After the press release of the CJEU on its Judgment, “shocked” (Michalopoulos, 2018; Science Media Centre, 2018) and “disappointing” (Callaway, 2018: 16; Science Media Centre, 2018) were likely the words best summarizing the mood of the industry and scientists. Since then, beyond some scarce exceptions in which scholars have shown a greater awareness toward the difficult task of the Court [see, e.g., Leyser (2018) and Purnhagen et al. (2018a)], the Judgment and the EU legal regime on GMO have been the target of a general criticism, not only from the Academia and the industry [see, e.g., Michalopoulos (2018) and Urnov et al. (2018)] but also from within EU institutions [see SAM (2018) and Michalopoulos (2019)]. Indeed, after the positive expectations created by the Opinion of Advocate General Bobek (Callaway, 2018; Michalopoulos, 2018; Purnhagen et al., 2018a; Science Media Centre, 2018; Marks and Livingstone, 2019), the Judgment does not bring good news to plant breeders and the agricultural sector (Michalopoulos, 2018; Purnhagen et al., 2018a; Science Media Centre, 2018; Urnov et al., 2018). However, it needs to be noted that the approach of the Court toward NBT, aligned with “the Applicants [Confédération paysanne and Others] together with the French Government” (Opinion of Advocate General Bobek, para 87), is coherent with the European understanding of the precautionary principle in this field as well as with recital 17 Directive 2001/18/EC [anticipated by legal scholars like Krämer (2015) and Spranger (2015), and noticed also by Purnhagen et al. (2018a) and Eriksson (2018)]. Certainly, the role of recital 17 Directive 2001/18/EC acknowledged by the Court contradicts the approach of the Advocate General to recital 17 Directive 2001/18/EC based on historical interpretation (cf. paras 90 ff of the Opinion of the Advocate General with paras 44, 51, 54 and the conclusion of the Judgment). However, historical interpretation is far from being the usual approach of the CJEU (Rösler, 2012; Scholz and Cunha, 2017; Purnhagen et al. 2018a). That art 3(1) Directive 2001/18/EC is to be interpreted “strictly” (para 41 of the Judgment) was already anticipated by Krämer (2015) and Spranger (2015). Besides, the need to take into account “the context [ … ] and the objectives pursued by the rules of which it is part” (Judgment, para 42) and the principle of narrow interpretation of exemptions (Judgment, para 41), are well known rules of legal interpretation in the EU [see, e.g., Scholz (2012a; 2012b) and Beck (2012)] and was also anticipated by Krämer (2015) and Spranger (2015). In fact, the conclusions and reasoning of the Court were anticipated by Krämer (2015) and Spranger (2015) to a large extent. In the light of the foregoing, the Judgment, at least as regards its conclusions on NBT, can hardly be deemed groundless from a legal perspective nor surprising. From a rational and a scientific perspective though, as manifested by some scholars [see, e.g., Leyser (2018) or Purnhagen et al. (2018a)], the Judgment is just as objectionable as the EU legal regime on GMO.

After the Judgment, the idea of a revision of the EU legal framework on GMO as a reaction to interpretation of the CJEU [see, e.g., Bioökonmierat (2018); Michalopoulos (2019) and Urnov et al. (2018)] gained momentum, resulting in the “Statement by the Group of Chief Scientific Advisors” ⁵ [see SAM (2018)]. However, in the current European context as regards GMO, defined by Directive (EU) 2015/412, ⁶ Commission Implementing Decision (EU) 2016/321 of 3 March 2016, ⁷ and by the Judgment itself, this headlong rush toward a new GMO legal framework does not seem to have much chances of success in the short term [see also Purnhagen et al. (2018b)]. In fact, hastiness might contribute to further intensify polarization of public opinion in Europe on this issue [see, e.g., in this respect Gelinsky and Hilbeck (2018); Noisette (2019) and Antoniou (2019)] “reducing the possibility of breaking deadlock” (Mandel, 2005: 168) in the short to medium term. Furthermore, it also seems to have unintentionally prevented a sober analysis of some aspects of the Judgment that might have relevant implications on plant breeding and agriculture.

The application before the Conseil d'État (the French court that referred the questions for preliminary ruling) requested to “revoke Article D. 531-2 of the Environmental Code, transposing Directive 2001/18, which excludes mutagenesis from the definition of techniques giving rise to genetic modification within the meaning of Article L. 531-1 of the code, and ban the cultivation and marketing of herbicide-tolerant rape varieties obtained by mutagenesis” (Judgment, para 20). Therefore, the request was not focused on NBT but on herbicide tolerant crops (Eriksson, 2018; Leyser, 2018) and on mutagenesis (Purnhagen et al., 2018a; 2018b) in a broad sense. Furthermore, as acknowledged by the Conseil d'État, “[t]he only herbicide resistant seeds registered in the common catalogue of varieties of agricultural plant species are the result of in vitro random mutagenesis. [ … ] no variety of herbicide resistant seed resulting from the directed mutagenesis techniques has yet been included in the common catalogue” (Opinion, para 25). Besides, the Decision of the Conseil d'État, the Opinion of Advocate General Bobek, and the Judgment itself have all of them a broader scope than strictly NBT. Even the heading of the press release of the CJEU on the Judgment [see CJEU (2018)] refers to mutagenesis in a broad sense, not only to NBT. In fact, the conclusions of the Court in its Judgment deal more on mutagenesis lato sensu and even on the concept of GMO, than on NBT. However, after the Judgment, most of the scientific publications [see, e.g., Callaway (2018) and Purnhagen et al. (2018a)] and press publications [see, e.g., The Irish Times (2019); Marks and Livingstone (2019) or Zimmere (2018)] focused mainly on the impacts of the Judgment on NBT, not on mutagenesis in a broad sense. In the end, the Judgment itself has come to be known as the “ruling on new breeding techniques” [see, e.g., Opoku Gakpo (2018) or Devuyst (2018)]. As shown in the following paragraphs, this bias in the interpretation of the Judgment might be involuntarily concealing some relevant potential effects of the Judgment on plant breeding and free trade in the EU that should be known and, where appropriate, adequately addressed.

Due to the shift of attention toward NBT above described, potential implications of the Judgment on traditional techniques of random mutagenesis and varieties thereof have been generally overlooked or misinterpreted [among the very few exceptions see Martin in Science Media Centre (2018), Gelinsky and Hilbeck (2018), CIOPORA (2018), Wanner et al. (2019), or Jorasch (2019)].

The Conseil d'État, in its third question referred for a preliminary ruling, asked the CJEU whether “[a]rticles 2 and 3 of [sic.] and Annex I B to Directive [2001/18] on the deliberate release into the environment of [GMOs] constitute [ … ] a full harmonization measure prohibiting Member States from subjecting organisms obtained by mutagenesis to all or some of the obligations laid down in the directive or to any other obligation, or do the Member States, when transposing those provisions, have a discretion to define the regime to be applied to organisms obtained by mutagenesis” (para 25 of the Judgment). The Judgment concludes that “[a]rticle 3(1) of Directive 2001/18 [ … ] does not have the effect of denying Member States the option of subjecting such organisms [ … ] to the obligations laid down in that directive or to other obligations” (para 82).

The Court justified its positioning by arguing that “to the extent to which the EU legislature has not regulated those organisms, Member States have the option of defining their legal regime” (para 79), with the only limitation of “compliance with EU law, in particular the rules on the free movement of goods set out in Articles 34 to 36 TFEU” (para 79). This conclusion apparently stems from art 5(3) of the Treaty of the European Union (TEU) and art 2(2) TFEU; i.e., from the principle of subsidiarity and the rules applying to shared competences [see also Purnhagen et al. (2018b)]. Such interpretation has been already well described by the legal literature in relation to the EU legal regime on GMO [see, e.g., Sadeleer (2014) and Weimer (2019)] and was implicitly acknowledged by the Court in previous cases, like Pioneer Hi Bred Italia. ⁸ However, in Pioneer Hi Bred Italia the Court, even if bound by the same legal principles than in Confédération paysanne and Others, decides just in the opposite direction. The main reason motivating these diverging decisions seemingly derives from the fact that in Pioneer Hi Bred Italia the Court appreciates the “harmonized” (Pioneer Hi Bred Italia, para 5) nature of the matter at issue, while in Confédération paysanne and Others it does not (see Confédération paysanne and Others, para 79: “to the extent to which the EU legislature has not regulated those organisms [ … ]”). Be that as it may, the interpretation of the Court in Confédération paysanne and Others was not the only possible reading of Directive 2001/18/EC in relation to mutagenesis.

The Advocate General in its Opinion (see paras 115–117) frames two scenarios that in his view might explain the legislative positioning of the EU legislature in relation to mutagenesis: (a) “the EU legislature made a legislative choice. It carried out an evaluation, and on the basis of that evaluation came to the conclusion that all the mutagenesis techniques are to be excluded because they are safe” (Opinion, para 116); or, (b) “by inserting the mutagenesis exemption, the EU legislature did not make any statement about its safety” (para 117). The Advocate General compares the role of the EU legislature in the first scenario with that of “an architect that decided to have a room called ‘mutagenesis' in his house, but who also decided to keep that room empty” (para 116); while in the second scenario, according to the Advocate General, “the architect effectively decided to leave that space called ‘mutagenesis' outside his house” (para 117). The first scenario amounts to full harmonization (see para 116 of the Opinion), while the second scenario would represent a lack of harmonization (see para 117 of the Opinion). Such scheme stems from the legal reasoning formerly mentioned (deriving from arts 5(3) TEU and 2(2) TFEU) on the basis of the equilibrium on which the EU regime on GMO is built [i.e., the compromise between “[t]he protection of human health and the environment” (recital 5 Directive 2001/18/EC) and the principles governing the internal market in the EU (Salvi, 2016)]. However, the Court does not follow any of the options framed by the Advocate General. Instead, the Court decides to square the circle. Indeed, like the Advocate General, the Court is of the opinion that “the EU legislature has not regulated those organisms” (Judgment, para 79), but it assumes a safety assessment of the EU legislature as regards mutagenesis, manifested in recital 17 (see Judgment, paras 44, 45, 51, 54 and conclusion). In other words, the Court interprets art 3(1), Annex I B (1) and recital 17 Directive 2001/18/EC as a minimum threshold of harmonization (Purnhagen et al., 2018b), and therefore, according to the logic set in art 2(2) TFEU: “Member States shall again exercise their competence to the extent that the Union has decided to cease exercising its competence.” Recouping the example of the Advocate General in its Opinion, “the EU legislator would be like an architect that decided to have a room called ‘mutagenesis' in his house” (Opinion, para 116), but that instead of taking the decision “to keep that room empty” [as framed by the Advocate General (Opinion, para 116)], simply left it this way, and therefore, implicitly allowed EU Member States to furnish it (see Judgment, paras 44, 45, 51, 54, 79 and conclusion).

It could be argued that what the Court really has done is to transform an implicit preemption of action of Member States allegedly stemming from recital 17 Directive 2001/18/EC [equivalent to the above mentioned first scenario framed by the Advocate General (Opinion, para 116)], in a renounce of the EU legislature to regulate GMO obtained by means of traditional techniques of random mutagenesis. This interpretation is supported by the very late appearance of a case like Confédération paysanne and Others. In other words, if the possibility of traditional mutagenesis being regulated at a national level needed the pronunciation of the Court after so many years, then maybe the scenario of the EU legislature fully harmonizing those techniques should have been seriously considered by the Court as the most plausible option. However, this line of reasoning is somehow countered by the disharmonizing effect of Directive (EU) 2015/412 on the EU legal regime on GMO [see the Opinion of the Advocate General, para 122, Salvi (2016), Purnhagen et al. (2018b) and Wanner et al. (2019)], and, most importantly, this was not the interpretative path taken by the Court.

From the Judgment onwards, three categories of organisms matter in practice: (1) non-GMO; (2) GMO mentioned in art 3(1) Directive 2001/18/EC obtained through traditional techniques of random mutagenesis; (3) GMO falling within art 2(2) Directive 2001/18/EC [among which, according to the Court, organisms obtained by means of NBT are included (Urnov et al., 2018)]. Before the Judgment, varieties obtained by means of traditional techniques of random mutagenesis were claimed to be “an independent third category due to aspects of risk evaluation” (Spranger, 2015: 25), but that view is not clearly recognized in Directive 2001/18/EC, and there was no legal certainty on this issue until the Judgment. As observed by some scholars and breeders' associations [see, eg, Martin in Science Media Centre (2018); Gelinsky and Hilbeck (2018); CIOPORA (2018); Wanner et al. (2019), or Jorasch (2019)], from now on, according to the Judgement, GMO obtained by means of traditional mutagenesis will be able to be subjected by EU Member States “to the obligations laid down in that directive or to other obligations” (para 82 and conclusion 3). The Court is silent on GMO obtained through cell fusion (point (2) of Annex I B Directive 2001/18/EC), but it is foreseeable the interpretation of the Court extends to them.

This “reclassification” done by the Court might have in turn important implications. Indeed, because of the reference of the Court “to the obligations laid down in that directive [Directive 2001/18/EC] or to other obligations” (para 82 and conclusion 3), Member States might regulate the risk assessment of such varieties or its labelling at a national level, or subject them to other conditions and limitations. Furthermore, it cannot be ruled out that, as a result of the Judgment in connection to Directive (EU) 2015/412, the cultivation of such varieties end restricted or even prohibited at a national level in the same way as GM varieties within the scope of Directive 2001/18/EC [on the analysis of Directive (EU) 2015/412 see, e.g., Salvi (2016)]. In fact, in the light of the Judgment, mutant varieties bred through random mutagenesis might end being subjected “to other [national] national obligations” (para 82 and conclusion 3) potentially stricter and more burdensome than those stemming from Directive 2001/18/EC. It is clear from the aforesaid that the decision of the Court, in addition to further disharmonizing GMO regulation in the EU (Wanner et al., 2019), might also result, despite the condition introduced by the Court [of “compliance with EU law, in particular with the rules on the free movement of goods” (para 82)], in obstacles to the free movement of goods. If Member States end eventually following the possibility set by the CJEU as regards traditional mutant varieties, the free movement of goods [see Wanner et al. (2019)], plant innovation and agriculture [see Martin in Science Media Centre (2018)], and consumer choice in the EU, might be severely affected. Therefore, in that case, action should be taken at an EU level to reharmonize this area of the EU legal regime on GMO in order to impede or minimize the aforementioned potential negative impacts.

In a position paper issued before the Judgment, IFOAM stated that techniques falling within the category of “mutagenesis” are not “[a]cceptable for organic breeding” and “[t]o be phased out” (IFOAM Organics International, 2017: 20); and, shortly after the press release of the Judgment [see CJEU (2018)], showed its satisfaction with the position adopted by the Court [see IFOAM EU Group (2018b)]. However, after the Judgment, references to traditional mutagenesis (and to mutagenesis lato sensu) practically disappeared from IFOAM's communications [see, e.g., IFOAM EU Group (2018b) and IFOAM EU Group (2019)] despite IFOAM being apparently well aware of the potential reach of the Judgment [see, e.g., IFOAM EU Group (2018a)]. In the light of it, it cannot be excluded that the Court might have gone even further than some players of the organic sector wished. It must not be forgotten that at a worldwide level there are at least 3318 registered varieties obtained through traditional mutagenesis, 55% of them breed before 1990 (IAEA).

In Table 1 , the concept of GMO under Directive 2001/18/EC as interpreted by the Court is schematized through the criteria that may end with an exemption from the scope of Directive 2001/18/EC. Construed from the legal analysis of the Judgment carried out in this paper, Table 1 systematizes the interpretative efforts reflected in the literature [New Techniques Working Group (2012); Krämer (2015); Spranger (2015); Krämer (2015); Spranger (2015); Vives-Vallés (2016); Vives-Vallés (2018), Purnhagen et al. (2018a; 2018b), Sprink et al. (2016); Eriksson et al. (2018); Eriksson (2018); Wanner et al. (2019); Custers et al. (2019), etc.] and adapts them either to the situation post Judgment and/or to the purpose of the table. It is worth noting that the reasoning portrayed in Table 1 is not new, but it was already anticipated by Krämer (2015) and Spranger (2015) to a great extent. Krämer (2015) and Spranger (2015) detected already in 2015 that the key to understand the concept of GMO of Directive 2001/18/EC are not as much the descriptions contained in arts 2(2) and 3, but mainly the logical scheme set in those articles plus their annexes (i.e., whether the lists they refer to/contain are open or closed) interpreted in the light of the precautionary principle and recital 17 Directive 2001/18/EC. Some of these aspects have been also pointed out, before and after the Judgment, by other scholars [see, eg, New Techniques Working Group (2012); Vives-Vallés (2016) or Purnhagen et al. (2018a; 2018b)]. Therefore, according to the Court, how natural those techniques may be is not determinant (Custers et al., 2019) and the techniques listed in Annex I A Part 1 do not exhaust the notion of (nonexempted) GMO of art 2(2)(a) Directive 2001/18/EC. It is instead the inability of those techniques to fit in Annex I A Part 2 and Annex I B Directive 2001/18/EC, that matters the most (see Table 1 ). Certainly, the Court considered in its assessment the definition in art 2(2) Directive 2001/18/EC, mentioning in fact the three requirements it contains [i.e., “alterations made to the genetic material of an organism” (para 28 of the Judgment), “with the exception of human beings” (para 27), and “in a way that does not occur naturally” (para 29)]; but the two first requirements (in paras 27 and 28) are basically prerequirements, and the importance of the third requirement (in para 29) is somehow watered down by the reference of the Court to “the general scheme of that directive [Directive 2001/18/EC]” (para 31) developed in paras 31 to 37 of the Judgment. The consequence of this interpretation is that, as anticipated by Krämer (2015) and Spranger (2015), a technique will lead to a nonexempted GMO (falling within art 2(2)(a) in connection to Annex I A Part 1 Directive 2001/18/EC) if such technique cannot be classified in Annex I A Part 2 nor in Annex I B Directive 2001/18/EC (see Table 1 ). In other words, a dynamic interpretation of the annexes as regards the techniques covered by them is mandatory for Annex I A Part 1 and not possible for the other annexes (Spranger, 2015). It is worth mentioning that, as implicitly acknowledged by the Court (see Judgment, paras 27–38, 40), what is to be understood by “mutagenesis” has nothing to do with the use of “recombinant nucleic acids” (NA) or “genetically modified organisms” (Annex I B Directive 2001/18/EC). Besides, for a GMO produced by means of mutagenesis to be excluded from the scope of Directive 2001/18/EC, in addition to the fulfilment of recital 17, the “condition that they do not involve the use of recombinant nucleic acid molecules or GMOs other than those produced by one or more of the techniques/methods listed in that annex [Annex I B]” (Judgment, para 40) must also be met (see Table 1 ). This was also foreseen by Krämer (2015) and Spranger (2015) and observed after the Judgment by Eriksson (2018). The Judgment however, even if mentioning all these requirements from Annex I B and recital 17, does not elaborate on any of them. Regarding “the condition that they do not involve the use of recombinant nucleic acid molecules” (Annex I B Directive 2001/18/EC), Krämer (2015) explains that Council Directive 90/220/EEC does not contain it and that its inclusion in Directive 2001/18/EC must be understood as “a supplementary requirement [ … ] to enlarge the field of application of Directive 2001/18 and to reduce the exemption of Article 3 and Annex I B” (Krämer, 2015: 12). As regards recital 17, Directive 2001/18/EC does not provide any guidance on its interpretation (Krämer, 2015); but it makes sense to interpret it as containing two different, but cumulative (i.e., both of them must be fulfilled), requirements (Krämer, 2015). Fulfilling “a number of applications” only is not enough [see Krämer (2015)]. Additionally, those applications must “have a long safety record” [see Krämer (2015)]. Directive 2001/18/EC does not explain either how recital 17 must be assessed Krämer (2015). A reading of recital 17 Directive 2001/18/EC coherent with the Judgment [as well as with the position taken by Krämer (2015) and Spranger (2015)] suggests that, somehow, the first requirement in recital 17 (i.e., “a number of applications”) should refer to the diversity of the applications, while the second requirement in recital 17 (i.e., “a long safety record”) might be connected to the number of records within each application as well as to the proven degree of “safety” of each application. It also must be noted that Annex I B refers to “the use of recombinant nucleic acid molecules or genetically modified organisms” but not to “[t]echniques of genetic modification” like Annex I A Part 1; therefore, those techniques of genetic modification that “do not involve the use of recombinant nucleic acid molecules or genetically modified organisms” (as mandated in Annex I B) and fitting also within the scientific notion of “mutagenesis,” should be deemed potentially coverable by Annex I B [see also Purnhagen et al. (2018b)], subjected only to the fulfilment of the requirements in recital 17. Besides, according to the Judgment (see also Table 1 ), the techniques listed in Annex I B must be deemed always included in art 2(2)(a) Directive 2001/18/EC (see Judgment, paras 27–38), and only excluded from the scope of Directive 2001/18/EC as long as they meet the requirements stemming from recital 17 (paras 43–48) and mentioned in Annex I B Directive 2001/18/EC (para 40). The Judgment though, does not provide any guidance on what is to be understood by to “not involve the use of recombinant nucleic acid molecules or genetically modified organisms other than those produced by one or more of the techniques/methods listed” in Annex I B Directive 2001/18/EC; nor on how should the requirements in recital 17 Directive 2001/18/EC be assessed. The term “mutagenesis” is not addressed in the Judgment either.