionic memristive phenomena in metal oxides: the valence change mechanism
Dittmann, R., Menzel, S., & Waser, R. (2021) · Advances in Physics · doi:10.1080/00018732.2022.2084006 · Cited by 194
Technological Exploration of RRAM Crossbar Array for Matrix-Vector Multiplication
Xia, L., Gu, P., Li, B., Tang, T., Yin, X., Huangfu, W., Yu, S., Cao, Y., Wang, Y., & Yang, H. (2016) · Journal of Computer Science and Technology · doi:10.1007/s11390-016-1608-8 · Cited by 183
“Some researchers use the technology at the device level to improve the performance of RRAM, such as using emerging oxide material with special characteristic[15,18-19] and optimizing the thickness of oxide layer[20-21].”
BackgroundPhase-Change and Redox-Based Resistive Switching Memories
Wouters, D. J., Waser, R., & Wuttig, M. (2015) · Proceedings of the IEEE · doi:10.1109/jproc.2015.2433311 · Cited by 173
Self-citationChallenges hindering memristive neuromorphic hardware from going mainstream
Adam, G. C., Khiat, A., & Prodromakis, T. (2018) · Nature Communications · doi:10.1038/s41467-018-07565-4 · Cited by 136
Resistive Random Access Memory for Future Information Processing System
Wu, H., Wang, X. H., Gao, B., Deng, N., Lu, Z., Haukness, B., Bronner, G. B., & Qian, H. (2017) · Proceedings of the IEEE · doi:10.1109/jproc.2017.2684830 · Cited by 124
Forming‐Free Grain Boundary Engineered Hafnium Oxide Resistive Random Access Memory Devices
Petzold, S., Zintler, A., Eilhardt, R., Piros, E., Kaiser, N., Sharath, S. U., Vogel, T., Major, M., McKenna, K. P., Molina‐Luna, L., et al. (2019) · Advanced Electronic Materials · doi:10.1002/aelm.201900484 · Cited by 84
Spiking Neural Networks Based on OxRAM Synapses for Real-Time Unsupervised Spike Sorting
Werner, T., Vianello, E., Bichler, O., Garbin, D., Cattaert, D., Yvert, B., de Salvo, B., & Perniola, L. (2016) · Frontiers in Neuroscience · doi:10.3389/fnins.2016.00474 · Cited by 77
“(B) Example of extracellular electrical signals recorded from n channels (microelectrodes) and zoom-in showing three distinct spike shapes (A, B, and C) corresponding to three different neurons. for further use and/or wireless transmission (Yin et al., 2014).”
BackgroundFormation and disruption of conductive filaments in a HfO2/TiN structure
Brivio, S., Tallarida, G., Cianci, E., & Spiga, S. (2014) · Nanotechnology · doi:10.1088/0957-4484/25/38/385705 · Cited by 71
Technological exploration of RRAM crossbar array for matrix-vector multiplication
Gu, P., Li, B., Tang, T., Yu, S., Cao, Y. K., Wang, Y., & Yang, H. (2015) · Asia and South Pacific Design Automation Conference (ASP-DAC) · doi:10.1109/aspdac.2015.7058989 · Cited by 81
Electrode-induced digital-to-analog resistive switching in TaO x -based RRAM devices
Li, X., Wu, H., Gao, B., Wu, W., Wu, D. M., Deng, N., Cai, J., & Qian, H. (2016) · Nanotechnology · doi:10.1088/0957-4484/27/30/305201 · Cited by 63
Egorov, K. V., Kuzmichev, D. S., Chizhov, P. S., Lebedinskiǐ, Y. Y., Hwang, C. S., & Markeev, A. M. (2017) · ACS Applied Materials & Interfaces · doi:10.1021/acsami.7b00778 · Cited by 61
“16], and resistance switching random access memory (ReRAM) [17-20].”
BackgroundCharge-dependent oxygen vacancy diffusion in Al2O3-based resistive-random-access-memories
Yang, M. Y., Kamiya, K., Magyari‐Köpe, B., Niwa, M., Nishi, Y., & Shiraishi, K. (2013) · Applied Physics Letters · doi:10.1063/1.4819772 · Cited by 52
Stable self-compliance resistive switching in AlO δ /Ta 2 O 5− x /TaO y triple layer devices
Wu, H., Li, X., Huang, F., Chen, A., Yu, Z., & Qian, H. (2014) · Nanotechnology · doi:10.1088/0957-4484/26/3/035203 · Cited by 41
“Migration of the oxygen ions to the AlOδ barrier layer also reduces the defect density in this layer [12, 14, 15], which changes the carrier transport process from Frenkel–Poole emission to Schottky emission.”
Background90nm W\Al2O3\TiW\Cu 1T1R CBRAM cell showing low-power, fast and disturb-free operation
Belmonte, A., Kim, W. H., Chan, B. T., Heylen, N., Fantini, A., Houssa, M., Jurczak, M., & Goux, L. (2013) · IEEE International Memory Workshop (IMW) · doi:10.1109/imw.2013.6582089 · Cited by 56
“benefit of the CBRAM mechanism where complete Cu dissolution may be induced by reset, while it was previously shown [13] that oxygen-vacancy recovery is limited in the case of oxide-based resistive switching RAM (OxRRAM), and that the state resistance is controlled by a very narrow constriction.”
BackgroundSelf-citationJames, A. P., Francis, L. R. V. J., & Kumar, D. S. (2014) · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · doi:10.1109/tvlsi.2012.2232946 · Cited by 34
Resistive memory variability: A simplified trap-assisted tunneling model
Garbin, D., Vianello, E., Rafhay, Q., Azzaz, M., Candelier, P., de Salvo, B., Ghibaudo, G., & Perniola, L. (2015) · Solid-State Electronics · doi:10.1016/j.sse.2015.09.004 · Cited by 31
Goux, L., Raghavan, N., Fantini, A., Nigon, R., Strangio, S., Degraeve, R., Kar, G. S., Chen, Y. Y., Stefano, F. D., Afanas'ev, V. V., et al. (2014) · Journal of Applied Physics · doi:10.1063/1.4896841 · Cited by 33
Self-citationText classification in memristor-based spiking neural networks
Huang, J., Serb, A., Stathopoulos, S., & Prodromakis, T. (2023) · Neuromorphic Computing and Engineering · doi:10.1088/2634-4386/acb2f0 · Cited by 30
“The extreme downscaled size [39], the large-scale integrability [40], multi-bit storage [41], crossbar arrangement [42], ns-scale switching speed [43] and high power efficiency [44] make memristors good candidates to replace SRAM in in-memory computing applications [45–47].”
BackgroundZhang, L., Cosemans, S., Wouters, D. J., Groeseneken, G., Jurczak, M., & Govoreanu, B. (2015) · IEEE Electron Device Letters · doi:10.1109/led.2015.2427313 · Cited by 26
“Different RHRS/RLRS ratio, 10, 50 and 5000 are analyzed, to mimic typical resistance ratios for oxide-based RRAM [1], [14], [15] and Cu-based CBRAM [16].”
MethodSelf-citationJacobs-Gedrim, R. B., Agarwal, S., Knisely, K. E., Stevens, J. E., Heukelom, M. S. V., Hughart, D. R., Niroula, J., James, C. D., & Marinella, M. J. (2017) · IEEE International Conference on Rebooting Computing (ICRC) · doi:10.1109/icrc.2017.8123657 · Cited by 29
Azzaz, M., Benoist, A., Vianello, E., Garbin, D., Jalaguier, E., Cagli, C., Charpin, C., Bernasconi, S., Jeannot, S., Dewolf, T., et al. (2016) · Solid-State Electronics · doi:10.1016/j.sse.2016.07.007 · Cited by 25
Cell Variability Impact on the One-Selector One-Resistor Cross-Point Array Performance
Zhang, L., Cosemans, S., Wouters, D. J., Groeseneken, G., Jurczak, M., & Govoreanu, B. (2015) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2015.2439958 · Cited by 23
Self-citationOn the impact of OxRAM-based synapses variability on convolutional neural networks performance
Garbin, D., Vianello, E., Bichler, O., Azzaz, M., Rafhay, Q., Candelier, P., Gamrat, C., Ghibaudo, G., DeSalvo, B., & Perniola, L. (2015) · IEEE/ACM International Symposium on Nanoscale Architectures (NANOARCH) · doi:10.1109/nanoarch.2015.7180611 · Cited by 20
Memory and Storage System Design with Nonvolatile Memory Technologies
Zhao, J., Xu, C., Chi, P., & Xie, Y. (2015) · IPSJ Transactions on System and LSI Design Methodology · doi:10.2197/ipsjtsldm.8.2 · Cited by 20
Garbin, D., Rafhay, Q., Vianello, E., Jeannot, S., Candelier, P., de Salvo, B., Ghibaudo, G., & Perniola, L. (2015) · Joint International EUROSOI Workshop and International Conference on Ultimate Integration on Silicon · doi:10.1109/ulis.2015.7063789 · Cited by 20
“Nonvolatile oxide-based resistive RAM (OxRAM) technology is a good candidate for the replacement of Flash technology due to their low operating current (sub-500 nA), switching time (< 10 ns), good endurance (10(11) cycles), high scalability (10×10 nm(2)) and high density (16Gb) [1-5].”
BackgroundBenefit of Al2O3/HfO2 bilayer for BEOL RRAM integration through 16kb memory cut characterization
Azzaz, M., Benoist, A., Vianello, E., Garbin, D., Jalaguier, E., Cagli, C., Charpin, C., Bernasconi, S., Jeannot, S., Dewolf, T., et al. (2015) · European Solid-State Device Research Conference · doi:10.1109/essderc.2015.7324765 · Cited by 17
“Other studies showed that inserting a thin Al2O3 layer inbetween the HfO2 switching layer and the metallic bottom electrode allows to improve the memory window as well as the operating current (down to the sub-μA current operating regime) [8].”
BackgroundAnalog high resistance bilayer RRAM device for hardware acceleration of neuromorphic computation
Jacobs-Gedrim, R. B., Agarwal, S., Goeke, R. S., Smith, C., Finnegan, P. S., Niroula, J., Hughart, D. R., Kotula, P. G., James, C. D., & Marinella, M. J. (2018) · Journal of Applied Physics · doi:10.1063/1.5042432 · Cited by 17
Emerging resistive memories for low power embedded applications and neuromorphic systems
DeSalvo, B., Vianello, E., Thomas, O., Clermidy, F., Bichler, O., Gamrat, C., & Perniola, L. (2015) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas.2015.7169340 · Cited by 14
ZnSnOy/ZnSnOx Bilayer Transparent Memristive Synaptic Device for Neuromorphic Computing
Kumar, D., Saleem, A., Keong, L. B., Singh, A., Wang, Y., & Tseng, T. (2022) · IEEE Electron Device Letters · doi:10.1109/led.2022.3186055 · Cited by 15
From Memory in our Brain to Emerging Resistive Memories in Neuromorphic Systems
DeSalvo, B., Vianello, E., Garbin, D., Bichler, O., & Perniola, L. (2015) · IEEE International Memory Workshop (IMW) · doi:10.1109/imw.2015.7150286 · Cited by 12
Huang, J., Stathopoulos, S., Serb, A., & Prodromakis, T. (2022) · Frontiers in Nanotechnology · doi:10.3389/fnano.2022.851856 · Cited by 17
“Memristors feature the potential for extreme downscaling (Khiat et al., 2016), back-end-of-line (BEOL) integrability (Xia et al., 2009), sub-ns switching capability (Choi et al., 2016) and very low switching energy (Goux et al., 2012).”
BackgroundBan, S., & Kim, O. (2014) · Japanese Journal of Applied Physics · doi:10.7567/jjap.53.06je15 · Cited by 12
Correlated Effects on Forming and Retention of Al Doping in HfO2-Based RRAM
Alayan, M., Vianello, E., de Salvo, B., Perniola, L., Padovani, A., & Larcher, L. (2017) · IEEE Design & Test · doi:10.1109/mdat.2017.2682246 · Cited by 11
“the sub-μA current operating regime) [8,9].”
Total Dose Hardness of ${\rm TiN}/{\rm HfO}_{\rm x}/{\rm TiN}$ Resistive Random Access Memory
Morgan, K. A., Huang, R., Potter, K., Shaw, C., Redman-White, W., & de Groot, C. H. (2014) · IEEE Transactions on Nuclear Science · doi:10.1109/tns.2014.2365058 · Cited by 11
Role of nitrogen incorporation into Al2O3-based resistive random-access memory
Yang, M. Y., Kamiya, K., Shirakawa, H., Magyari‐Köpe, B., Nishi, Y., & Shiraishi, K. (2014) · Applied Physics Express · doi:10.7567/apex.7.074202 · Cited by 11
Ultralow power switching of Ta2O5/AlOX bilayer synergistic resistive random access memory
Li, C., Wang, F., Hu, K., Li, W.-X., Zhao, J.-S., Ren, T.-L., Song, Z., & Zhang, K.-L. (2020) · Journal of Physics D: Applied Physics · doi:10.1088/1361-6463/ab8b02 · Cited by 6
Egorov, K. V., Kuzmichev, D. S., Sigarev, A. A., Miakota, D. I., Zarubin, S., Chizov, P. S., Perevalov, T. V., Gritsenko, V. A., Hwang, C. S., & Markeev, A. M. (2018) · Journal of Materials Chemistry C · doi:10.1039/c8tc00679b · Cited by 9
An 8-bit Radix-4 Non-Volatile Parallel Multiplier
Fu, C., Zhu, X., Huang, K., & Gu, Z. (2021) · Electronics · doi:10.3390/electronics10192358 · Cited by 9
Chen, C. Y., Goux, L., Fantini, A., Degraeve, R., Redolfi, A., Groeseneken, G., & Jurczak, M. (2016) · Solid-State Electronics · doi:10.1016/j.sse.2016.05.008 · Cited by 8
Self-citationDual bipolar resistive switching in the sub-forming regime of HfO2 resistive switching devices
Recher, S., Yalon, E., Ritter, D., Riess, I., & Salzman, J. (2015) · Solid-State Electronics · doi:10.1016/j.sse.2015.04.002 · Cited by 8
Ning, S., Iwasaki, T. O., & Takeuchi, K. (2014) · Solid-State Electronics · doi:10.1016/j.sse.2014.10.003 · Cited by 7
Modeling of resistive random access memory (RRAM) switching mechanisms and memory structures
Kamiya, K., Yang, M. Y., Magyari‐Köpe, B., Nishi, Y., & Shiraishi, K. (2014) · Elsevier eBooks · doi:10.1533/9780857098092.2.262 · Cited by 6
Lin, C., Wu, Y., Hung, T.-H., & Chang, Y.-T. (2014) · IEEE Transactions on Nanotechnology · doi:10.1109/tnano.2014.2323198 · Cited by 6
“In fact, many binary and ternary oxides such as TiO2 [1]–[3], ZrO2 [4]–[6], HfO2 [7]–[9], CuxO [10], SrTiO3 [11], and ZrTiOx [12] have been found to have resistive switching behaviors and demonstrate desirable characteristics.”
BackgroundSinha, P., & Raj, S. (2022) · International Conference on Computer Aided Design · doi:10.1145/3508352.3549448 · Cited by 7
“To take into account the older process used in previous work, we have used an older 70 nm crossbar with a 10 fJ switching energy for comparisons [1, 11].”
MethodBACH: A Bandwidth-Aware Hybrid Cache Hierarchy Design with Nonvolatile Memories
Zhao, J., Xu, C., Zhang, T., & Xie, Y. (2016) · Journal of Computer Science and Technology · doi:10.1007/s11390-016-1609-7 · Cited by 5
“When H-tree delay unveils at large capacities, STT-MRAM and ReRAM (with small cell sizes) become faster than SRAM.”
BackgroundInfluentialTransition metal attenuated mechanism for protective alumina formation from first principles
Babic, V., Geers, C., & Panas, I. (2018) · RSC Advances · doi:10.1039/c8ra08195f · Cited by 4
Resistive switching characteristics of Co2FeSi and Mn with Al2O3 granular nanocomposites
Talaeizadeh, M., Jamilpanah, L., Ebrahimi, S. A. S., & Mohseni, S. M. (2020) · Journal of Magnetism and Magnetic Materials · doi:10.1016/j.jmmm.2020.167336 · Cited by 4
Redox-Based Memristive Devices
Rana, V., & Waser, R. M. (2013) · Springer eBooks · doi:10.1007/978-1-4614-9068-5_7 · Cited by 5
In-memory Machine Learning using Adaptive Multivariate Decision Trees and Memristors
Chavan, A., Sinha, P., & Raj, S. (2024) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas58744.2024.10557852 · Cited by 3
Architecture and Technology of Neuromorphic Memristive Chips
Andreeva, N. V., Luchinin, V. V., Ryndin, E. A., Anchkov, M. G., Romanov, A. A., Чигирев, Д. А., Mazing, D. S., Gerasimova, M. I., Sevost’yanov, E. N., Trushlyakova, V. V., et al. (2022) · Nanobiotechnology Reports · doi:10.1134/s2635167622070035 · Cited by 2
Engineering of a TiN\Al2O3\(Hf, Al)O2\Ta2O5\Hf RRAM cell for fast operation at low current
Chen, C. Y., Goux, L., Fantini, A., Degraeve, R., Redolfi, A., Groeseneken, G., & Jurczak, M. (2015) · European Solid-State Device Research Conference · doi:10.1109/essderc.2015.7324764 · Cited by 2
“Note that the reason why nanometer-thick oxide layers are used is that the overall oxide-stack thickness should remain low for fast programming at low current [7,14].”
BackgroundSelf-citationIn-Memory Machine Learning Using Hybrid Decision Trees and Memristor Crossbars
Chavan, A., Sinha, P., & Raj, S. (2023) · IEEE International Symposium on Smart Electronic Systems (iSES) · doi:10.1109/ises58672.2023.00058 · Cited by 2
“The memristors used are the ones synthesized by Goux et al. which have energy utilization and cell width of 10 fJ and 70 nm respectively [41].”
MethodRethinking the memory hierarchy design with nonvolatile memory technologies
Zhao, J. (2014) · Cited by 1
Conductive Filaments: Formation, Observation and Manipulation
Celano, U. (2016) · Springer theses · doi:10.1007/978-3-319-39531-9_4 · Cited by 1
Neuromorphic Functional Modules of a Spiking Neural Network
Ryndin, E. A., Andreeva, N. V., Luchinin, V. V., Goncharov, K. S., & Raiimzhonov, V. S. (2022) · Nanobiotechnology Reports · doi:10.1134/s2635167622070175 · Cited by 1
“…very large-scale integration (CMOS-VLSI) [14, 23]; ● short switching time between the high-resistance and low-resistance states (85 ps for nitride-based memristors [24]); ● resistance to cyclic degradation; ● low power consumption (switching energy of less than 10 fJ [25]).”
BackgroundVeendrick, H. J. M. (2017) · Springer eBooks · doi:10.1007/978-3-319-47597-4_6
Veendrick, H. J. M. (2024) · Springer eBooks · doi:10.1007/978-3-031-64249-4_6
Multilevel, High Resistance Switching in Al 2 O 3 /TiO 2 Bilayer RRAM Devices
Timbie, D., Choi, H., Bianconi, S., Cheng, S., Ling, L., & Mohseni, H. (2026) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2026.3674821
“This Al 2 O 3 layer has been shown to enable more consistent filament formation and lower read currents [30], [31].”
Minvielle, M. (2017) · theses.fr (ABES) · doi:10.70675/30e2fd37z4e73z4c48zbb79z240c96cc0a60
Fully Sputtered HfO y /HfO x RRAM: Improved Synaptic Behavior for Neuromorphic Training Accelerators
Kim, Y., Jeon, S., Lim, S., & Woo, J. (2026) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2026.3714373
“4(b) [32], [33].”
Metadata
- Authors
- Goux, L., Fantini, A., Kar, G., Chen, Y.-Y., Jossart, N., Degraeve, R., Clima, S., Govoreanu, B., Lorenzo, G., Pourtois, G., Wouters, D. J., Kittl, J. A., Altimime, L., & Jurczak, M.
- Affiliations
- IMEC (BE)
- Venue
- 2012 Symposium on VLSI Technology (VLSIT)
- Publisher
- IEEE
- Published
- 2012-06
- Pages
- 159-160
- OpenAlex
- W2130388397
- Cited by
- 67
- References
- 2
- Citations by year
- 2026: 2 · 2024: 3 · 2023: 2 · 2022: 5 · 2021: 2 · 2020: 4 · 2019: 1 · 2018: 4 · 2017: 7 · 2016: 7 · 2015: 13 · 2014: 14 · 2013: 3
- FWCI
- 12.25
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Symposium on VLSI Technology (publishedVersion)
- Topics
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Memory and Neural Computing
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Ferroelectric and Negative Capacitance Devices
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Semiconductor materials and devices
- Keywords
- resistive random access memory, Al2O3 interlayer, tin anode
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.